Practice course resource playing method

Abstract

The invention discloses a practice course resource playing method, and belongs to the technical field of online education, and the practice course resource playing method comprises the following specific steps: 1, operation data real-time collection: obtaining a video, an action track and equipment state data of a user operation process through a camera, a sensor or an external device; 2, teaching resource intelligent analysis: carrying out structural splitting on course resources, and marking key knowledge points, operation nodes and expected behavior data; based on a real-time feedback mechanism of an operation behavior, the method is realized through a similarity function and a guidance information generation function, a dynamically adjusted intelligent playing strategy is realized through a playing mode switching function and an advanced learning path recommendation function, and meanwhile, multi-modal interaction and immersive learning support are provided; and realizing quantitative evaluation and personalized learning path planning through a learning effect evaluation function.

Description

Technical Field

[0001] The present invention belongs to the technical field of online education, and particularly relates to a method for playing practical course resources. Background Art

[0002] Practical course resources refer to the sum of various resources that support practical teaching activities, aiming to help students master skills and deepen theoretical knowledge through hands-on operations, simulation experiments, project practices, etc. The core goal of practical course resources is to narrow the gap between theory and practical application, help learners accumulate experience in real scenarios, and enhance their employment competitiveness.

[0003] The existing online teaching of practical courses (such as experimental operations, skill training, etc.) mostly relies on pre-recorded video resources, which have the following defects: it is impossible to adjust teaching content in real time according to the actual operations of students; there is a lack of personalized guidance and dynamic feedback mechanisms; the interaction form is single, making it difficult to meet the needs of complex practical scenarios. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the above-mentioned defects of the prior art and provide a method for playing practical course resources.

[0005] The technical solution adopted to solve the above technical problem is: a method for playing practical course resources, including the following specific steps:

[0006] Step 1: Real-time collection of operation data: Obtain video, action trajectories, and device status data of the user's operation process through a camera, sensor, or external device;

[0007] Step 2: Intelligent parsing of teaching resources: Structurally split the course resources, and mark key knowledge points, operation nodes, and expected behavior data;

[0008] Step 3: Real-time behavior analysis and guidance: First, compare the user's operation data with preset standard data to identify operation deviations, and then automatically generate and overlay guidance information on the playback screen;

[0009] Step 4: Dynamic adjustment of playback strategy: According to the operation analysis results, intelligently switch the playback mode and recommend an advanced learning path based on the user's level;

[0010] Step 5: Support for multi-modal interaction: Provide gesture control, voice commands, and AR / VR scene interaction operation methods;

[0011] Step 6: Evaluation of learning effect: Record operation data and generate an evaluation report, quantify the score, and provide feedback with improvement suggestions.

[0012] Through the above technical solutions, a real-time feedback mechanism based on operation behavior is implemented through a similarity function and a guidance information generation function. An intelligent playback strategy with dynamic adjustment is achieved through a playback mode switching function and an advanced learning path recommendation function. At the same time, multi-modal interaction and immersive learning support are provided, and quantitative evaluation and personalized learning path planning are realized through a learning effect evaluation function.

[0013] Further, in the first step, the collected operation data set is set as D = {d1, d2, …, d n}, where n is the number of collected data items, and d i represents the i-th data item, including image frames, action coordinates, and device parameters.

[0014] Further, in the second step, the course resources are split into multiple teaching units U = {u1, u2, …, u m}, where m is the number of teaching units. Each u j teaching unit contains a key knowledge point set K j = {k j1 , k j2 , …, k jp}, an operation node set O j = {o j1 , o j2 , …, o jq} and an expected behavior data set E j = {e j1 , e j2 , …, e jr}.

[0015] Through the above technical solutions, the teaching content and students' operations can be quantified to better match the students' levels.

[0016] Further, in the third step, let the current teaching unit be u j , its expected behavior data set be E j , and the user operation data set be D. Define a similarity function S(d i , e jk ) to measure the similarity between the user operation data and the expected behavior data. The specific formula is as follows:

[0017]

[0018] where s is the dimension of the data. For each operation data d i , find the expected behavior data e jk with the highest similarity to it. If S(d i , e jk ) < θ, it is considered that there is an operation deviation.

[0019] Through the above technical solution, it is possible to accurately recognize whether there are deviations in the operations of students.

[0020] Furthermore, the generation of the guidance information in step three adopts the following formula:

[0021] According to the type and severity of the operation deviation, a guidance information generation function G is defined. For an operation deviation g, whose type belongs to t and the severity is r, then g = G(t, r).

[0022] Furthermore, the switching of the playback mode adopts the following formula:

[0023] Set the number of operation deviations as N b , define the playback mode switching function P(N b ), then:

[0024]

[0025] where N1 and N2 are preset deviation quantity thresholds;

[0026] The recommendation of the advanced learning path adopts the following formula:

[0027] Let the user operation accuracy rate be where N c is the number of correct operations, N total is the total number of operations. According to the accuracy rate A, define the advanced learning path recommendation function R(A);

[0028]

[0029] where A1 and A2 are accuracy rate thresholds.

[0030] Through the above technical solution, it is possible to recommend courses more accurately according to the level of students.

[0031] Furthermore, the evaluation of the learning effect adopts the following formula:

[0032] Let the operation accuracy rate be A, the operation completion time be T, and the operation complexity be C. Define the learning effect evaluation function L(A, T, C):

[0033]

[0034] where w1, w2, and w3 are weight coefficients, and w1 + w2 + w3 = 1, T min is the shortest completion time of this operation.

[0035] Through the above technical solution, it is possible to quantify the learning effect, so as to better plan the learning path.

[0036] The beneficial effects of the present invention are as follows: Based on the real-time feedback mechanism of operation behavior, the present invention is implemented through a similarity function and a guidance information generation function, and realizes an intelligent playback strategy with dynamic adjustment through a playback mode switching function and an advanced learning path recommendation function. At the same time, it provides multi-modal interaction and immersive learning support, and realizes quantitative evaluation and personalized learning path planning through a learning effect evaluation function. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0039] As Figure 1 shown, a method for playing practical course resources in this embodiment includes the following specific steps:

[0040] Step 1: Real-time collection of operation data: Obtain video, action trajectories, and device status data of the user's operation process through a camera, sensor, or external device;

[0041] Step 2: Intelligent parsing of teaching resources: Structurally split the course resources, and mark key knowledge points, operation nodes, and expected behavior data;

[0042] Step 3: Real-time behavior analysis and guidance: First, compare the user's operation data with preset standard data to identify operation deviations, and then automatically generate and superimpose guidance information on the playback screen;

[0043] Step 4: Dynamic adjustment of the playback strategy: According to the operation analysis results, intelligently switch the playback mode and recommend an advanced learning path based on the user's level;

[0044] Step 5: Multi-modal interaction support: Provide gesture control, voice commands, and AR / VR scene interaction operation methods;

[0045] Step 6: Learning effect evaluation: Record operation data and generate an evaluation report, quantitatively score and feedback improvement suggestions. Based on the real-time feedback mechanism of operation behavior, an intelligent playback strategy with dynamic adjustment is realized through a similarity function and a guidance information generation function, and at the same time, multi-modal interaction and immersive learning support are provided. Quantitative evaluation and personalized learning path planning are realized through a learning effect evaluation function.

[0046] Let the set of operation data collected in Step 1 be D = {d1, d2,..., dn}, where n is the number of data items collected, and d i represents the i-th data item, including an image frame, action coordinates, and device parameters.

[0047] In the second step, the course resources are split into multiple teaching units U = {u1, u2,..., u m}, where m is the number of teaching units, and each u j teaching unit contains a set of key knowledge points K j = {k j1 , k j2 ,..., k jp}, a set of operation nodes O j = {o j1 , o j2 ,..., o jq} and a set of expected behavior data E j = {e j1 , e j2 ,..., e jr}, which can quantify the teaching content and students' operations and better match the students' levels.

[0048] In the third step, let the current teaching unit be u j , and its set of expected behavior data be E j , and the set of user operation data be D. Define a similarity function S(d i , e jk ) to measure the similarity between the user operation data and the expected behavior data. The specific formula is as follows:

[0049]

[0050] where s is the dimension of the data. For each operation data d i , find the expected behavior data e jk with the highest similarity to it. If S(d i , e jk ) < θ, it is considered that there is an operation deviation, and it is possible to accurately recognize whether there is an operation deviation in the students' operations.

[0051] In the third step, the generation of guidance information adopts the following formula:

[0052] According to the type and severity of the operation deviation, define a guidance information generation function G. For an operation deviation g, whose type belongs to t and the severity is r, then g = G(t, r).

[0053] The switching of the playback mode adopts the following formula:

[0054] Set the number of operation deviations to N b , and define a playback mode switching function P(Nb ) then:

[0055]

[0056] where N1 and N2 are preset deviation quantity thresholds;

[0057] The advanced learning path recommendation adopts the following formula:

[0058] Let the user operation accuracy rate be where N c is the number of correct operations, and N total is the total number of operations. According to the accuracy rate A, define the advanced learning path recommendation function R(A);

[0059]

[0060] where A1 and A2 are accuracy rate thresholds, and courses can be recommended more accurately according to the student level.

[0061] The learning effect evaluation adopts the following formula:

[0062] Let the operation accuracy rate be A, the operation completion time be T, and the operation complexity be C. Define the learning effect evaluation function L(A, T, C):

[0063]

[0064] where w1, w2, and w3 are weight coefficients, and w1 + w2 + w3 = 1, and T min is the shortest completion time of this operation, which can quantify the learning effect and thus better plan the learning path.

[0065] The above is only a preferred embodiment of the present invention and is not used to limit the protection scope of the present invention.

Claims

1. A method for playing practical course resources, characterized in that It includes the following specific steps: Step 1: Real-time collection of operation data: Obtain videos, action trajectories, and device status data of the user's operation process through cameras, sensors, or external devices; Step 2: Intelligent parsing of teaching resources: Structurally split the course resources, and label key knowledge points, operation nodes, and expected behavior data; Step 3: Real-time behavior analysis and guidance: First, compare the user's operation data with the preset standard data to identify operation deviations, and then automatically generate and overlay guidance information on the playback screen; Step 4: Dynamic adjustment of playback strategy: According to the operation analysis results, intelligently switch the playback mode and recommend an advanced learning path based on the user's level; Step 5: Support for multimodal interaction: Provide gesture control, voice commands, and AR / VR scene interaction operation methods; Step 6: Evaluation of learning effect: Record the operation data and generate an evaluation report, quantify the score, and feedback improvement suggestions.

2. The method for playing practical course resources according to claim 1, characterized in that, In the first step, the set of operation data collected is set as D = {d1, d2, …, d n}, where n is the number of data items collected, and d i represents the i-th data item, including an image frame, an action coordinate, and device parameters.

3. A method for playing practical course resources according to claim 2, characterized in that In the second step, the course resources are split into multiple teaching units U = {u1, u2, …, u m}, where m is the number of teaching units, and each u j teaching unit contains a set of key knowledge points K j = {k j1 , k j2 , …, k jp}, a set of operation nodes O j = {o j1 , o j2 , …, o jq} and a set of expected behavior data E j = {e j1 , e j2 , …, e jr}.

4. A method for playing practical course resources according to claim 3, characterized in that In step 3, let the current teaching unit be u j , and its expected behavior data set be E j , the user operation data set be D, and define a similarity function S(d i , e jk ) to measure the similarity between the user operation data and the expected behavior data. The specific formula is as follows: where s is the dimension of the data, for each operation data d i , find the expected behavior data e with the highest similarity to it jk , if S(d i , e jk ) < θ, it is considered that there is an operation deviation.

5. A method for playing practical course resources according to claim 4, characterized in that, The generation of the guidance information in Step 3 adopts the following formula: According to the type and severity of the operation deviation, define the guidance information generation function G. For the operation deviation g, whose type belongs to t and the severity is r, then g = G(t, r).

6. A method for playing practical course resources according to claim 5, characterized in that, The switching of the playback mode adopts the following formula: Set the number of operating deviations to N b , define the playback mode switching function P(N b ), then: where N1 and N2 are preset deviation quantity thresholds; The recommendation of the advanced learning path adopts the following formula: Let the user operation accuracy rate be where N c is the number of correct operations, and N total is the total number of operations. According to the accuracy rate A, define the advanced learning path recommendation function R(A); where A1 and A2 are accuracy thresholds.

7. A method for playing practical course resources according to claim 6, characterized in that, The evaluation of the learning effect adopts the following formula: Let the operation accuracy rate be A, the operation completion time be T, and the operation complexity be C. Define the learning effect evaluation function L(A, T, C): where w1, w2, and w3 are weight coefficients, and w1 + w2 + w3 = 1, and T min is the shortest completion time of this operation.

Images