Industrial robot programming teaching method and system

Abstract

The invention discloses an industrial robot programming teaching method and system, and belongs to the technical field of programming teaching, and the method specifically comprises the steps: collecting programming behavior data and industrial robot operation data in real time, generating learning state data of students according to the programming behavior data and the industrial robot operation data, and storing the learning state data of the students; the learning state data of the student comprises a programming behavior, a knowledge mastering degree and a learning style of the student, determining a knowledge point node embedding offset in combination with a preset dynamic knowledge graph according to the learning state data of the student, and updating the current dynamic knowledge graph according to the knowledge point node embedding offset, determining a current knowledge difficulty of the student based on the current dynamic knowledge graph, and pushing difficulty analysis data to a learning terminal of the student based on the current knowledge difficulty; according to the invention, accurate knowledge feedback for individual differences is realized, and the pertinence and efficiency of industrial robot programming teaching are effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of programming teaching, and in particular relates to an industrial robot programming teaching method and system. Background Art

[0002] With the development of intelligent manufacturing and industrial automation, industrial robots are increasingly being used in a variety of fields, including welding, handling, assembly, and painting. To meet the urgent demand for robot programming talent, various vocational education institutions, colleges and universities, and internal corporate training programs have all offered robot programming courses.

[0003] Existing methods for teaching industrial robot programming primarily rely on centralized instruction, task-driven training, and simulation-based operations. These methods suffer from the following shortcomings: a lack of real-time, personalized feedback, making it difficult for teachers to promptly identify each student's specific programming difficulties; difficulty accurately identifying cognitive barriers; and low efficiency in utilizing teaching resources. Therefore, a new method for teaching industrial robot programming is urgently needed.

[0004] For example, a Chinese patent with authorization announcement number CN116312147B discloses a programming teaching method and system based on a teaching robot, which includes: an electronic device sends a programming file to the teaching robot, the teaching robot queries a collection of picking strategies based on the target waste category to which the target object belongs, obtains an original picking strategy, and executes the original picking strategy based on a reference clamping force; when the electronic device determines that the teaching robot fails to pick up the target object, it outputs a first manual operation interface to obtain the target clamping force when the teaching robot successfully picks up the target object; determines a target clamping force range based on the target clamping force; the teaching robot obtains the target clamping force range from the electronic device, updates the reference clamping force range in the original picking strategy based on the target clamping force range, and saves the updated original picking strategy in the picking strategy collection. This can enhance the success rate of the teaching robot in picking up waste and comprehensively improve the user's programming and hands-on abilities.

[0005] The defects of the above patent are: lack of personalized feedback, difficulty in estimating students' current knowledge difficulties, and low teaching efficiency. Summary of the Invention

[0006] In view of the shortcomings of the existing technology, the present invention proposes an industrial robot programming teaching method and system.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] An industrial robot programming teaching method, comprising:

[0009] Real-time collection of programming behavior data and industrial robot operation data;

[0010] generating student learning status data based on the programming behavior data and the industrial robot operation data, wherein the student learning status data includes the student's programming behavior, knowledge mastery level, and learning style;

[0011] In combination with a preset dynamic knowledge graph, based on the student learning status data, a knowledge point node embedding offset is determined. The knowledge point node embedding offset is used to adjust the node association strength of the dynamic knowledge graph. The dynamic knowledge graph is based on the industrial robot programming knowledge graph and is constructed using a dynamic time-series graph neural network.

[0012] Update the current dynamic knowledge graph according to the knowledge point node embedding offset;

[0013] The student's current knowledge difficulties are determined based on the current dynamic knowledge graph, so as to push difficulty analysis data to the student's learning terminal based on the current knowledge difficulties.

[0014] Specifically, generating the student's learning status data based on the programming behavior data and the industrial robot operation data includes:

[0015] Arrange programming behavior data in chronological order, break it down into the smallest analyzable units, and form structured tabular data;

[0016] Use process verification methods to identify logical errors. According to the error pattern library, similar logical errors are aggregated to obtain logical error types, including syntax errors, logical vulnerabilities, and device adaptation errors. The error pattern library is constructed based on the industrial robot knowledge base.

[0017] Break down programming tasks into knowledge units, correspond them to the industrial robot programming knowledge graph, and dynamically evaluate students' knowledge mastery;

[0018] Extract students' behavioral characteristics and analyze their learning styles based on the extracted behavioral characteristics.

[0019] Specifically, the method of combining a preset dynamic knowledge graph and determining the embedding offset of a knowledge point node according to the student learning status data includes:

[0020] Based on the industrial robot knowledge base, build an industrial robot programming knowledge graph;

[0021] Based on the industrial robot programming knowledge graph, a dynamic knowledge graph is constructed using a dynamic time-series graph neural network. The network aggregates hierarchical time-series features through a time decay function and a double-loop propagation mechanism to update the edge weights of the dynamic knowledge graph.

[0022] Generate knowledge point node embedding offset based on students' learning status data.

[0023] Specifically, generating the knowledge point node embedding offset according to the student's learning status data includes:

[0024] According to the students’ learning status data, a mapping rule with the embedding offset of knowledge point nodes is established;

[0025] According to the above mapping rules, the knowledge point node embedding offset is calculated for each student's knowledge point node.

[0026] Specifically, according to the above mapping rules, the knowledge point node embedding offset is calculated for each student's knowledge point node, including:

[0027] Calculate the initial knowledge point node embedding offset through mapping rules and dynamic knowledge graph;

[0028] The initial embedding offset of each knowledge point node and the initial embedding offsets of its immediate predecessor and successor nodes are averaged over the neighborhood.

[0029] Repeat the calculation of the initial knowledge point node embedding offset and neighborhood steps until the maximum change amplitude of the knowledge point node is lower than the preset threshold;

[0030] The knowledge point node embedding offset output by the iteration is normalized as the final knowledge point node embedding offset.

[0031] Specifically, the calculation of the initial knowledge point node embedding offset through the mapping rule and the dynamic knowledge graph includes:

[0032] Count the performance differences of students on tasks related to knowledge point nodes, perform weighted summation on the performance differences, and obtain the difficulty measurement value of the knowledge point node;

[0033] According to the students' learning style, a style sensitivity coefficient is preset, and the difficulty measurement value of the knowledge point node is multiplied by the style sensitivity coefficient to obtain the initial knowledge point node embedding offset.

[0034] Specifically, updating the current dynamic knowledge graph according to the knowledge point node embedding offset includes: applying the calculated knowledge point node embedding offset to the dynamic knowledge graph, recalculating the distance and weight between nodes, and forming an individually differentiated dynamic knowledge graph.

[0035] An industrial robot programming teaching system, used to implement the aforementioned industrial robot programming teaching method, comprising: a data acquisition module, a state data generation module, an offset determination module, an update module, and a difficulty determination and resolution module;

[0036] The data acquisition module is used to collect programming behavior data and industrial robot operation data in real time;

[0037] The status data generating module is used to generate the student's learning status data based on the programming behavior data and the industrial robot operation data;

[0038] The offset determination module is used to determine the embedding offset of the knowledge point node according to the student learning status data in combination with the preset dynamic knowledge graph;

[0039] The updating module is used to update the current dynamic knowledge graph according to the embedding offset of the knowledge point node;

[0040] The difficulty determination and solution module is used to determine the student's current knowledge difficulties based on the current dynamic knowledge graph, so as to push difficulty analysis data to the student's learning terminal based on the current knowledge difficulties.

[0041] Specifically, the state data generation module includes: a disassembly unit and a state data generation unit;

[0042] The disassembling unit is used to arrange the programming behavior data in chronological order, disassemble it into the smallest analyzable units, and form structured table data;

[0043] The state data generating unit is used to analyze students' programming behaviors according to structured table data, and to evaluate students' knowledge mastery and learning styles.

[0044] Specifically, the offset determination module includes: a mapping rule establishment unit and an embedding offset unit;

[0045] The mapping rule establishing unit is used to establish a mapping rule with the knowledge point node embedding offset according to the student's learning status data;

[0046] The embedding offset unit is used to calculate the initial embedding offset according to the above mapping rule, and then perform neighborhood averaging and iteration.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] The present invention proposes a method and system for teaching industrial robot programming. By constructing a dynamic knowledge graph and introducing multi-dimensional learning behavior analysis and cognitive disorder inference mechanisms, it can collect students' programming process data in real time, dynamically adjust the association paths between knowledge points, and automatically infer students' current knowledge difficulties. The teacher's terminal or electronic blackboard presents teaching content that is highly matched with students' difficulties, realizing intelligent, differentiated and precise programming teaching, and significantly improving teaching efficiency, student mastery quality and the utilization rate of teaching resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flow chart of an industrial robot programming teaching method provided by the present invention;

[0050] Figure 2 A flow chart for generating student learning status data provided by the present invention;

[0051] Figure 3 Schematic diagram of calculation of embedding offset of knowledge point nodes provided by the present invention;

[0052] Figure 4 This is an architectural diagram of an industrial robot programming teaching method according to the present invention. DETAILED DESCRIPTION

[0053] The present application is described in detail below with reference to specific embodiments. The following embodiments will help those skilled in the art to further understand the present application, but are not intended to limit the present application in any form. It should be noted that those skilled in the art may make several variations and improvements without departing from the scope of the present application. These all fall within the scope of protection of the present application.

[0054] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0055] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other and are all within the scope of protection of the present application. In addition, although the functional modules are divided in the device schematic and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order than the module division in the device or the order in the flow chart. In addition, the words "first", "second", "third", etc. used in this application do not limit the data and execution order, but only distinguish between the same items or similar items with basically the same functions and effects.

[0056] Unless otherwise defined, all technical and scientific terms used in this specification have the same meanings as those commonly understood by those skilled in the art to which this application belongs. The terms used in this specification and in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" as used in this specification includes any and all combinations of one or more of the relevant listed items.

[0057] Example 1

[0058] See also Figure 1The present invention provides an embodiment of an industrial robot programming teaching method, comprising the following specific steps:

[0059] The electronic device sends a programming file to the teaching robot, wherein the programming file includes a control program written according to the programming teaching content;

[0060] Step S1: During the teaching process, real-time collection of programming behavior data and industrial robot operation data;

[0061] Specifically, when students operate in the virtual programming environment, the following data are recorded in real time: programming behavior data and industrial robot operation data;

[0062] Programming behavior data includes: instruction operation data, which records the programming instruction types selected by students, such as motion instructions, logical judgment instructions, sensor call instructions, etc., the instruction input order, and instruction parameter settings, such as movement speed, coordinate value, and number of loops; debugging behavior data, which counts the number of times students debug the program, the debugging time point, the location and content of code modifications during the debugging process, and feedback information on the program running results after debugging, such as success or failure, error type, etc.; learning interaction data, which monitors students' speech content, question frequency, and access records of learning materials in the software's online discussion area, including visit duration, number of visits, and specific material types, as well as interactive behaviors with teachers and classmates, such as the number of times they request guidance from teachers and their active participation in group discussions;

[0063] Through the real-time data transmission channel established between the software and the actual industrial robot equipment, relevant data of the industrial robot operation is obtained. The industrial robot operation data includes: robot status data, which collects information such as the robot's real-time position, movement speed, joint angle, torque size, etc., and analyzes the performance of the program written by students on the actual equipment; sensor data, which receives data feedback from device sensors (such as visual sensors and force sensors) to determine whether the student program processes the sensor signals correctly and whether the sensor data is reasonably used to achieve the task goals.

[0064] Step S2: generating student learning status data based on the programming behavior data and the industrial robot operation data, combining the preset dynamic knowledge graph, determining the knowledge point node embedding offset based on the student learning status data, updating the current dynamic knowledge graph based on the knowledge point node embedding offset, and determining the student's current knowledge difficulty based on the current dynamic knowledge graph;

[0065] The specific steps of step S2 are:

[0066] Step S201: constructing an industrial robot programming knowledge graph and establishing an error pattern library;

[0067] In this embodiment, the industrial robot programming knowledge system is sorted out, and knowledge points (such as kinematic principles, sensor applications, programming grammar rules, etc.) are constructed as knowledge graph nodes. The nodes are connected through logical relationships (such as association and application) to form a structured knowledge graph.

[0068] Collect a large number of student programming error cases, analyze the error types (such as syntax errors, logical errors, path planning errors, etc.), combine with relevant knowledge points in the knowledge graph, and establish a mapping relationship between error patterns and knowledge points, that is, an error pattern library. For example, the coordinate value out of range error corresponds to the coordinate system establishment and coordinate calculation knowledge point.

[0069] Step S202: Analyze the student's programming behavior, knowledge mastery, and learning style based on the pre-processed programming behavior data and industrial robot operation data;

[0070] The specific steps of step S202 are:

[0071] Step S2021: Arrange the pre-processed programming behavior data in chronological order, break it down into the smallest analyzable units, and form structured table data;

[0072] For example, a complete programming instruction is broken down into instruction type (such as motion control) + parameter setting (speed, coordinates) + execution result (success / error); debugging behavior is recorded as debugging time + modified code location + error prompt content, etc.

[0073] Step S2022: Use the process verification method to identify logical errors. According to the error pattern library, similar logical errors are aggregated to obtain logical error types, including syntax error, logical vulnerability, and device adaptation error.

[0074] In this embodiment, the process verification method includes basic rule checking, sequence rationality analysis, and parameter validity verification; basic rule checking verifies whether the programming instructions follow the basic logic of industrial robot programming, such as whether the motion instructions are used after the coordinate system is defined, and whether the initialization configuration is completed before calling the sensor; sequence rationality analysis analyzes whether the instruction combination meets the task objectives. For example, in a welding task, check whether the instruction sequence of moving to the welding point → starting welding → moving to the next welding point is correct. If it is reversed, it is marked as a logical error; parameter validity verification compares whether the instruction parameters are within the allowable range of the equipment, such as whether the movement speed exceeds the maximum speed limit of the robot, and whether the coordinate value exceeds the workspace;

[0075] The syntax error category classifies spelling errors and misuse of symbols (such as missing semicolons) as syntax errors, and analyzes instruction keywords with high-frequency errors, such as common format errors such as for loop statements; the logic vulnerability category identifies functional abnormalities caused by incorrect conditional judgments and chaotic loop nesting, and records typical error cases, such as an infinite loop caused by failure to set loop termination conditions; the device adaptation error category targets errors that occur during actual operation, such as motor overload and sensor signal loss, and associates possible causes in programming, such as load calculation errors and improper sensor data processing.

[0076] Step S2023: Decompose the programming task into knowledge units, correspond them to the industrial robot programming knowledge graph, and dynamically evaluate the student's knowledge mastery;

[0077] Specifically, programming tasks are broken down into knowledge units, which correspond to the industrial robot programming knowledge graph, including kinematics, control logic, and sensor applications. Kinematics-related tasks identify instructions involving forward and inverse kinematics calculations and trajectory planning, and associate them with basic kinematics knowledge nodes. Control logic-related tasks focus on the use of conditional judgments (if-else) and loop statements (while), corresponding to PLC programming logic nodes. Sensor applications analyze the code for sensor data acquisition, filtering, and threshold judgment, and map them to sensor principle and application nodes.

[0078] The dynamic assessment of students' knowledge mastery is specifically carried out using the learning trajectory tracking method, including: initial contact, when students try a certain type of knowledge point task for the first time, if the completion rate is less than 60% and the errors are concentrated in the core concepts, they are judged as not mastered; gradual improvement, through multiple practices, if the error rate decreases and they can solve similar problems independently, it is adjusted to preliminary mastery; in-depth understanding, when students can flexibly use knowledge points to solve complex tasks, such as multi-sensor fusion control, and have strong ability to apply knowledge to other situations, they are marked as proficiently mastered; forgetting warning, if students have not used a certain knowledge point for a period of time, the error rate in subsequent practice will rise again, triggering a knowledge consolidation reminder.

[0079] Step S2024: extracting the student's behavioral characteristics and analyzing the student's learning style based on the extracted behavioral characteristics.

[0080] In this embodiment, behavioral features are extracted from interaction data. Interaction data includes the materials accessed, questions asked, and debugging performed by students. Behavioral features include: material preferences, questioning patterns, and debugging habits. Material preferences are analyzed by counting the duration and frequency of students' access to different types of materials (video tutorials, illustrated manuals, and code examples) to determine their learning media preferences. Questioning patterns are analyzed by analyzing the content of students' questions in discussion forums to distinguish between basic help-seeking questions, such as how to set up a coordinate system, and extended exploratory questions, such as how to optimize paths to reduce energy consumption. Debugging habits are observed by observing students' debugging behaviors to distinguish between trial-and-error types (frequent, small code modifications) and systematic troubleshooting types (locating problems before making corrections).

[0081] Based on behavioral characteristics, students' learning styles are divided into four categories, including: visually oriented, who prefer to learn through video demonstrations and have a high acceptance of dynamic images; logical reasoning, who tend to read technical documents and are good at understanding programming logic from a principle level; practical exploration, who are accustomed to accumulating experience through repeated debugging and trial and error and have a strong interest in practical tasks; and social interaction, who rely on online discussions and teacher guidance and make significant progress in collaborative learning.

[0082] Step S203: Analyze the difficulties encountered by students in their current learning process based on the analysis results of their programming behavior, knowledge mastery, and learning style.

[0083] The specific steps of step S203 are:

[0084] Step S2031: Based on the industrial robot programming knowledge graph, a dynamic knowledge graph is constructed using a dynamic time-series graph neural network. The network aggregates hierarchical time-series features through a time decay function and a double-loop propagation mechanism, and updates the edge weights of the dynamic knowledge graph.

[0085] Specifically, a dynamic time-series graph neural network model consisting of an input layer, a hidden layer, and an output layer is constructed. The input layer is the student learning status data, including the student's programming behavior, knowledge mastery, and learning style. The hidden layer designs a time decay function and a double-loop propagation mechanism to process the temporal characteristics of the data; the output layer outputs the updated knowledge graph edge weights, and defines the time decay function: γ(t) = e -λ×Δt , where Δt represents the time interval between the current operation and the historical similar operation, λ represents the learning progress adjustment parameter, and the edge weight is dynamically updated according to the time decay function;

[0086] Double-loop propagation mechanism: In the inner loop, within each time step, for the learning status data of a single student, local time series feature aggregation is performed in the knowledge graph with the currently involved knowledge point node as the center, and the feature information of the node itself and its neighboring nodes at that time step is integrated; in the outer loop, as time goes by, the inner loop process is continuously repeated, information is transmitted and integrated between different time steps, hierarchical time series feature aggregation is realized, and the weights of each edge in the knowledge graph are gradually updated, so that the knowledge graph can dynamically reflect the changes in the relationship between knowledge points during the student's learning process.

[0087] Step S2032: Based on the analysis results of the student's programming behavior, knowledge mastery level, and learning style, generate knowledge point node embedding offsets, adjust the node association strength of the dynamic knowledge graph, and form an individually differentiated dynamic knowledge graph;

[0088] The specific steps of step S2032 include:

[0089] 1. Based on the instruction usage frequency and error type distribution in the programming behavior data, the mastery probability of each knowledge point in the knowledge mastery data, and the learning preferences and interaction behaviors in the learning style data, establish a mapping rule with the knowledge point node embedding offset;

[0090] For example, the mapping rules can be determined based on the behavioral data of students during the learning process. For example, if students make multiple errors related to the path planning algorithm during programming exercises, such as unreasonable path planning leading to robot collisions, according to the mapping rules, the initial embedding offset of the path planning algorithm knowledge point node will increase accordingly; if students frequently consult materials on welding programming applications, according to the mapping rules, the initial embedding offset of the welding programming application node will decrease, indicating that the students have a good grasp of this knowledge point.

[0091] 2. According to the above mapping rules, calculate the knowledge point node embedding offset for each student's knowledge point node;

[0092] According to the above mapping rules, the knowledge point node embedding offset is calculated for each student's knowledge point node. The specific steps include:

[0093] Calculate the initial knowledge point node embedding offset through mapping rules and dynamic knowledge graph;

[0094] Specifically, the performance differences of the student on the tasks related to the knowledge point are counted, including: the accuracy difference, which is the difference from the average accuracy; the completion time difference, which is the deviation from the standard time; the error reproduction difference, which is the deviation from the average number of retries on the knowledge point; the above three differences are weighted and summarized according to pre-set weights (set by personnel in this field according to actual conditions) to obtain the difficulty measurement value of the node. According to the student's learning style, such as visualization preference, text preference, hands-on practice preference, etc., a style sensitivity coefficient is predefined for each type of knowledge point. The difficulty measurement value is multiplied by the style sensitivity coefficient of the corresponding knowledge point to obtain the initial knowledge point node embedding offset.

[0095] The initial embedding offset of each knowledge point node and the initial embedding offsets of its immediate predecessor and successor nodes are averaged over the neighborhood.

[0096] Repeat the calculation of the initial knowledge point node embedding offset and neighborhood steps until the maximum change amplitude of the knowledge point node is lower than the preset threshold;

[0097] The knowledge point node embedding offset output by the iteration is normalized as the final knowledge point node embedding offset.

[0098] In this embodiment, the initial offset value is calculated based on local behavior. For example, if a student gets stuck on a question and the information is not propagated to adjacent knowledge points, the model will overfit to the local anomaly. In the first round of offset calculation, each node only considers its own behavioral characteristics, without considering its position in the entire knowledge path. Through iterative neighborhood smoothing, the state of each node is corrected by its upstream and downstream nodes, ultimately forming a well-structured offset pattern. Multiple rounds of iteration are the modeling of this process, reflecting the estimation of the student's cognitive state, rather than a static score.

[0099] The purpose of normalization is to unify the numerical scale to facilitate subsequent application in dynamic knowledge graphs.

[0100] 3. Apply the calculated knowledge point node embedding offset to the dynamic knowledge graph, recalculate the distance and weight between nodes, and form an individually differentiated dynamic knowledge graph.

[0101] Specifically, the embedding offset is used to update the weights, strengthen the association between knowledge points closely related to the student's current learning status, weaken the association between irrelevant or already mastered knowledge points, form a differentiated knowledge transmission path that conforms to the individual characteristics of the student, and highlight the student's unique knowledge cognitive structure in the learning process.

[0102] Step S2033: Establish a cognitive impairment inference model, extract the correlation between the current operation and each node in the dynamic knowledge graph, and use the Bayesian network to build a probabilistic graph model to infer the student's current learning difficulties.

[0103] Step S3: Push difficulty analysis data to the student's learning terminal based on the current knowledge difficulty.

[0104] Specifically, based on the difficulties encountered by students in the current learning process, targeted teaching content push strategies are generated, immediate intervention is provided, personalized learning paths are planned for students, and the intervention effects are evaluated.

[0105] In this embodiment, a targeted teaching content push strategy is generated based on the data analysis results. The strategy includes: if a student's mastery probability of a certain knowledge node is lower than a threshold and the student has a passive guidance learning style, the teacher will provide the student with a one-on-one explanation, or push a video tutorial containing a detailed explanation of the knowledge node, accompanied by step-by-step exercises, and provide a pop-up window with instruction usage prompts in the programming interface;

[0106] During the subsequent student programming process, the system provides immediate intervention based on the problems detected in real time. For example, when a programming error is detected, an error prompt window pops up to explain the error type and cause, the error code line is highlighted in different colors in the code editing area, and code correction examples related to the error are provided.

[0107] Evaluation of intervention effectiveness, that is, evaluation of teaching effectiveness, establishes a multi-dimensional intervention effectiveness evaluation indicator system, including: academic performance evaluation, comparing students' programming task completion status before and after receiving personalized intervention, including indicators such as task completion time, code correctness, and functional implementation completeness; knowledge mastery evaluation, evaluating the extent of improvement in knowledge mastery through regular testing or observing students' application of previously weak knowledge nodes in new tasks; learning behavior evaluation, analyzing changes in students' learning interaction behavior after intervention, such as whether participation in online discussion areas has increased, whether the frequency of access to independent learning materials has increased, etc.

[0108] Example 2

[0109] See also Figure 4 , another embodiment provided by the present invention: an industrial robot programming teaching system, comprising: a data acquisition module, a state data generation module, an offset determination module, an update module and a difficulty determination and resolution module;

[0110] The data acquisition module is used to collect programming behavior data and industrial robot operation data in real time;

[0111] The status data generating module is used to generate the student's learning status data based on the programming behavior data and the industrial robot operation data;

[0112] The offset determination module is used to determine the embedding offset of the knowledge point node according to the student learning status data in combination with the preset dynamic knowledge graph;

[0113] The updating module is used to update the current dynamic knowledge graph according to the embedding offset of the knowledge point node;

[0114] The difficulty determination and solution module is used to determine the student's current knowledge difficulties based on the current dynamic knowledge graph, so as to push difficulty analysis data to the student's learning terminal based on the current knowledge difficulties.

[0115] The state data generation module includes: a disassembly unit and a state data generation unit;

[0116] The disassembling unit is used to arrange the programming behavior data in chronological order, disassemble it into the smallest analyzable units, and form structured table data;

[0117] The state data generating unit is used to analyze students' programming behaviors according to structured table data, and to evaluate students' knowledge mastery and learning styles.

[0118] The offset determination module includes: a mapping rule establishment unit and an embedding offset unit;

[0119] The mapping rule establishing unit is used to establish a mapping rule with the knowledge point node embedding offset according to the student's learning status data;

[0120] The embedding offset unit is used to calculate the initial embedding offset according to the above mapping rule, and then perform neighborhood averaging and iteration.

[0121] In addition, the parts of the above technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0122] The above-described specific embodiments further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above description is merely a specific embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for teaching industrial robot programming, characterized in that: include: Real-time collection of programming behavior data and industrial robot operation data; generating student learning status data based on the programming behavior data and the industrial robot operation data, wherein the student learning status data includes the student's programming behavior, knowledge mastery level, and learning style; In combination with a preset dynamic knowledge graph, based on the student learning status data, a knowledge point node embedding offset is determined. The knowledge point node embedding offset is used to adjust the node association strength of the dynamic knowledge graph. The dynamic knowledge graph is based on the industrial robot programming knowledge graph and is constructed using a dynamic time-series graph neural network. Update the current dynamic knowledge graph according to the knowledge point node embedding offset; The student's current knowledge difficulties are determined based on the current dynamic knowledge graph, so as to push difficulty analysis data to the student's learning terminal based on the current knowledge difficulties.

2. The method for teaching industrial robot programming according to claim 1, wherein: Generating the student's learning status data according to the programming behavior data and the industrial robot operation data includes: Arrange programming behavior data in chronological order, break it down into the smallest analyzable units, and form structured tabular data; Use process verification methods to identify logical errors. According to the error pattern library, similar logical errors are aggregated to obtain logical error types, including syntax errors, logical vulnerabilities, and device adaptation errors. The error pattern library is constructed based on the industrial robot knowledge base. Break down programming tasks into knowledge units, correspond them to the industrial robot programming knowledge graph, and dynamically evaluate students' knowledge mastery; Extract students' behavioral characteristics and analyze their learning styles based on the extracted behavioral characteristics.

3. The industrial robot programming teaching method according to claim 2, characterized in that: The method of combining a preset dynamic knowledge graph and determining the embedding offset of a knowledge point node according to the student learning status data includes: Based on the industrial robot knowledge base, build an industrial robot programming knowledge graph; Based on the industrial robot programming knowledge graph, a dynamic knowledge graph is constructed using a dynamic time-series graph neural network. The network aggregates hierarchical time-series features through a time decay function and a double-loop propagation mechanism to update the edge weights of the dynamic knowledge graph. Generate knowledge point node embedding offset based on students' learning status data.

4. The method for teaching industrial robot programming according to claim 3, wherein: The method of generating a knowledge point node embedding offset according to the student's learning status data includes: According to the students’ learning status data, a mapping rule with the embedding offset of knowledge point nodes is established; According to the above mapping rules, the knowledge point node embedding offset is calculated for each student's knowledge point node.

5. The method for teaching industrial robot programming according to claim 4, wherein: According to the above mapping rules, the knowledge point node embedding offset is calculated for each student's knowledge point node, including: Calculate the initial knowledge point node embedding offset through mapping rules and dynamic knowledge graph; The initial embedding offset of each knowledge point node and the initial embedding offsets of its immediate predecessor and successor nodes are averaged over the neighborhood. Repeat the calculation of the initial knowledge point node embedding offset and neighborhood steps until the maximum change amplitude of the knowledge point node is lower than the preset threshold; The knowledge point node embedding offset output by the iteration is normalized as the final knowledge point node embedding offset.

6. The method for teaching industrial robot programming according to claim 5, wherein: The calculation of the initial knowledge point node embedding offset by mapping rules and dynamic knowledge graph includes: Count the performance differences of students on tasks related to knowledge point nodes, perform weighted summation on the performance differences, and obtain the difficulty measurement value of the knowledge point node; According to the students' learning style, a style sensitivity coefficient is preset, and the difficulty measurement value of the knowledge point node is multiplied by the style sensitivity coefficient to obtain the initial knowledge point node embedding offset.

7. The industrial robot programming teaching method according to claim 6, characterized in that: The updating of the current dynamic knowledge graph according to the knowledge point node embedding offset includes: applying the calculated knowledge point node embedding offset to the dynamic knowledge graph, recalculating the distance and weight between nodes, and forming an individually differentiated dynamic knowledge graph.

8. An industrial robot programming teaching system, used to implement an industrial robot programming teaching method according to any one of claims 1 to 7, characterized in that: include: Data acquisition module, status data generation module, offset determination module, update module and difficulty determination and resolution module; The data acquisition module is used to collect programming behavior data and industrial robot operation data in real time; The status data generating module is used to generate the student's learning status data based on the programming behavior data and the industrial robot operation data; The offset determination module is used to determine the embedding offset of the knowledge point node according to the student learning status data in combination with the preset dynamic knowledge graph; The updating module is used to update the current dynamic knowledge graph according to the embedding offset of the knowledge point node; The difficulty determination and solution module is used to determine the student's current knowledge difficulties based on the current dynamic knowledge graph, so as to push difficulty analysis data to the student's learning terminal based on the current knowledge difficulties.

9. The industrial robot programming teaching system according to claim 8, characterized in that: The state data generation module includes: a disassembly unit and a state data generation unit; The disassembling unit is used to arrange the programming behavior data in chronological order, disassemble it into the smallest analyzable units, and form structured table data; The state data generating unit is used to analyze students' programming behaviors according to structured table data, and to evaluate students' knowledge mastery and learning styles.

10. The industrial robot programming teaching system according to claim 9, characterized in that: The offset determination module includes: a mapping rule establishment unit and an embedding offset unit; The mapping rule establishing unit is used to establish a mapping rule with the knowledge point node embedding offset according to the student's learning status data; The embedding offset unit is used to calculate the initial embedding offset according to the above mapping rule, and then perform neighborhood averaging and iteration.

Images