Intelligent production line teaching method and system for sorting and packaging
By obtaining reference parameters for intelligent production line teaching tasks, extracting features and performing neural network evaluation, the problem of low efficiency of traditional teaching methods is solved, and personalized teaching and efficient teaching effects are achieved.
Patent Information
- Application Number
- CN202510225610.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-27
- Publication Date
- 2025-06-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The traditional intelligent production line teaching methods are inefficient and cannot be personalized for individual students, resulting in poor teaching results.
By obtaining the reference parameters of the target operation task, extracting features as target features, and providing teaching arrangement auxiliary data based on the neural network calculation evaluation results to improve teaching efficiency.
Quantitative evaluation of intelligent production line teaching tasks has been realized, the pertinence and practicality of teaching has been improved, and the teaching efficiency and quality have been improved.
Smart Images
Figure CN120106792A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent production line teaching, and in particular to a teaching method and system for a sorting and packaging intelligent production line. Background Art
[0002] At present, intelligent production lines have been widely used in many industries such as processing, manufacturing, and assembly, realizing the automation, intelligence, and informatization of the production process, which not only significantly improves production efficiency, but also reduces production costs and improves product quality. New demands for production line control teaching have also emerged. Traditional production line teaching methods often adopt a unified teaching method for students and provide overall scores to reflect the level of students. If teachers manually check the specific learning situation of each student and make targeted learning arrangements, the workload required is very large, resulting in low teaching efficiency. Summary of the invention
[0003] The main purpose of the present invention is to provide a teaching method and system for an intelligent production line of sorting and packaging, which can automatically obtain reference parameters for the execution of target operation tasks, quantitatively evaluate the execution effect through reference parameters, provide auxiliary data support for teachers' teaching arrangements, and improve teaching efficiency.
[0004] To solve the above problems, the present application provides a smart production line teaching method for sorting and packaging, the method comprising: obtaining a current target operation task, wherein the target operation task includes at least one of several teaching tasks; in response to the execution of the target operation task, obtaining reference parameters for executing the target operation task; extracting at least one feature of the reference parameter as a target feature, and calculating and outputting an evaluation result of the target operation task based on the target feature.
[0005] Preferably, obtaining the current target running task includes: obtaining the currently executed running package, parsing the running steps in the running package, extracting the task types corresponding to the running steps and integrating them as the target running task.
[0006] Preferably, the reference parameters are obtained based on sorting efficiency, packaging quality and production line operation status; wherein the sorting efficiency includes the ratio of sorting time and the number of successful sorting of target product units corresponding to the target operation task, the determination conditions of the packaging quality include at least the packaging completeness and weight of the finished product output by the target operation task, and the determination conditions of the production line status include at least the temperature characterization value and energy consumption characterization value of the production line during the execution of the target operation task.
[0007] Preferably, extracting at least one feature of the reference parameter as a target feature includes: inputting the reference parameter and student information corresponding to the target running task into a preset feature extraction network; and selecting at least one feature output by the feature extraction network as the target feature.
[0008] Preferably, the evaluation results include the completion representation value of the target operation task on each teaching task and the score value of the target operation task; wherein, the completion representation value of the target operation task on each teaching task is obtained by inputting the target feature into a preset classification network, and the score value of the target operation task is obtained by inputting the target feature into a preset score prediction network.
[0009] Preferably, the classification network is a multi-layer neural network; and / or, the score prediction network is a regression neural network.
[0010] Preferably, after extracting at least one feature of the reference parameters as a target feature, and calculating and outputting an evaluation result of the target operation task based on the target feature, the method also includes: updating the learning progress of the trainees corresponding to the target operation task and the teaching task completion degree of the instructor corresponding to the trainees based on the evaluation result of the target operation task.
[0011] Preferably, the teaching task includes one or more of a sorting task, a conveying task, a transferring task and a packaging task of the target product unit.
[0012] Preferably, the intelligent production line is a chessboard assembly production line; the target operation tasks include: any one of sorting and packaging of single-layer chessboards, sorting and packaging of multi-layer chessboards, and sorting and packaging of mixed chessboards.
[0013] In order to solve the above technical problems, the present application proposes a sorting and packaging intelligent production line teaching system, which is used to implement any of the above-mentioned sorting and packaging intelligent production line teaching methods, and the system includes: an acquisition module: used to obtain the current target operation task, wherein the target operation task includes at least one of several teaching tasks; a response module: used to respond to the execution of the target operation task and obtain reference parameters for executing the target operation task; a processing module: used to extract at least one feature of the reference parameter as a target feature, and calculate and output the evaluation result of the operation task based on the target feature.
[0014] The beneficial effect of the present invention is that, different from the prior art, the present invention first obtains the current target operation task, then obtains the reference parameters in the target operation task, extracts at least one feature of the reference parameter as the target feature, and calculates and outputs the evaluation result of the task based on the target feature. Each target operation task corresponds to one or more teaching tasks, ensuring that the target operation task is guided by the teaching task, and can flexibly adapt to the needs of different teaching tasks, thereby improving the pertinence and practicality of teaching. The real-time reference parameters are collected during the execution of the task to provide a reliable data basis for subsequent analysis and evaluation. By extracting features from the reference parameters, the complexity of data processing is reduced, and the key information required for the evaluation is retained, thereby improving the accuracy and efficiency of the evaluation. In addition, the target features required for the evaluation are selected from the extracted features to quantitatively evaluate the execution effect of the target operation task, thereby providing effective technical support for improving the teaching quality and improving the teaching efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them: Figure 1 It is a flow chart of the first embodiment of the intelligent production line teaching method for sorting and packaging provided by the present application; Figure 2 It is a flow chart of another embodiment of the intelligent production line teaching method for sorting and packaging of the present application; Figure 3 It is a structural diagram of an embodiment of the sorting and packaging intelligent production line teaching system proposed in this application. DETAILED DESCRIPTION
[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0017] The term "and / or" herein is merely a description of the association relationship of associated objects, indicating that there may be three relationships, for example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " herein generally indicates that the objects associated before and after are in an "or" relationship. In addition, "many" herein means two or more than two. In addition, the term "at least one" herein means any combination of at least two of any one or more of a plurality of, for example, including at least one of A, B, and C, which may mean including any one or more elements selected from the set consisting of A, B, and C. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.
[0018] Please refer to Figure 1 , Figure 1 It is a flow chart of the first embodiment of the intelligent production line teaching method for sorting and packaging provided by the present application.
[0019] The intelligent production line teaching method of the present application can be applied to the teaching of chess game container systems to solve the problems of low teaching efficiency and inability to provide personalized teaching based on the individual differences of students in the current intelligent production line control teaching.
[0020] Specifically, if Figure 1 As shown, the flowchart of an embodiment of the intelligent production line teaching method for sorting and packaging of the present application specifically includes the following steps: Step S11: Obtain the current target running task, wherein the target running task includes at least one of several teaching tasks.
[0021] Specifically, the target operation task can be a specific task that students need to complete during the control learning process of the chess game container system. The teaching task can be set based on the teaching objectives and is used to enable students to master relevant knowledge and skills through a series of tasks during the control learning process of the chess game container system.
[0022] In some embodiments, the teaching task includes one or more of a sorting task, a conveying task, a transfer task, and a packaging task of the target product unit.
[0023] Specifically, in the chess game container system, the sorting task can be to classify different types of chess pieces, the transport task can be to transport chess pieces from one place to another through a conveying mechanism, the transfer task can be to move chess pieces from one location to another designated location through a robotic arm or a clamping mechanism, and the packaging task can be to put the sorted chess pieces into a chess box according to certain rules. Each teaching task can have different difficulty levels. For example, the sorting tasks can be arranged from simple to complex as: single color sorting, multi-color sorting, font sorting, etc. The difficulty level of the teaching task can be matched with the progress of the teaching goal. The later the progress of the teaching goal, the higher the difficulty level of the teaching task.
[0024] In some specific embodiments, the target operation task may be one of the teaching tasks. The teaching goal may be to enable students to master the skill of sorting chess pieces. According to the teaching goal, the corresponding teaching task is set to sort chess pieces of a specific type, and the target operation task may be to sort red chess pieces. It is understandable that students need to control the chess game container system to accurately sort out the red chess pieces from a pile of chess pieces of different colors and place them in the designated position by making an operation package of the chess game container system. By running a single target task, students can focus on the targeted practice of a single skill.
[0025] In other specific embodiments, the target operation task can be a variety of teaching tasks, and the teaching goal can be to enable students to master the skills of sorting, conveying and packaging chess pieces. The teaching tasks can be sorting chess pieces of a specific type, conveying the sorted chess pieces to the target position, and packaging the chess pieces at the target position according to packaging requirements. The target operation task can be sorting red chess pieces, conveying the sorted red chess pieces to the target position, and packaging the red chess pieces at the target position according to packaging requirements. Integrating multiple teaching tasks into one target operation task allows students to learn the connection methods of each stage in a complete process and achieve multi-dimensional targeted exercises. In practical applications, the target operation tasks are flexibly designed and adjusted to meet the learning needs of different students.
[0026] In some embodiments, obtaining the current target running task includes: obtaining the currently executed running package, parsing the running steps in the running package, extracting the task types corresponding to the running steps and integrating them as the target running task.
[0027] Specifically, the operation package may be a program package containing a series of operation instructions and task information. By parsing the operation package, the system can extract the specific tasks and steps that need to be executed currently, and then determine the target operation task.
[0028] In some application scenarios, it can be a host computer environment, and the operation package can be an encapsulated program package, which contains the operation instructions and task information required to execute the task. The operation package can be a binary file, a script file, a configuration file, etc. In other application scenarios, other data transmission protocols can also be included. For example, the operation package can be a TCP data packet, the operation instructions can be set in the header field of the TCP data packet, and the task information can be in the data field of the TCP data packet. In the case where the operation package adopts multiple data structures, different naming conventions can be set for the operation packages of different data structures, so that the system can match the corresponding parsing engine according to the name of the operation package to parse the operation package.
[0029] In some embodiments, the intelligent production line is a chess game assembly production line, and the target operation tasks include: any one of sorting and packaging of single-layer chess boards, sorting and packaging of multi-layer chess boards, and sorting and packaging of mixed chess boards.
[0030] Specifically, the sorting and packaging of a single-layer chessboard may be a process of sorting and conveying chess pieces, and transferring and packaging chess pieces according to position rules on a chessboard with only one layer. The sorting and packaging of a multi-layer chessboard may be a process of sorting and conveying chess pieces, and transferring and packaging chess pieces according to position rules on a chessboard with a multi-layer structure. The sorting and packaging of a mixed chessboard may be a process of sorting and packaging chess pieces for combined chessboards of different specifications. The sorting from difficult to easy according to the difficulty of running the target task may be sorting of mixed chessboards, sorting of multi-layer chessboards, and sorting of single-layer chessboards. The difficulty level of the teaching task may match the progress of the teaching goal. The later the progress of the teaching goal, the higher the difficulty level of the teaching task.
[0031] Step S12: In response to the target operation task being executed, obtaining reference parameters for executing the target operation task.
[0032] Specifically, the reference parameters may be various data and information used to evaluate the execution status of the target operation task and the system performance during the execution of the target operation task.
[0033] In some embodiments, the reference parameters are obtained based on sorting efficiency, packaging quality and production line operation status; wherein the sorting efficiency includes the ratio of the sorting time and the number of successful sorting of the target product unit corresponding to the target operation task, the determination condition of the packaging quality includes at least the packaging completeness and weight of the finished product output by the target operation task, and the determination condition of the production line status includes at least the temperature characterization value and energy consumption characterization value of the production line during the execution of the target operation task.
[0034] Specifically, the shorter the sorting time and the higher the number of successful sorting, the higher the sorting efficiency. Stable production line temperature and low energy consumption indicate that the system is in good operating condition. The packaging quality can be judged by comparing the packaging execution steps and the corresponding execution completeness during the execution of the target operation task with the standard steps to obtain the packaging completeness representation value, and the weight representation value can be obtained by comparing the weight of the product output by the output of the target operation task with the preset weight range.
[0035] In some specific embodiments, the target operation task is to complete the sorting of 1,000 chess pieces within one hour. The sorting efficiency is evaluated by recording the actual sorting time and the number of successful sorting during the execution of the target operation task. For example, if 998 products are sorted within one hour and only 2 products fail, the sorting efficiency is 0.98. In other specific embodiments, the target operation task is to complete the packaging of 10 chessboards. The standard steps are to open the chessboard cover, rotate the chessboard 180 degrees horizontally, and move 32 corresponding chess pieces to the corresponding positions when the chessboard is a chessboard, then close the chessboard and close the chessboard buckle. The preset weight range of the chessboard is 1.5kg±0.05kg, and different scores are set for each step according to its importance. If there is an error in the step, the score is deducted according to the corresponding step score. At the same time, the automatic weighing equipment can also be used to output the weight of the product output by the target operation task execution, and compared with the preset weight range to obtain the weight representation value. In addition, by monitoring the temperature and energy consumption values of the production line, problems in the operation of the sorting and packaging intelligent production line can be discovered and solved in a timely manner to ensure the stable operation of the chess game container system. Therefore, the acquisition and evaluation of reference parameters not only helps to improve the performance and quality of the system, but also helps to optimize students' operating skills and strategies.
[0036] Step S13: extract at least one feature of the reference parameter as a target feature, and calculate and output an evaluation result of the target operation task based on the target feature.
[0037] Specifically, the target feature is a key feature extracted from the reference parameter that can reflect the task execution status or system performance. Extracting at least one feature of the reference parameter as the target feature includes: inputting the reference parameter and the student information corresponding to the target running task into a preset feature extraction network. Selecting at least one feature output by the feature extraction network as the target feature.
[0038] In some specific embodiments, the features related to the learning level of the trainees extracted from the reference parameters may be sorting efficiency features, packaging quality features, and production line operation features. At least one feature of the reference parameters may be extracted as a target feature according to the teaching objectives. When the teaching objective is to improve sorting efficiency, parameters related to sorting speed and accuracy may be selected for analysis and evaluation.
[0039] In other specific embodiments, the target feature can be extracted by inputting the reference parameters and the trainee information corresponding to the target operation task into a preset feature extraction network. The reference parameters include sorting efficiency, packaging quality, production line operation status, etc. The trainee information includes the name of the trainee, each trainee's unique code and learning progress, etc.
[0040] In some embodiments, the evaluation result includes a completion characterization value of the target operation task on each teaching task and a score value of the target operation task. The completion characterization value of the target operation task on each teaching task is obtained by inputting the target feature into a preset classification network, and the score value of the target operation task is obtained by inputting the target feature into a preset score preset network.
[0041] Specifically, the classification network can input the target features and output the completion of the target operation task on each teaching task. The completion can be reflected by probability distribution or category label, reflecting the completion of the target operation task in different dimensions. The score prediction network is a neural network that calculates the score based on the input data. In the chess game container teaching scenario, the score prediction network can input the target features and output the score value of the target operation task. The score value can be a scalar used to measure the overall completion or performance of the target operation task. The higher the score, the better the task completion. The weights of each step in the task can be set according to the actual usage scenario. In some application scenarios, the classification network is a multi-layer neural network, which can learn complex nonlinear relationships and is suitable for classification. In some application scenarios, the classification prediction network is a regression neural network.
[0042] The solution of the present application first obtains the current target operation task, then obtains the reference parameters in the target operation task, extracts at least one feature of the reference parameter as the target feature, and calculates and outputs the evaluation result of the task based on the target feature. Each target operation task corresponds to one or more teaching tasks, ensuring that the target operation task is guided by the teaching task, and can flexibly adapt to the needs of different teaching tasks, thereby improving the pertinence and practicality of teaching. The real-time reference parameter collection during the task execution provides a reliable data basis for subsequent analysis and evaluation, and reduces the complexity of data processing by extracting features from the reference parameters, retaining the key information required for the evaluation, thereby improving the accuracy and efficiency of the evaluation. The target features required for the evaluation are selected from the extracted features to quantitatively evaluate the execution effect of the target operation task, thereby providing effective technical support for improving the teaching quality and improving the teaching efficiency.
[0043] In some embodiments, see Figure 2 , Figure 2is a flow chart of another embodiment of the intelligent production line teaching method for sorting and packaging of the present application. After executing the above step S13, the intelligent production line teaching method for sorting and packaging further includes the following steps: Step S14: Based on the evaluation result of the target operation task, the learning progress of the student corresponding to the target operation task and the corresponding teaching completion degree of the student are updated.
[0044] Specifically, the evaluation result of the target operation task can be the completion representation degree of the target operation task on each teaching task and the score value of the target operation task. The learning progress can be the completion progress of the trainees on each teaching task. The teaching completion can be evaluated based on the learning progress of the students combined with the teaching objectives. The teacher user interface and the student user interface are designed separately to show real-time feedback results to students and teachers. Through the evaluation of teaching completion, teachers can understand the teaching effect, identify deficiencies and problems in teaching, and make targeted improvements and optimizations to improve the teaching quality. Students can understand their position and progress in learning by checking their learning progress and teaching completion, thereby stimulating learning motivation and promoting the improvement of learning effects.
[0045] See also Figure 3 , Figure 3 It is a structural diagram of an embodiment of the sorting and packaging intelligent production line teaching system proposed in this application.
[0046] like Figure 3 As shown, the intelligent production line teaching system for sorting and packaging of this embodiment is used to implement the intelligent production line teaching method for sorting and packaging of any of the above embodiments, and specifically includes an acquisition module, a response module and a processing module, wherein the acquisition module is used to acquire the current target operation task, wherein the target operation task includes at least one of several teaching tasks; the response module is used to respond to the execution of the target operation task and acquire the reference parameters for executing the target operation task; the processing module is used to extract at least one feature of the reference parameter as the target feature, and calculate and output the evaluation result of the operation task based on the target feature.
[0047] In some embodiments, the acquisition module acquires the current target running task including: acquiring the currently executed running package, parsing the running steps in the running package, extracting the task types corresponding to the running steps and integrating them as the target running task.
[0048] In some embodiments, the response module is also used to obtain the result based on sorting efficiency, packaging quality and production line operation status; wherein, the sorting efficiency includes the ratio of the sorting time and the number of successful sorting of the target product unit corresponding to the target operation task, the judgment condition of the packaging quality includes at least the packaging completeness and weight of the finished product output by the target operation task, and the judgment condition of the production line status includes at least the temperature characterization value and energy consumption characterization value of the production line during the execution of the target operation task.
[0049] In some embodiments, the processing module extracts at least one feature of the reference parameter as a target feature, including: inputting the reference parameter and the student information corresponding to the target operation task into a preset feature extraction network; and selecting at least one feature output by the feature extraction network as the target feature.
[0050] In some embodiments, the evaluation results output by the processing module include the completion characterization value of the target operation task on each teaching task and the score value of the target operation task; wherein the completion characterization value of the target operation task on each teaching task is obtained by inputting the target feature into a preset classification network, and the score value of the target operation task is obtained by inputting the target feature into a preset score prediction network. wherein the classification network is a multi-layer neural network, and the score prediction network is a regression neural network.
[0051] In some embodiments, the sorting and packaging intelligent production line teaching system may further include an evaluation module, which is used to update the learning progress of the trainees corresponding to the target operation task and the teaching task completion degree of the instructor corresponding to the trainees based on the evaluation result of the target operation task after the processing module executes the extraction of at least one feature of the reference parameter as the target feature, calculates and outputs the evaluation result of the target operation task based on the target feature.
[0052] The solution of the present application first obtains the current target operation task, then obtains the reference parameters in the target operation task, extracts at least one feature of the reference parameter as the target feature, and calculates and outputs the evaluation result of the task based on the target feature. Each target operation task corresponds to one or more teaching tasks, ensuring that the target operation task is guided by the teaching task, and can flexibly adapt to the needs of different teaching tasks, thereby improving the pertinence and practicality of teaching. The real-time reference parameter collection during the task execution provides a reliable data basis for subsequent analysis and evaluation, and reduces the complexity of data processing by extracting features from the reference parameters, retaining the key information required for the evaluation, thereby improving the accuracy and efficiency of the evaluation. The target features required for the evaluation are selected from the extracted features to quantitatively evaluate the execution effect of the target operation task, thereby providing effective technical support for improving the teaching quality and improving the teaching efficiency.
[0053] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.
Claims
1. A teaching method for intelligent production line of sorting and packaging, characterized in that: The method comprises: Acquire a current target running task, wherein the target running task includes at least one of a plurality of teaching tasks; In response to the target operation task being executed, obtaining reference parameters for executing the target operation task; At least one feature of the reference parameter is extracted as a target feature, and an evaluation result of the target operation task is calculated and output based on the target feature.
2. The intelligent production line teaching method for sorting and packaging according to claim 1 is characterized in that: The obtaining of the current target running task includes: obtaining the currently executed running package, parsing the running steps in the running package, extracting the task types corresponding to the running steps and integrating them as the target running task.
3. The intelligent production line teaching method for sorting and packaging according to claim 1 is characterized in that: The reference parameters are obtained based on sorting efficiency, packaging quality and production line operation status; Among them, the sorting efficiency includes the ratio of the sorting time and the number of successfully sorted target product units corresponding to the target operation task, the judgment condition of the packaging quality includes at least the packaging completeness and weight of the finished product output by the target operation task, and the judgment condition of the production line status includes at least the temperature characterization value and energy consumption characterization value of the production line during the execution of the target operation task.
4. The intelligent production line teaching method for sorting and packaging according to claim 3 is characterized in that: The extracting at least one feature of the reference parameter as a target feature comprises: Inputting the reference parameters and the student information corresponding to the target operation task into a preset feature extraction network; At least one feature output by the feature extraction network is selected as the target feature.
5. The intelligent production line teaching method for sorting and packaging according to claim 1 is characterized in that: The evaluation result includes the completion representation value of the target operation task on each of the teaching tasks and the score value of the target operation task; Among them, the completion representation value of the target operation task on each of the teaching tasks is The target feature is input into a preset classification network, and the score value of the target running task is input into a preset score prediction network.
6. The intelligent production line teaching method for sorting and packaging according to claim 4 is characterized in that: The classification network is a multi-layer neural network; and / or the score prediction network is a regression neural network.
7. The intelligent production line teaching method for sorting and packaging according to claim 4 is characterized in that: After performing the step of extracting at least one feature of the reference parameter as a target feature, and calculating and outputting an evaluation result of the target operation task based on the target feature, the method further includes: Based on the evaluation result of the target operation task, the learning progress of the student corresponding to the target operation task and the teaching task completion degree of the teacher corresponding to the student are updated.
8. The intelligent production line teaching method for sorting and packaging according to claim 1 is characterized in that: The teaching task includes one or more of a sorting task, a conveying task, a transfer task and a packaging task of a target product unit.
9. The teaching method for intelligent production line of sorting and packaging according to claim 1, characterized in that: The intelligent production line is a chess game assembly production line; The target operation task includes: any one of sorting and packaging of a single-layer chessboard, sorting and packaging of a multi-layer chessboard, and sorting and packaging of a mixed chessboard.
10. A sorting and packaging intelligent production line teaching system, characterized in that: The system is used to implement the intelligent production line teaching method for sorting and packaging according to any one of claims 1 to 9, and the system comprises: An acquisition module: used to acquire a current target operation task, wherein the target operation task includes at least one of a plurality of teaching tasks; Response module: used to respond to the execution of the target operation task and obtain reference parameters for executing the target operation task; Processing module: used for extracting at least one feature of the reference parameter as a target feature, and calculating and outputting an evaluation result of the running task based on the target feature.