An experimental teaching method and system based on the scenario of science and technology special commissioners

Abstract

The present invention relates to the technical field of experimental teaching evaluation, and specifically relates to an experimental teaching method and system based on the scenario of science and technology special commissioners. The method includes: The present invention can create an experimental scenario based on the integration of experimental teaching objectives and content; generate an experimental scenario activation value based on node information, and the cloud distribution center determines whether the operation node of the experimental scenario of the student meets the experimental scenario reception requirements based on the experimental scenario activation value; obtain the operation video generated by the student based on the experimental scenario, read the operation video, and perform face recognition of the student on the operation video based on the student face recognition model to obtain the student face recognition result; it can judge the node information of the operation node of the experimental scenario of the student, and can ensure that the operation node of the experimental scenario of the student meets the experimental operation requirements, and further improve the efficiency of the experiment. Through the real scenario of experimental teaching by science and technology special commissioners and simulated role-playing, students can better master the professional skills and operation methods required in the front line of production.

Description

Technical Field

[0001] The present invention relates to the technical field of experimental teaching evaluation, and particularly relates to an experimental teaching method and system based on the scenario of science and technology commissioners. Background Art

[0002] In today's rapidly developing technological era, higher education and vocational education are facing unprecedented challenges and opportunities. Traditional teaching methods often focus on the imparting of theoretical knowledge, while neglecting the cultivation of practical skills and the stimulation of innovation ability. In order to cultivate high-quality scientific and technological talents who meet the needs of future society, it is particularly important to explore a teaching mode that closely combines theoretical knowledge with practical application.

[0003] By constructing multiple simulated scenarios of science and technology commissioners' work, such as agricultural science and technology promotion, enterprise technology upgrading, community science and technology service, etc., each scenario includes real or virtual project tasks and challenges. Combining with the work process of science and technology commissioners, trainees experience the production front-line scenarios through role-playing, including demand research, scheme design, technology implementation, effect evaluation and other links.

[0004] In the prior art, there is no experimental teaching method and system based on the scenario of science and technology commissioners to train and cultivate the skills of trainees through simulated experimental scenarios. Summary of the Invention

[0005] The purpose of the present invention is to provide an experimental teaching method and system based on the scenario of science and technology commissioners: to solve the technical problems that the existing solutions lack front-line scenarios such as the scenario of science and technology commissioners in experimental teaching, cannot evaluate the experimental operation logs of trainees in a timely manner and give experimental feedback, resulting in poor experimental teaching effects.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] On the one hand, an experimental teaching method based on the scenario of science and technology commissioners, the method includes:

[0008] Obtain the experimental teaching objectives and contents, and create an experimental scenario based on the integration of the experimental teaching objectives and contents;

[0009] Upload the experimental scenario to the cloud distribution center, the cloud distribution center obtains the node information of the trainee's experimental scenario operation node, generates an experimental scenario activation value based on the node information, and the cloud distribution center determines whether the trainee's experimental scenario operation node meets the experimental scenario reception requirements based on the experimental scenario activation value;

[0010] The trainee's experimental scenario operation node receives the experimental scenario, the trainee operates based on the experimental scenario, and generates an experimental operation log based on the trainee's operation record;

[0011] Obtain the operation video generated by the trainee based on the experimental scenario, read the operation video, perform trainee face recognition on the operation video based on the trainee face recognition model, and obtain the trainee face recognition result;

[0012] Determine the experimental operation log corresponding to the trainee based on the trainee face recognition result, generate the experimental operation score of the trainee based on the experimental operation log, and determine whether to generate an experimental diagnosis and improvement report according to the experimental operation score.

[0013] Furthermore, creating an experimental scenario based on the integration of experimental teaching objectives and content specifically includes the following process:

[0014] Determine the experimental components in the experimental component library based on the experimental teaching objectives and content. Among them, the experimental components include laboratory equipment, low-value consumables, experimental materials, and component parts of the database type. Different experimental teaching objectives and content correspond to different experimental components in the experimental component library;

[0015] The experimental components in the experimental component library are displayed on the building interface through a selection instruction, and a virtual experimental process is obtained by combining the experimental components through a building instruction:

[0016] Receive the virtual experiment building instruction of the science and technology commissioner and execute to display the experimental component library interface and the building interface;

[0017] After the experimental components in the experimental component library interface receive a selection instruction or a drag instruction, they are displayed in the building interface; after the experimental components in the building interface receive an attribute selection instruction, the component attributes are displayed and the component attributes are determined through a confirmation instruction to obtain the experimental components with confirmed component attributes; the experimental components with confirmed component attributes are connected to the experimental components after receiving a connection instruction to obtain a virtual experimental process;

[0018] Publish the virtual experimental process to obtain an experimental scenario.

[0019] Furthermore, generating an experimental scenario activation value based on the node information specifically includes the following process:

[0020] Obtain the load rate of the node based on the node information ;

[0021] Obtain the computing power of the node based on the node information, and count the predicted computing power corresponding to the experimental scenario. Calculate the difference between the node computing power and the predicted computing power, and record the difference as the computing power redundancy A;

[0022] Obtain the delay B of the node and the data transmission distance C from the node to the cloud distribution center based on the node information;

[0023] Substitute the load rate , the computing power redundancy A, the delay B, and the data transmission distance C into the experimental scenario activation value calculation formula to obtain the experimental scenario activation value. The calculation formula is as follows:

[0024] ;

[0025] Among them, is the experimental scenario activation value, and the value of e is 2.72.

[0026] Furthermore, the cloud distribution center determines whether the student's experimental scenario operation node meets the experimental scenario reception requirements based on the experimental scenario activation value, which specifically includes the following process:

[0027] Obtain the experimental scenario activation value threshold. Among them, the experimental scenario activation value threshold is stored in the cloud distribution center. Determine whether the experimental scenario activation value exceeds the experimental scenario activation value threshold. If so, it is determined that the student's experimental scenario operation node meets the experimental scenario reception requirements. If not, it is determined that the student's experimental scenario operation node does not meet the experimental scenario reception requirements.

[0028] Furthermore, perform face recognition on the student in the operation video based on the student face recognition model, and the specific process of obtaining the student face recognition result includes the following:

[0029] Use the MTCNN network to detect the position of the student's first-frame face in the operation video. Initialize the particle filter according to the first-frame face position, and perform random particle resampling to update the weight distribution of the particles. According to the different weights assigned and the state transition matrix adopted, predict the face preselection box through the particle swarm, and use the preselection box as the face recommendation area to input into the R-net and O-net networks for further detection and recognition to obtain the student face recognition result.

[0030] Furthermore, predict the face preselection box through the particle swarm according to the different weights assigned and the state transition matrix adopted, which specifically includes the following process:

[0031] ;

[0032] Among them, is the particle position corresponding to the next moment, is the particle position corresponding to the current moment, , is the state transition matrix, is the weight corresponding to the particle, is the control input;

[0033] Determine the position of the particle swarm through the positions of N particles, and determine the position of the face preselection box based on the position of the particle swarm.

[0034] Furthermore, generate the student's experimental operation score based on the experimental operation log, which specifically includes the following process:

[0035] Obtain the number of process steps actually operated by the trainee and the number of process steps that the trainee should operate based on the experimental operation log, and calculate the ratio of the number of process steps actually operated by the trainee to the number of process steps that the trainee should operate ;

[0036] Obtain the number of components actually used by the trainee and the number of components that the trainee should use based on the experimental operation log, and calculate the ratio of the number of components actually used by the trainee to the number of components that the trainee should use ;

[0037] Obtain the start time T0 and end time T1 of the trainee's operation based on the experimental operation log, and calculate the time period T from time T0 to time T1;

[0038] Obtain the order of the process steps actually operated by the trainee based on the experimental operation log, and determine whether the order of the process steps actually operated by the trainee is consistent with the order of the process steps of the predetermined operation. If so, the operation score coefficient R of the trainee is 1. If not, the operation score coefficient R of the trainee is 0;

[0039] The ratio 、ratio 、time period T and the operation score coefficient R of the trainee are substituted into the calculation formula of the trainee's experimental operation score LMS to obtain the trainee's experimental operation score LMS. The calculation formula is as follows:

[0040] ;

[0041] Among them, is the score base value corresponding to the experimental scenario. Different experimental scenarios correspond to different score base values, which are set by the science and technology special commissioner.

[0042] Furthermore, judging whether to generate an experimental diagnosis and improvement report based on the experimental operation score specifically includes the following steps:

[0043] Load the experimental operation score threshold, and judge whether the trainee's experimental operation score exceeds the preset experimental operation score threshold. If so, do not generate an experimental diagnosis and improvement report. If not, generate an experimental diagnosis and improvement report.

[0044] On the other hand, an experimental teaching system based on the science and technology special commissioner scenario, the system includes an experimental teaching scenario creation module, a cloud distribution center, an experimental operation log recording module, a face recognition module and an experimental operation score calculation module;

[0045] The experimental teaching scenario creation module is used to obtain the experimental teaching objectives and content, and create an experimental scenario based on the integration of the experimental teaching objectives and content;

[0046] The cloud distribution center is used to upload the experimental scenario to the cloud distribution center. The cloud distribution center obtains the node information of the student's experimental scenario operation node, generates an experimental scenario activation value based on the node information, and determines whether the student's experimental scenario operation node meets the experimental scenario reception requirements based on the experimental scenario activation value;

[0047] The experimental operation log recording module is used for the student's experimental scenario operation node to receive the experimental scenario. The student operates based on the experimental scenario, and generates an experimental operation log based on the student's operations;

[0048] The face recognition module is used to obtain the operation video generated by the student based on the experimental scenario, read the operation video, and perform face recognition on the operation video based on the student's face recognition model to obtain the student's face recognition result;

[0049] The experimental operation score calculation module is used to determine the experimental operation log corresponding to the student based on the student's face recognition result, generate the student's experimental operation score based on the experimental operation log, and determine whether to generate an experimental diagnosis and improvement report based on the experimental operation score.

[0050] Compared with the existing solutions, the beneficial effects achieved by the present invention are:

[0051] The present invention can create an experimental scenario based on the integration of experimental teaching objectives and content; generate an experimental scenario activation value based on the node information, and the cloud distribution center determines whether the student's experimental scenario operation node meets the experimental scenario reception requirements based on the experimental scenario activation value; obtain the operation video generated by the student based on the experimental scenario, read the operation video, and perform face recognition on the operation video based on the student's face recognition model to obtain the student's face recognition result; it can judge the node information of the student's experimental scenario operation node, ensure that the student's experimental scenario operation node meets the experimental operation requirements, and further improve the efficiency of the experiment.

[0052] The present invention can generate the student's experimental operation score based on the experimental operation log, and determine to generate an experimental diagnosis and improvement report based on the experimental operation score. Through the real scenario of the science and technology commissioner's experimental teaching and simulated role-playing, students can better master the professional skills and operation methods required for the front line of production. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0054] Figure 1It is the workflow diagram of an experimental teaching method based on the scenario of science and technology special commissioners in an embodiment of the present invention;

[0055] Figure 2 It is the workflow diagram of another experimental teaching method based on the scenario of science and technology special commissioners in an embodiment of the present invention;

[0056] Figure 3 It is the workflow diagram of another experimental teaching method based on the scenario of science and technology special commissioners in an embodiment of the present invention;

[0057] Figure 4 It is the system block diagram of an experimental teaching system based on the scenario of science and technology special commissioners in an embodiment of the present invention. Detailed implementation manners

[0058] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0059] In addition, the described features, structures or characteristics may be combined in any suitable manner in one or more example embodiments. In the following description, many specific details are provided to give a thorough understanding of the example embodiments of the present disclosure. However, those skilled in the art will realize that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, steps, etc. may be used. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0060] This embodiment provides an experimental teaching method based on the scenario of science and technology special commissioners. Figure 1 It is the workflow diagram of an experimental teaching method based on the scenario of science and technology special commissioners in an embodiment of the present invention. As Figure 1 shown, the method includes the following steps:

[0061] Step S101: Obtain the experimental teaching objectives and contents, and create an experimental scenario based on the integration of the experimental teaching objectives and contents;

[0062] Step S102: Upload the experimental scenario to the cloud distribution center. The cloud distribution center obtains the node information of the operation nodes of the experimental scenario of the trainees, generates an experimental scenario activation value based on the node information, and the cloud distribution center determines whether the operation nodes of the experimental scenario of the trainees meet the experimental scenario reception requirements based on the experimental scenario activation value.

[0063] Step S103: The operation node of the trainee's experimental scenario receives the experimental scenario. The trainee operates based on the experimental scenario, and an experimental operation log is generated based on the trainee's operation record.

[0064] Step S104: Obtain the operation video generated by the trainee based on the experimental scenario, read the operation video, and perform trainee face recognition on the operation video based on the trainee face recognition model to obtain the trainee face recognition result.

[0065] Step S105: Determine the experimental operation log corresponding to the trainee based on the trainee face recognition result, generate the experimental operation score of the trainee based on the experimental operation log, and determine whether to generate an experimental diagnosis and improvement report according to the experimental operation score.

[0066] In summary, the present invention can create an experimental scenario based on the integration of experimental teaching objectives and content; generate an experimental scenario activation value based on node information, and the cloud distribution center determines whether the operation node of the trainee's experimental scenario meets the experimental scenario reception requirements based on the experimental scenario activation value; obtain the operation video generated by the trainee based on the experimental scenario, read the operation video, and perform trainee face recognition on the operation video based on the trainee face recognition model to obtain the trainee face recognition result; can judge the node information of the operation node of the trainee's experimental scenario, can ensure that the operation node of the trainee's experimental scenario meets the experimental operation requirements, and further improve the efficiency of the experiment.

[0067] The present invention can generate the experimental operation score of the trainee based on the experimental operation log, and determine whether to generate an experimental diagnosis and improvement report according to the experimental operation score. Through the real scenario of the science and technology commissioner's experimental teaching and simulated role-playing, trainees can better master the professional skills and operation methods required for the front line of production.

[0068] In some embodiments, in step S101, Figure 2 is the workflow diagram of another experimental teaching method based on the science and technology commissioner scenario of the embodiment of the present invention. As Figure 2 shown, creating an experimental scenario based on the integration of experimental teaching objectives and content specifically includes the following steps:

[0069] Step S201: Determine the experimental components in the experimental component library based on the experimental teaching objectives and content. Among them, the experimental components include laboratory equipment, low-value consumables, experimental materials, and components of the database type. Different experimental teaching objectives and content correspond to different experimental components in the experimental component library.

[0070] Step S202: The experimental components in the experimental component library are displayed on the building interface through a selection instruction, and a virtual experimental process is obtained by combining the experimental components through a building instruction.

[0071] Specifically, it includes the following process:

[0072] Receive the virtual experiment setup instructions of the science and technology special commissioner and execute to display the experimental component library interface and the setup interface;

[0073] After receiving the selection instruction or drag instruction, the experimental components in the experimental component library interface are displayed in the setup interface; after the experimental components in the setup interface receive the attribute selection instruction, the component attributes are displayed and the component attributes are determined through the confirmation instruction to obtain the experimental components with confirmed component attributes; after the experimental components with confirmed component attributes receive the connection instruction, the experimental components are connected to obtain the virtual experiment process;

[0074] Step S203: Publish the virtual experiment process to obtain the experimental scenario.

[0075] In some embodiments, generating the experimental scenario activation value based on the node information specifically includes the following process:

[0076] Obtain the load rate of the node based on the node information ;

[0077] Obtain the computing power of the node based on the node information, and count the predicted computing power corresponding to the experimental scenario, calculate the difference between the node computing power and the predicted computing power, and record the difference as the computing power redundancy A;

[0078] Obtain the delay B of the node and the data transmission distance C from the node to the cloud distribution center based on the node information;

[0079] Substitute the load rate , the computing power redundancy A, the delay B, and the data transmission distance C into the experimental scenario activation value calculation formula to obtain the experimental scenario activation value. The calculation formula is as follows:

[0080] ;

[0081] Among them, is the experimental scenario activation value, and the value of e is 2.72.

[0082] Further, the cloud distribution center determines whether the operation node of the student's experimental scenario meets the experimental scenario reception requirements based on the experimental scenario activation value, which specifically includes the following process:

[0083] Obtain the experimental scenario activation value threshold, where the experimental scenario activation value threshold is stored in the cloud distribution center, and determine whether the experimental scenario activation value exceeds the experimental scenario activation value threshold. If so, it is determined that the operation node of the student's experimental scenario meets the experimental scenario reception requirements; if not, it is determined that the operation node of the student's experimental scenario does not meet the experimental scenario reception requirements.

[0084] In some embodiments, performing student face recognition on the operation video based on the student face recognition model to obtain the student face recognition result specifically includes the following process:

[0085] Use the MTCNN network to detect the position of the student's first-frame face in the operation video. Initialize the particle filter according to the position of the first-frame face, perform random particle resampling, update the weight distribution of the particles, and predict the face pre-selection box through the particle swarm according to the different weights assigned and the state transition matrix adopted. Use the pre-selection box as the face recommendation area and input it into the R-net and O-net networks for further detection and recognition to obtain the student face recognition result.

[0086] It should be noted that MTCNN (Multi-task Cascaded Convolutional Networks) is a classic face detection and key point localization network, which consists of three cascaded convolutional neural networks, namely P-Net (Proposal Network), R-Net (Refine Network) and O-Net (Output Network), for realizing the face recognition task.

[0087] In some embodiments, using the MTCNN network to detect the position of the student's first-frame face in the operation video specifically includes the following process:

[0088] Use the image pyramid technology to scale the first-frame face image of the student in the operation video at different scales, and then input it into the P-net network to generate face candidate boxes. Among them, the MTCNN network includes a structure of three cascaded neural networks, which are composed of three layers of networks: the P-net network, the R-net network, and the O-net network;

[0089] Specifically, the image pyramid technology is an effective multi-scale image representation method, which is often used in scale space analysis in image processing, including image enhancement, feature extraction, and target detection.

[0090] The P-net network initially extracts features and calibrates positions through FCN (Fully Convolutional Networks), then uses non-maximum suppression to exclude candidate boxes with high overlap, and performs correction through bounding box regression to obtain candidate boxes. The candidate boxes obtained by the P-net network are intercepted in the original image and used as the input of the R-net to obtain the position of the student's first-frame face. Among them, the bounding box regression uses the Euclidean distance as the loss function of the distance metric.

[0091] In some embodiments, in step S103, Figure 3 is the flowchart of another experimental teaching method based on the science and technology commissioner scenario in the embodiments of the present invention. As Figure 3 shown, initializing the particle filter according to the position of the first-frame face and performing random particle resampling and updating the weight distribution of the particles specifically include the following steps:

[0092] Step S301: Initialize the particle filter according to the first-frame face position. Particle initialization means placing particles in the image in a given or random manner, and specifying that the initial state of the particles is consistent with the tracking region.

[0093] Step S302: Use the prior probability of the previous time to estimate the posterior probability density in the current scenario.

[0094] Step S303: Calculate the similarity of the particles, and calculate the similarity of each particle with the tracking region.

[0095] Step S304: Update the weight of each particle according to the similarity and normalize it.

[0096] Step S305: Particle resampling, eliminating particles with low weights, and generating more particles by duplicating particles with high weights.

[0097] Step S306: Set the number of iterations and stop resampling until the number of iterations is reached.

[0098] Furthermore, the particle resampling specifically includes the following process:

[0099] 1) Particle screening: N is the number of particle sets, and they are sorted according to the particle weights. Sort the weights of each current particle, set a weight threshold, eliminate those below the threshold, and retain the particle swarm with weights higher than the threshold as the replication object.

[0100] 2) Particle replication: Each time, a fixed space is reserved to add random particles, that is, the number of replicated particles remains constant at i. Determine the number of particles with different weights to be replicated by comparing the size relationship between the number of particles in the screened particle swarm and i.

[0101] 3) Adding random particles: Divide the particles into intervals. The number of interval divisions is greater than N - i. Randomly select N - i intervals for uniform sampling, sample N - i particles with different weights, and add the previously replicated i particles. The total number of particles after sampling remains N unchanged.

[0102] In some embodiments, according to the different weights assigned and the state transition matrix adopted, predict the face pre-selection box through the particle swarm, which specifically includes the following process:

[0103] ;

[0104] Among them, is the particle position corresponding to the next moment, is the particle position corresponding to the current moment, and are the state transition matrices, is the weight corresponding to the particle, For the control input;

[0105] Determine the position of the particle swarm through the positions of N particles, and determine the position of the face preselection box based on the position of the particle swarm.

[0106] In some embodiments, generating the experimental operation score of a trainee based on the experimental operation log specifically includes the following process:

[0107] Obtain the number of process steps actually operated by the trainee and the number of process steps that the trainee should operate based on the experimental operation log, and calculate the ratio of the number of process steps actually operated by the trainee to the number of process steps that the trainee should operate ;

[0108] Obtain the number of components actually used by the trainee and the number of components that the trainee should use based on the experimental operation log, and calculate the ratio of the number of components actually used by the trainee to the number of components that the trainee should use ;

[0109] Obtain the start time T0 and end time T1 of the trainee's operation based on the experimental operation log, and calculate the time period T from time T0 to time T1;

[0110] Obtain the order of the process steps actually operated by the trainee based on the experimental operation log, and determine whether the order of the process steps actually operated by the trainee is consistent with the order of the process steps of the predetermined operation. If so, the operation score coefficient R of the trainee is 1, and if not, the operation score coefficient R of the trainee is 0;

[0111] Substitute the ratio 、ratio 、time period T and the operation score coefficient R of the trainee into the calculation formula of the experimental operation score LMS of the trainee to obtain the experimental operation score LMS of the trainee. The calculation formula is as follows:

[0112] ;

[0113] Among them, is the score base value corresponding to the experimental scenario. Different experimental scenarios correspond to different score base values, which are set by the science and technology special commissioner.

[0114] Furthermore, determining whether to generate an experimental diagnosis and improvement report based on the experimental operation score specifically includes the following steps:

[0115] Load the experimental operation score threshold, and determine whether the experimental operation score of the trainee exceeds the preset experimental operation score threshold. If so, do not generate an experimental diagnosis and improvement report, and if not, generate an experimental diagnosis and improvement report.

[0116] Generating the experimental diagnosis and improvement report specifically includes:

[0117] Experimental preparation stage

[0118] Analyze the preparation of trainees before the experiment, including the understanding of preview materials, the preparation of experimental tools, etc.

[0119] Point out whether there are problems such as insufficient preparation and unclear understanding of the experimental purpose.

[0120] Experimental operation stage

[0121] Detailedly record the performance of trainees during the experimental operation process, including the mastery of skills, the standardization of operations, the reactions when encountering problems, etc.

[0122] Analyze in which links trainees show deficiencies, such as unskilled operations, neglect of details, lack of innovative thinking, etc.

[0123] Experimental results and analysis

[0124] Evaluate the experimental results of trainees, including the accuracy of data, the rationality of conclusions, etc.

[0125] Analyze the gap between the experimental results and the expected goals, and the reasons for this gap.

[0126] The present invention also provides an experimental teaching system based on the scenario of science and technology commissioners, Figure 4 which is a system block diagram of an experimental teaching system based on the scenario of science and technology commissioners according to an embodiment of the present invention, as Figure 4 shown. The system includes an experimental teaching scenario creation module, a cloud distribution center, an experimental operation log recording module, a face recognition module, and an experimental operation score calculation module;

[0127] The experimental teaching scenario creation module is used to obtain the experimental teaching objectives and contents, and create an experimental scenario based on the integration of the experimental teaching objectives and contents;

[0128] The cloud distribution center is used to upload the experimental scenario to the cloud distribution center. The cloud distribution center obtains the node information of the operation nodes of the trainee's experimental scenario, generates an experimental scenario activation value based on the node information, and the cloud distribution center judges whether the operation nodes of the trainee's experimental scenario meet the experimental scenario reception requirements based on the experimental scenario activation value;

[0129] The experimental operation log recording module is used for the operation nodes of the trainee's experimental scenario to receive the experimental scenario. The trainee operates based on the experimental scenario, and generates an experimental operation log based on the trainee's operation records;

[0130] The face recognition module is used to obtain the operation video generated by the trainee based on the experimental scenario, read the operation video, and perform face recognition on the operation video based on the trainee's face recognition model to obtain the trainee's face recognition result;

[0131] The experimental operation score calculation module is used to determine the experimental operation log corresponding to the trainee based on the trainee's face recognition result, generate the experimental operation score of the trainee based on the experimental operation log, and determine whether to generate an experimental diagnosis and improvement report according to the experimental operation score.

[0132] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that includes one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0133] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0134] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0135] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only for some logical function divisions. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0136] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. An experimental teaching method based on the scenario of science and technology special commissioners, characterized in that the method Including: Obtain the experimental teaching objectives and content, and create an experimental scenario based on the integration of the experimental teaching objectives and content; Upload the experimental scenario to the cloud distribution center. The cloud distribution center obtains the node information of the operation nodes of the trainee's experimental scenario, generates an experimental scenario activation value based on the node information, and the cloud distribution center determines whether the operation nodes of the trainee's experimental scenario meet the experimental scenario reception requirements based on the experimental scenario activation value; Among them, generating the experimental scenario activation value based on the node information specifically includes the following process: Obtain the load rate of a node based on node information ; Obtain the node computing power based on the node information, and count the predicted computing power corresponding to the experimental scenario. Calculate the difference between the node computing power and the predicted computing power, and record the difference as the computing power redundancy A; Obtain the delay B of the node and the data transmission distance C from the node to the cloud distribution center based on the node information; Substitute the load factor , the computing power redundancy A, the latency B, and the data transmission distance C into the calculation formula for the experimental scenario activation value to obtain the experimental scenario activation value. The calculation formula is as follows: ； Among them, is the activation value of the experimental scenario, and the value of e is 2.72; The operation nodes of the trainee's experimental scenario receive the experimental scenario. The trainee operates based on the experimental scenario, and generates an experimental operation log based on the trainee's operation record; Obtain the operation video generated by the trainee based on the experimental scenario, read the operation video, and perform face recognition of the trainee on the operation video based on the trainee face recognition model to obtain the trainee face recognition result: Use the MTCNN network to detect the position of the trainee's first-frame face in the operation video, initialize the particle filter according to the position of the first-frame face, and perform random particle resampling. Update the weight distribution of the particles. According to the different weights assigned and the state transition matrix adopted, predict the face pre-selection box through the particle swarm, specifically including the following process: ； Among them, is the particle position corresponding to the next moment, is the particle position corresponding to the current moment, , is the state transition matrix, is the weight corresponding to the particle, is the control input; Determine the position of the particle swarm through the positions of N particles, and determine the position of the face pre-selection box based on the position of the particle swarm; Take the pre-selection box as the face recommendation area and input it into the R-net and O-net networks for further detection and recognition to obtain the trainee face recognition result; Determine the experimental operation log corresponding to the trainee based on the trainee face recognition result, generate the experimental operation score of the trainee based on the experimental operation log, and determine whether to generate an experimental diagnosis and improvement report according to the experimental operation score. Among them, generating the experimental operation score of the trainee based on the experimental operation log specifically includes the following process: Obtain the number of process steps actually operated by the trainee and the number of process steps that the trainee should operate based on the experimental operation log, and calculate the proportion of the number of process steps actually operated by the trainee to the number of process steps that the trainee should operate ; Obtain the number of components actually used by the trainee and the number of components that the trainee should use based on the experimental operation log, and calculate the proportion of the number of components actually used by the trainee to the number of components that the trainee should use ; Obtain the start time T0 and end time T1 of the trainee's operation based on the experimental operation log, and calculate the time period T from time T0 to time T1; Obtain the sequence of the process steps of the trainee's actual operation based on the experimental operation log, and determine whether the sequence of the process steps of the trainee's actual operation is consistent with the predetermined sequence of the operation process steps. If so, the operation score coefficient R of the trainee is 1. If not, the operation score coefficient R of the trainee is 0; Substitute the ratio , ratio , time period T and the operation score coefficient R of the trainee into the calculation formula of the experimental operation score LMS of the trainee to obtain the experimental operation score LMS of the trainee. The calculation formula is as follows: ； Among them, is the score base value corresponding to the experimental scenario. Different experimental scenarios correspond to different score base values, which are set by the science and technology special commissioners.

2. The experimental teaching method based on the scenario of science and technology special commissioners according to claim 1, wherein Creating an experimental scenario based on the integration of the experimental teaching objectives and content specifically includes the following process: Determine the experimental components in the experimental component library based on the experimental teaching objectives and content. Among them, the experimental components include laboratory equipment, low-value consumables, experimental materials, and components of the database type. Different experimental teaching objectives and content correspond to different experimental components in the experimental component library; The experimental components in the experimental component library are displayed on the construction interface through a selection instruction, and a virtual experimental process is obtained by combining the experimental components through a construction instruction; Receive the virtual experiment construction instruction of the science and technology commissioner and execute to display the experimental component library interface and the construction interface; After receiving a selection instruction or a drag-and-drop instruction, the experimental components in the experimental component library interface are displayed in the building interface; after receiving an attribute selection instruction, the experimental components in the building interface display the component attributes and determine the component attributes through a confirmation instruction to obtain the experimental components with confirmed component attributes; after receiving a connection instruction, the experimental components with confirmed component attributes are connected to obtain a virtual experimental process; The virtual experimental process is published to obtain an experimental scenario.

3. The experimental teaching method based on the scenario of science and technology special commissioners according to claim 1 is characterized in that, The cloud distribution center determines whether the operation nodes of the student's experimental scenario meet the requirements for receiving the experimental scenario based on the activation value of the experimental scenario, which specifically includes the following process: Obtain the threshold value of the experimental scenario activation value. Among them, the threshold value of the experimental scenario activation value is stored in the cloud distribution center. Determine whether the experimental scenario activation value exceeds the threshold value of the experimental scenario activation value. If so, it is determined that the operation nodes of the student's experimental scenario meet the requirements for receiving the experimental scenario. If not, it is determined that the operation nodes of the student's experimental scenario do not meet the requirements for receiving the experimental scenario.

4. The experimental teaching method based on the science and technology special commissioner scenario according to claim 1, characterized in that, Determine whether to generate an experimental diagnosis and improvement report based on the experimental operation score, which specifically includes the following steps: Load the threshold value of the experimental operation score. Determine whether the student's experimental operation score exceeds the preset threshold value of the experimental operation score. If so, no experimental diagnosis and improvement report is generated. If not, an experimental diagnosis and improvement report is generated.

5. An experimental teaching system based on the scenario of science and technology special commissioners, characterized in that, Applicable to an experimental teaching method based on the scenario of science and technology commissioners described in any one of claims 1 to 4. The system includes an experimental teaching scenario creation module, a cloud distribution center, an experimental operation log recording module, a face recognition module, and an experimental operation score calculation module; The experimental teaching scenario creation module is used to obtain the experimental teaching objectives and content, and create an experimental scenario based on the integration of the experimental teaching objectives and content; The cloud distribution center is used to upload the experimental scenario to the cloud distribution center. The cloud distribution center obtains the node information of the operation nodes of the student's experimental scenario, generates an experimental scenario activation value based on the node information, and the cloud distribution center determines whether the operation nodes of the student's experimental scenario meet the requirements for receiving the experimental scenario based on the experimental scenario activation value; The experimental operation log recording module is used for the operation nodes of the student's experimental scenario to receive the experimental scenario. The student operates based on the experimental scenario, and an experimental operation log is generated based on the student's operation records; The face recognition module is used to obtain the operation video generated by the student based on the experimental scenario, read the operation video, and perform face recognition on the operation video based on the student's face recognition model to obtain the face recognition result of the student; The experimental operation score calculation module is used to determine the experimental operation log corresponding to the student based on the face recognition result of the student, generate the experimental operation score of the student based on the experimental operation log, and determine whether to generate an experimental diagnosis and improvement report based on the experimental operation score.

Images