Intelligent interactive evaluation and team cooperation management system for higher vocational colleges

Abstract

The invention discloses a higher vocational college-oriented intelligent interactive evaluation and team cooperation management system, and the system comprises a data collection module which is used for obtaining initial physiological parameters and initial operation parameters corresponding to a target practical training scene, and carrying out the data processing of the initial physiological parameters and the initial operation parameters, so as to obtain initial operation data; the data verification module is used for carrying out data verification and correction on the initial operation data to obtain calibration operation data; the data fusion module is used for performing data fusion processing on the calibration operation data to obtain fusion operation data; the data weighting module is used for performing weighting processing based on the initial physiological parameters, the initial operation parameters and the fusion operation data to obtain weighted operation data; the data evaluation module is used for extracting feature information from the weighted operation data and generating operation evaluation information; and the data feedback module is used for generating real-time feedback information in combination with the operation evaluation information and the weighted operation data. According to the invention, comprehensiveness and accuracy of user practical training operation evaluation can be improved.

Description

Technical Field

[0001] The present invention relates to the field of big data technology, and more specifically, to an intelligent interactive evaluation and team collaboration management system for higher vocational colleges. Background Art

[0002] In higher vocational education, the traditional evaluation methods for students' learning effects have obvious deficiencies, mainly reflected in the neglect of the students' team collaboration process and the continuous stability of practical operations. The current online evaluation systems mostly focus on the correctness of knowledge answering, and cannot comprehensively quantify multi-dimensional indicators such as the cooperation degree, interaction frequency, and operation quality of students in experimental operations and project promotion. In addition, some evaluation platforms lack dynamic monitoring of the practical operation process, and it is difficult to identify and adjust in a timely manner when students encounter sudden errors or team conflicts. Therefore, there are defects such as incomplete and inaccurate evaluation in the related technologies for the practical training operation process of higher vocational colleges. Summary of the Invention

[0003] In view of the above-mentioned defects of the prior art, the technical problem to be solved by the present invention is how to improve the comprehensiveness and accuracy of the evaluation of users' practical training operations.

[0004] To solve at least one of the above-mentioned technical problems, the present invention provides an intelligent interactive evaluation and team collaboration management system for higher vocational colleges.

[0005] According to one aspect of the present disclosure, there is provided an intelligent interactive evaluation and team collaboration management system for higher vocational colleges, including:

[0006] A data acquisition module, configured to obtain initial physiological parameters and initial operation parameters corresponding to a target practical training scenario, and perform data processing on the initial physiological parameters and the initial operation parameters to obtain initial operation data;

[0007] A data verification module, configured to perform data verification and correction on the initial operation data to obtain calibrated operation data;

[0008] A data fusion module, configured to perform data fusion processing on the calibrated operation data to obtain fused operation data;

[0009] A data weighting module, configured to perform weighting processing based on the initial physiological parameters, the initial operation parameters, and the fused operation data to obtain weighted operation data;

[0010] A data evaluation module, configured to extract feature information from the weighted operation data and generate operation evaluation information based on the feature information;

[0011] A data feedback module, configured to combine the operation evaluation information and the weighted operation data to generate real-time feedback information corresponding to the target practical training scenario.

[0012] In a specific embodiment, the data acquisition module includes:

[0013] A data acquisition unit for acquiring the initial physiological parameters and the initial operation parameters;

[0014] A data preprocessing unit electrically connected to the data acquisition unit for preprocessing the initial operation parameters to obtain data to be synchronized;

[0015] A data synchronization unit electrically connected to the data acquisition unit and the data preprocessing unit respectively for performing data alignment processing on the data to be synchronized and the initial physiological parameters to obtain the initial operation data.

[0016] In a specific embodiment, the data verification module includes:

[0017] A compensation value calculation unit electrically connected to the data acquisition module for performing data compensation processing on the initial operation data to obtain a data compensation value;

[0018] A data correction unit electrically connected to the compensation value calculation unit for correcting the original timestamp based on the data compensation value to obtain a calibrated timestamp; the original timestamp is the timestamp corresponding to the acquisition of the initial physiological parameters and the initial operation parameters;

[0019] A first data integration unit electrically connected to the data acquisition module and the data correction unit respectively for performing first data integration processing based on the calibrated timestamp, the initial physiological parameters and the initial operation parameters to obtain calibrated operation data.

[0020] In a specific embodiment, the data fusion module includes:

[0021] A first data fusion unit electrically connected to the data verification module for performing first fusion processing based on channel weight data, the number of channels and the calibrated operation data to obtain a first fusion data set; the channel weight data and the number of channels are determined based on the channels when the calibrated operation data is transmitted;

[0022] A second data fusion unit electrically connected to the first data fusion unit for performing second fusion processing on the first fusion data set based on a data fusion formula to obtain a second fusion data set;

[0023] A second data integration unit electrically connected to the second data fusion unit for performing second data integration processing based on the second fusion data set and the calibrated operation data to obtain the fusion operation data.

[0024] In a specific embodiment, the data weighting module includes:

[0025] A weighting processing unit, electrically connected to the data fusion unit, for performing weighted correction on the calibration timestamp based on a reference time value to obtain a target timestamp;

[0026] A third data integration unit, electrically connected to the weighting processing unit, for performing third data integration processing on the target timestamp, the initial physiological parameters, and the initial operation parameters to obtain the weighted operation data.

[0027] In a specific embodiment, the data weighting module further includes:

[0028] A reference time acquisition unit, for acquiring the reference time value.

[0029] In a specific embodiment, the data evaluation module includes:

[0030] A feature extraction unit, electrically connected to the data weighting module, for extracting features from the weighted operation data to obtain the feature information;

[0031] An operation evaluation unit, electrically connected to the feature extraction unit, for calculating the operation evaluation information based on the feature information and an evaluation function.

[0032] In a specific embodiment, the operation evaluation unit is further configured to perform anomaly detection based on the operation evaluation information to obtain an anomaly detection result.

[0033] In a specific embodiment, the data feedback module includes:

[0034] A data feedback unit, electrically connected to the data evaluation module, for generating real-time feedback information and adjustment instructions based on the operation evaluation information and the anomaly detection result.

[0035] In a specific embodiment, the system further includes:

[0036] An output module, electrically connected to the data feedback module, for performing formatting processing on the real-time feedback information to obtain target feedback information.

[0037] Implementing the present invention has the following beneficial effects:

[0038] Through the collaborative operation of multiple modules such as data collection, data verification, data fusion, data weighting, data evaluation, and data feedback, the present invention can improve the accuracy and comprehensiveness of the evaluation in the training scenarios of higher vocational colleges, and can also take into account the team collaboration efficiency. Specifically, after collecting data, verifying, fusing, and weighting the data can reduce data errors while making the evaluation results more in line with the training scenarios, thereby improving the evaluation accuracy. In addition, the system can analyze the operation conditions of team members through the data fusion and weighting mechanisms to provide team collaboration evaluation, thus improving the comprehensiveness of the evaluation of the training process. Moreover, the system can generate feedback information in real time through the data feedback module, thereby improving the real-time monitoring of the training process. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention 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 of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0040] Figure 1 FIG. 1 is a first system architecture diagram of the intelligent interactive evaluation and team collaboration management system for higher vocational colleges provided by an embodiment of the present invention;

[0041] Figure 2 FIG. 2 is a schematic architecture diagram corresponding to the data collection module provided by an embodiment of the present invention;

[0042] Figure 3 FIG. 3 is a schematic architecture diagram corresponding to the data verification module provided by an embodiment of the present invention;

[0043] Figure 4 FIG. 4 is a schematic architecture diagram corresponding to the data fusion module provided by an embodiment of the present invention;

[0044] Figure 5 FIG. 5 is a schematic architecture diagram corresponding to the data weighting module provided by an embodiment of the present invention;

[0045] Figure 6 FIG. 6 is a second system architecture diagram of the intelligent interactive evaluation and team collaboration management system for higher vocational colleges provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] The following will clearly and completely describe the technical solutions in the embodiments of this specification with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of this invention.

[0047] It should be noted that the terms "first", "second", etc. in the specification and claims of this invention and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of this invention described here can be implemented in an order different from those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0048] The following will detail various exemplary embodiments, features, and aspects of the present disclosure with reference to the accompanying drawings. The same reference numerals in the drawings denote elements having the same or similar functions. Although various aspects of the embodiments are shown in the drawings, the drawings do not have to be drawn to scale unless otherwise specified.

[0049] The special term "exemplary" here means "serving as an example, embodiment, or illustrative". Any embodiment described here as "exemplary" does not have to be construed as superior to or better than other embodiments.

[0050] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" in this article means any one of multiple or any combination of at least two of multiple. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set composed of A, B, and C.

[0051] In addition, to better illustrate the present disclosure, numerous specific details are given in the following specific implementation manners. Those skilled in the art should understand that the present disclosure can also be implemented without some specific details. In some instances, methods, means, elements, and circuits well-known to those skilled in the art are not described in detail to highlight the gist of the present disclosure.

[0052] Figure 1This is the system architecture diagram corresponding to the intelligent interactive evaluation and team collaboration management system for higher vocational colleges provided by the embodiments of the present invention. As Figure 1 shown, the intelligent interactive evaluation and team collaboration management system for higher vocational colleges includes:

[0053] A data acquisition module, configured to obtain the initial physiological parameters and initial operation parameters corresponding to the target training scenario, and perform data processing on the initial physiological parameters and initial operation parameters to obtain initial operation data;

[0054] A data verification module, configured to perform data verification and correction on the initial operation data to obtain calibrated operation data;

[0055] A data fusion module, configured to perform data fusion processing on the calibrated operation data to obtain fused operation data;

[0056] A data weighting module, configured to perform weighting processing based on the initial physiological parameters, initial operation parameters, and fused operation data to obtain weighted operation data;

[0057] A data evaluation module, configured to extract feature information from the weighted operation data and generate operation evaluation information based on the feature information;

[0058] A data feedback module, configured to combine the operation evaluation information and the weighted operation data to generate real-time feedback information corresponding to the target training scenario.

[0059] In a specific embodiment, the intelligent interactive evaluation and team collaboration management system for higher vocational colleges may include a data acquisition module, a data verification module, a data fusion module, a data weighting module, a data evaluation module, and a data feedback module.

[0060] Specifically, the target training scenario may be any scenario where students perform training operations. The physiological information of students collected in this scenario is the initial physiological parameters, and the operation parameters collected by students during the training operation are the initial operation parameters.

[0061] The data acquisition module may be deployed on multiple sensor nodes. The multiple sensor nodes may be cameras, VR (Virtual Reality) positioning modules, training operation terminals, training online discussion platforms, etc. At the same time, for each sensor node, a sensor module for obtaining user physiological information may be embedded to detect hand movement parameters, eye movement parameters, user heart rate, and skin electrical activity in the target training scenario, so as to record the physiological state of the user in the target training scenario in real time and use it as the initial physiological parameters. Among them, for high-dynamic VR scenarios, the actions, interaction logs, and positioning data of students during the actual operation can be focused on collecting.

[0062] The sensor module may include an IMU sensor (Inertial Measurement Unit), an eye tracker, a pressure sensor, an EDA sensor, an ECG sensor, etc., to obtain initial physiological parameters, ensure that the sensors can cover each user in the entire target training scenario, and can collect the changes in their physiological information in real time. For example, use the IMU sensor in combination with the pressure sensor to measure the hand movement parameters of the user, use the eye tracker to measure the eye movement parameters of the user, use the EDA sensor to obtain the skin electrical activity of the user, and use the ECG sensor to obtain the user's heart rate. For the data corresponding to the skin electrical activity and the user's heart rate, the two can be cross-validated with each other, or one of the two can be obtained separately. In the present invention, the skin electrical activity is taken as an example for illustration.

[0063] Specifically, the hand movement parameters can be used to analyze the accuracy, stability and strength of the user's hand movement. For example, in fine operation tasks, the hand coordination and fatigue level can be evaluated. The eye movement parameters can reveal whether the user efficiently focuses on the key areas, and can be used to analyze the attention distribution, visual search pattern and information processing efficiency. The user's heart rate can reflect the user's fatigue or stress state, and can be used to analyze the user's physiological load and stress level. The skin electrical activity is mainly used to evaluate the emotional and stress levels, and the physiological signals it reflects may have a direct or indirect impact on the training process. For example, a high skin conductance value is usually associated with the activation of the sympathetic nervous system, which may cause muscle tension and affect fine hand operations, such as the operation of experimental instruments; or, sweating on the skin will change the friction between the palm or fingers and the device, which may affect the grasping force and tactile perception, thus affecting the task performance. Therefore, combining physiological parameters can comprehensively reflect and analyze the influencing factors of the user during the training process.

[0064] In a specific embodiment, a data verification module can also be deployed in each sensor node. Using the initial operation data obtained by the data acquisition module, a non-linear regression model is used to predict the internal clock drift trend and compensate it in real time. For example, in VR training, due to long-term high-load operation, clock errors are caused, and the errors are controlled within the range of microseconds to sub-milliseconds through a compensation algorithm.

[0065] As Figure 2 shown, the data acquisition module includes:

[0066] A data acquisition unit for acquiring initial physiological parameters and initial operation parameters;

[0067] In a specific embodiment, the initial physiological parameters can be represented in matrix form and consist of multiple variables. Define the initial physiological parameter E as follows:

[0068] E = [T H P]

[0069] Among them, T represents hand movement parameters, H represents eye movement parameters, and P represents the user's skin electrical activity.

[0070] In a specific embodiment, sensor data can be read regularly, and the data can be written into a local database through an interface. Each sensor node reports data regularly (such as every second) to capture the real-time changes of physiological parameters and obtain the initial physiological parameters represented by matrix E.

[0071] In a specific embodiment, the data acquisition unit is also used to obtain the initial operation parameters corresponding to the students participating in the training. The initial operation parameters can include the position parameters of the team members, i.e., students, the operation trajectory parameters, and the interaction parameters between members.

[0072] Specifically, in the target training scenario, RFID card readers, cameras, and VR positioning devices can be deployed in the team operation area to obtain the position parameters of team members, the operation trajectory parameters, and the interaction parameters between members. RFID tags can be used to identify personnel identities, cameras cooperate with computer vision to identify personnel positions, and the VR positioning module is used to accurately track the action trajectories of users to generate operation trajectory parameters and interaction parameters between members.

[0073] In addition, an ultra-wideband (UWB) positioning system can also be introduced to improve the positioning accuracy. The indoor positioning accuracy of UWB can reach 10 - 30 centimeters, which can meet the requirements of fine operation recording.

[0074] The data preprocessing unit, electrically connected to the data acquisition unit, is used to perform data preprocessing on the initial operation parameters to obtain the operation data to be synchronized;

[0075] In a specific embodiment, the data preprocessing unit can also fuse the position parameters, operation trajectory parameters, and interaction parameters between members obtained through various positioning means to ensure the accuracy and reliability of the obtained initial operation parameters. At the same time, the data preprocessing unit can also perform preprocessing such as denoising and smoothing on the initial physiological parameters and initial operation parameters.

[0076] Specifically, the operation data to be synchronized can be represented in matrix form and consists of the position parameters of multiple students and the acquisition time of the position parameters. Define the operation data to be synchronized O as follows:

[0077]

[0078] Among them, x, y, and z respectively represent the three-dimensional coordinates of the students or training operations in the target training scenario, with the unit of meters, which can be obtained through RFID / UWB positioning or camera positioning algorithms; n is the number of students, and t is the original timestamp, representing the data acquisition time, sorted in chronological order.

[0079] A data synchronization unit, electrically connected to the data preprocessing unit, is configured to perform data alignment processing on the data to be synchronized and the initial physiological parameters to obtain initial operation data.

[0080] In a specific embodiment, the data synchronization unit is electrically connected to the data preprocessing unit and can also be electrically connected to the data acquisition unit to obtain the initial physiological parameter E and the data to be synchronized O, and format and integrate the initial physiological parameter E and the data to be synchronized O to ensure that their acquisition times are aligned.

[0081] Specifically, the Precision Time Protocol (PTP) can be used to synchronize the clocks of each sensor node. The Precision Time Protocol (PTP) is a network protocol that can synchronize the clocks of the entire computer network to sub-microsecond accuracy. By deploying PTP clients on each sensor node and synchronizing the time with the master control server (PTP master clock), a unified time reference for the initial physiological parameters and the initial operation parameters is ensured. Finally, the initial physiological parameters and the initial operation parameters are combined to form the initial operation data for storage and subsequent analysis.

[0082] Pair the initial physiological parameter E and the data to be synchronized O according to the time stamp to obtain the final initial operation data D:

[0083]

[0084] The initial operation data D can include multiple records. Each record corresponds to an acquisition moment, i.e., the original time stamp, and includes both the initial physiological parameter and the data to be synchronized.

[0085] In a specific embodiment, multiple topics can be created under the ROS (Robot Operating System) framework to publish the initial physiological parameter and the initial operation parameter, and the time synchronization mechanism or message synchronization tool of ROS can be used to pair the initial physiological parameter E and the data to be synchronized O that are close to the original time stamp. At the same time, the IEEE 1588 PTP protocol can be deployed on the underlying network to ensure that the system clocks of each sensor node are synchronized to the sub-millisecond level, and the synchronized initial operation data is written into the database or saved through ROS message recording.

[0086] In the data acquisition module, after the data acquisition unit obtains the initial physiological parameters and initial operation parameters corresponding to the target training scenario, the data preprocessing unit performs preprocessing such as denoising and formatting on them, and cooperates with the data synchronization unit to ensure the alignment of data timestamps and different data sources, so that the data acquisition module can collect accurate and complete data, thereby improving the usability of the data. Moreover, the processes of preprocessing and synchronization can enhance data consistency, reduce data errors, and thus improve the reliability of the system.

[0087] As Figure 3 shown, the data verification module includes:

[0088] A compensation value calculation unit, electrically connected to the data acquisition module, for performing data compensation processing on the initial operation data to obtain a data compensation value;

[0089] In a specific embodiment, for the processed physiological parameters included in the initial operation data, a non-linear regression model can be used to predict the internal clock drift trend and perform real-time compensation. For example, in VR training, due to long-term high-load operation, clock errors may occur. Therefore, the error can be controlled within the range of microseconds to sub-milliseconds through a compensation algorithm.

[0090] Specifically, for each data record included in the initial operation data D, assuming the original timestamp is t, in microseconds, and corresponding to hand movement parameters during acquisition, the following compensation calculation formula can be used to perform data compensation processing on the initial operation data:

[0091] d = α*(T - T0)+β*(T - T0) 2

[0092] where d is the data compensation value, T is the hand movement parameter; T0 is the hand movement reference parameter; α is the linear drift coefficient, and the range can be 0.1 to 1.0; β is the quadratic drift coefficient, and the range can be 0.01 to 0.1.

[0093] For the initial operation data D, a drift vector including all hand movement parameter records can be defined. The drift vector D1 is:

[0094] D1 = [d1,d2,…,d n

[0095] where each d i = α*(T i -T0)+β*(T i -T0) 2 , T i is the hand movement parameter of the i-th sample.

[0096] A data correction unit, electrically connected to the compensation value calculation unit, is configured to correct the original timestamp based on the data compensation value to obtain a calibrated timestamp; the original timestamp is the timestamp corresponding to the acquisition of the initial physiological parameters and the initial operation parameters;

[0097] In a specific embodiment, the original timestamp can be corrected using the data compensation value to obtain a calibrated timestamp, thereby eliminating clock drift.

[0098] Specifically, let the original timestamp be t and the data compensation value be d, then the calibrated timestamp can be defined as:

[0099] t′ = t - d

[0100] where t is the original timestamp, in microseconds, provided by the sensor; d is the data compensation value, in microseconds; and t' is the calibrated timestamp, in microseconds.

[0101] For the initial operation data D, a calibrated time vector including the calibrated timestamps corresponding to all hand movement parameters can be defined. The calibrated time vector T1 is:

[0102] T′ = [t′1, t′2, … t′ n

[0103] where each t′ i = t i - d i .

[0104] A first data integration unit, electrically connected to the data acquisition module and the data correction unit respectively, is configured to perform a first data integration process based on the calibrated timestamp, the initial physiological parameters, and the initial operation parameters to obtain calibrated operation data.

[0105] In a specific embodiment, the calibrated timestamp, the initial physiological parameters, and the initial operation parameters can be subjected to a first data integration process to form a corrected data packet, that is, calibrated operation data, which can be used for subsequent data fusion and analysis.

[0106] In the calibrated operation data, the calibrated timestamp, the initial physiological parameters, and the initial operation parameters corresponding to each record can be integrated into a vector form, and the calibrated operation data is represented in matrix form. Specifically, the calibrated operation data D sc is:

[0107]

[0108] where t′ i is the calibrated timestamp, T i is the hand movement parameter in the initial physiological parameters, and S i ​is the initial operation data, such as position parameters, operation trajectory parameters, and interaction parameters between members.

[0109] In the data verification module, the compensation value calculation unit can calculate the data error based on the hand movement parameters to obtain the data compensation value, and cooperate with the data correction unit to adjust the original timestamp to ensure the consistency of the time data. Through error compensation and data correction, the accuracy of the data is improved, and the timing integrity of the data can be guaranteed, making the subsequent data processing more stable and accurate.

[0110] Such as Figure 4 As shown, the data fusion module includes:

[0111] The first data fusion unit, electrically connected to the data verification module, is used to perform the first fusion process based on the channel weight data, the number of channels, and the calibration operation data to obtain the first fusion data set; the channel weight data and the number of channels are determined based on the channels during the transmission of the calibration operation data;

[0112] In a specific embodiment, the calibration operation data D sc can be uploaded to the distributed edge node, and a multi-channel redundant transmission path can be constructed by using low-latency caching and pre-fusion algorithms on the edge side to ensure that the calibration operation data D sc can still be transmitted to the edge node through multiple paths in the scenarios of network partitioning, jitter, or data packet loss. In addition, the edge node can also perform local time comparison, pre-fusion, and preliminary error elimination on the calibration operation data D sc to ensure the continuity of the data stream during the transmission process.

[0113] In a specific embodiment, before using the first data fusion unit to perform the first fusion process on the calibration operation data, the calibration operation data D sc can be redundantly transmitted by using multiple independent network channels to avoid data loss in the case of network partitioning or jitter.

[0114] Specifically, assume that the network transmission uses M independent channels, and there may be different delays and error rates in each channel. Each channel corresponds to the calibration operation data D sc denoted as , where i = 1, 2,..., M. The first fusion data set S r can be confirmed by combining the number of channels and the channel weight data and using the multi-channel weighted redundant fusion algorithm. The first fusion data set S

[0115]

[0116] Among them, w i is the weight of the i-th channel, that is, the channel weight data, satisfying In addition, wi It can be dynamically adjusted according to the real-time quality (such as latency, bit error rate) of each channel, and the initial value can be For example, when the number of channels is 3, the channel weight data corresponding to each channel is 0.33.

[0117] The second data fusion unit, electrically connected to the first data fusion unit, is configured to perform a second fusion process on the first fusion data set based on a data fusion formula to obtain a second fusion data set;

[0118] In a specific embodiment, the first fusion data sets S from each channel can be pre-fused at the edge computing node r to further reduce the data deviation caused by network latency.

[0119] Specifically, assume that each record in the first fusion data set S r has obtained multiple approximate data through redundant transmission, and the pre-fusion process is performed using the data averaging method within a local time window. The time window width can be defined as Δt, with the unit of microseconds, and then the records within the same window can be fused.

[0120] It can be considered that the first fusion data set S r includes multiple records. For the K records within the time window, the corresponding second fusion data D p is calculated as follows:

[0121]

[0122] where D j is the j-th record within the time window, and D j = [t j , E j , S j .

[0123] Furthermore, during the calculation process, the mean values of the calibration timestamp, the initial physiological parameters, and the initial operation parameters can be calculated respectively:

[0124] Average calibration timestamp

[0125] Average initial physiological parameters

[0126] Average initial operation parameters For the initial operation parameters, the mean value can be calculated separately for each dimension.

[0127] where T j is the hand movement parameter, H j is the eye movement parameter, P j is the skin electrical activity of the user, Sj Represents an operation data vector, such as [x, y, z] coordinates.

[0128] The second data integration unit, which is electrically connected to the second data fusion unit, is configured to perform second data integration processing based on the second fusion data set and the calibration operation data to obtain fused operation data.

[0129] In a specific embodiment, the second data integration unit can be used to compare and integrate the second fusion data D p with the calibration operation data D sc at the edge node to generate the finally output fused operation data, thereby ensuring data consistency and integrity. The fused operation data may include a fused timestamp, fused physiological parameters, and fused operation parameters.

[0130] Specifically, the output fused operation data S final can be defined as a weighted combination of the second fusion data D p and the calibration operation data D sc . Let the fusion weight coefficient be λ, and its value range is 0 to 1, then the fused operation data S final is:

[0131] S final = λD p +(1 - λ)D sc

[0132] where λ can take the value of 0.7, indicating that in the fused operation data, the proportion of the second fusion data is 70%, and the proportion of the calibration operation data is 30%.

[0133] Fusing each element respectively, we get:

[0134] Fused timestamp t final = λt p +(1 - λ)t;

[0135] Fused physiological parameter E final = λE p +(1 - λ)E;

[0136] Fused operation parameter S final = λS p +(1 - λ)S.

[0137] In the data fusion module, the first data fusion unit preliminarily fuses the data according to the channel weights and the number of channels, and the second data fusion unit further processes the preliminarily fused data by using a fusion algorithm. Then, the second data integration unit combines the calibration operation data, and finally obtains the fused operation data. Through multi-channel fusion, the stability and representativeness of the data can be improved. Moreover, through the data fusion algorithm, the deviation that may be brought by a single data source can be reduced, and the accuracy of system decision-making can be improved.

[0138] As Figure 5 shown, the data weighting module includes:

[0139] A reference time acquisition unit for acquiring a reference time value;

[0140] The construction of a global clock consensus module can be realized through the data weighting module. First, collect the time information of each edge node, calculate the globally unified time reference, and then introduce a dynamic weighting mechanism. According to the network status, latency, and historical error of each node, different correction weights are assigned to different data channels (such as VR high-frequency data and online interaction data) to achieve fine adjustment of cross-system time series. When a local anomaly (such as a short-term network partition) is detected, a backup correction channel is automatically enabled to ensure global clock consistency.

[0141] In a specific embodiment, first use the reference time acquisition unit to acquire the reference time value. Assume that the node timestamps obtained from N edge nodes are t1, t2, … t N , the reference time value can be calculated using the weighted average formula, and the reference time value T c is:

[0142]

[0143] where, w i represents the weight corresponding to the i-th edge node and satisfies the condition; t i is the node timestamp corresponding to the i-th edge node. w i can satisfy the condition and is calculated through the error index e i corresponding to each node.

[0144] Specifically, the weight w i of the edge node is:

[0145]

[0146] where, e i represents the time error estimation value of the i-th node, in microseconds, and the usual range can be selected from 0.5 to 10 microseconds.

[0147] A weighted processing unit, electrically connected to the data fusion unit, is configured to perform weighted correction on the calibration timestamp based on a reference time value to obtain a target timestamp;

[0148] In a specific embodiment, the weighted processing unit may be used to perform weighted correction on the calibration timestamps corresponding to each record by using the reference time value to obtain the target timestamp.

[0149] Specifically, for each data record, set its corresponding calibration timestamp as t local , and use the following dynamic weighted correction formula to calculate the target timestamp, where the target timestamp t final is:

[0150] t final = λT c +(1 - λ)t local

[0151] where the unit of the target timestamp is microseconds; T c is the reference time value; λ is the dynamic weighting coefficient, and its value range can be 0 to 1. Generally, when the network quality is high, the range of λ can be between 0.7 and 0.9, and when the network fluctuates greatly, the range of λ can be between 0.5 and 0.7. λ can be obtained by real-time monitoring of delay and error statistical data.

[0152] A third data integration unit, electrically connected to the weighted processing unit, is configured to perform third data integration processing on the target timestamp, the initial physiological parameters, and the initial operation parameters to obtain weighted operation data.

[0153] In a specific embodiment, perform third data integration processing on the target timestamp, the initial physiological parameters, and the initial operation parameters to obtain weighted operation data, and the weighted operation data can represent the data stream after high-precision clock correction for global unity.

[0154] Specifically, the weighted operation data can be expressed in vector form, and the weighted operation data D final is:

[0155] D final = [t final E S]

[0156] where E is the initial physiological parameter, including hand movement parameter T, eye movement parameter H, and the skin electrical activity of the user, and S represents the initial operation parameter, such as [x, y, z] coordinates.

[0157] In the data weighting module, the reference time acquisition unit is used to acquire the reference time value to correct the data time information, so that the weighting processing unit can adjust the data based on the reference time value to obtain more accurate time information. And through the third data integration unit, the physiological parameters and operation parameters are combined to form a more stable data set. Through time weighting and correction, the data is made to more conform to the actual operation time, and combined with physiological parameters, the data is made more accurate, adapted to different scenario requirements, and the scientific nature of the evaluation is improved.

[0158] The data evaluation module includes:

[0159] A feature extraction unit, electrically connected to the data weighting module, is used to extract features from the weighted operation data to obtain feature information;

[0160] In a specific embodiment, the data evaluation module can be used to perform real-time analysis on behaviors such as students' online discussions, experimental operations, and project collaborations. The pre-trained model and the lightweight convolutional neural network are respectively used to operate the data for analysis, and combined with the operation logs, quantitative team collaboration metrics such as interaction frequency, role division, task response time, and operation stability are realized. For different scenarios (such as laboratory practical operations and VR simulations), a differential evaluation model can also be set to output the team collaboration score and the behavior heat map.

[0161] Specifically, the feature extraction unit extracts features from the weighted operation data to extract the key features included therein for subsequent team collaboration scoring, interaction status, and operation stability evaluation.

[0162] In a specific embodiment, the weighted operation data D final includes the following features:

[0163] 1. Interaction frequency F, defined as the number of interaction records per unit time, and the calculation formula is:

[0164]

[0165] where, Δt is the window duration corresponding to the time window, with the unit of second; n int is the total number of interaction events within the time window Δt.

[0166] 2. Average response time R, defined as the average delay representing the operation response, and the calculation formula is:

[0167]

[0168] where, n is the number of records within the time window, and a i is the response time in the i-th record.

[0169] 3. Error rate E r, defined as the number of operation errors per unit time, and the calculation formula is:

[0170]

[0171] where n is the number of records within the time window, and b i is the number of errors corresponding to the i-th record.

[0172] In a specific embodiment, the feature information may include the interaction frequency F, the average response time R, and the error rate E r .

[0173] The operation evaluation unit is electrically connected to the feature extraction unit and is configured to calculate operation evaluation information based on the feature information and the evaluation function. The operation evaluation unit is further configured to perform anomaly detection based on the operation evaluation information to obtain an anomaly detection result.

[0174] In a specific embodiment, in addition, the operation evaluation information may include an operation evaluation score for characterizing the team collaboration situation.

[0175] Specifically, the evaluation function for calculating the operation evaluation score S team is:

[0176]

[0177] where w F , w R , w E are the weights corresponding to each index, satisfying w F +w R +w E =1. For example, w F can be 0.4, w R can be 0.3, w E can be 0.3.

[0178] F norm is the standardized value of the interaction frequency, and the calculation formula is:

[0179]

[0180] where F min and F max are the preset minimum and maximum interaction frequencies respectively. For example, F min =0.1 times / second, F max =1.0 times / second.

[0181] R norm is the standardized value of the response time, and the calculation formula is:

[0182]

[0183] Among them, R min and R max are respectively the preset minimum and maximum expected response times. For example, R min = 50 milliseconds, and R max = 200 milliseconds.

[0184] is the error rate normalization value, and the calculation formula is:

[0185]

[0186] Among them, The unit is error / record.

[0187] In a specific embodiment, the operation evaluation information may further include an interaction status report, and the interaction status report may include the following parts:

[0188] 1. Interaction activity, which can be directly reflected by the F value.

[0189] 2. Response delay status: It can be described by the R value and divided into "excellent", "good", and "to be improved".

[0190] 3. Error incidence rate: It can be represented by E r and the risk level is given.

[0191] 4. Comprehensive anomaly index A, and the calculation formula is:

[0192]

[0193] Among them, γ1, γ2, and γ3 are anomaly detection weights, and γ1 + γ2 + γ3 = 1; for example, γ1 and γ3 can take the value of 0.3, and γ2 can take the value of 0.4.

[0194] In a specific embodiment, the operation evaluation unit may also detect abnormal situations according to a preset threshold and obtain an anomaly detection result. The anomaly detection can be combined with the comprehensive anomaly index A and the preset threshold A th to detect abnormal situations. If A exceeds the preset threshold A th (for example, 0.6), it is determined to be in an abnormal state, an anomaly detection result is generated, and a warning is triggered.

[0195] In the data evaluation module, the feature extraction unit can analyze the weighted operation data, extract key feature information, and then, based on the feature information and the evaluation function, calculate the evaluation information through the operation evaluation unit, while detecting abnormal situations. Through feature extraction, the depth of data analysis is improved, and the accuracy of evaluation can be ensured. In addition, anomaly detection can timely identify abnormal user operations, thereby improving the real-time performance, accuracy, and comprehensiveness of system evaluation.

[0196] The data feedback module includes:

[0197] A data feedback unit, electrically connected to the data evaluation module, for generating real-time feedback information and adjustment instructions based on operation evaluation information and abnormal detection results.

[0198] In a specific embodiment, the operation stability of the user can be evaluated through the data evaluation module, and the relevant data can be integrated into real-time feedback information.

[0199] Specifically, the operation stability scoring data S stab can characterize the operation error and the fluctuation of the operation time. Suppose the standard deviation of the operation response time recorded within the time window is σ i and the mean value of the total error number is a Then the operation stability scoring data S is: stab That is:

[0200]

[0201] where δ1 and δ2 are adjustment constants. The value range of δ1 can be 0.01 - 0.05, with the unit of per millisecond, and the value range of δ2 can be 0.1 - 0.5.

[0202] Furthermore, through the data feedback unit, based on the operation evaluation score S team , the operation stability scoring data S stab and the comprehensive abnormal index A in the interaction status report, real-time feedback information and adjustment instructions are generated.

[0203] Specifically, first, a feedback feature vector Q is constructed and a comprehensive deviation correction factor C is defined.

[0204] The feedback feature vector Q is:

[0205]

[0206] The comprehensive deviation correction factor C is:

[0207] C = α1 * (1 - S team ) + α2 * (1 - S stab ) + α3 * A

[0208] where α1, α2, and α3 are weighting coefficients, and satisfy α1 + α2 + α3 = 1; the range of C is 0 - 1, and the larger C is, the greater the required correction force.

[0209] Suppose the preset deviation correction threshold is C th , then the adjustment instruction I c can be defined as:

[0210]

[0211] Meanwhile, the real-time feedback information, i.e., the real-time feedback report R f will include the values of each index and the comprehensive evaluation conclusion. For example, the report content is as follows: the teamwork score, i.e., the operation evaluation score, is 0.61, the operation stability, i.e., the operation stability score data, is 0.65, and the comprehensive anomaly index A is 0.37; Suggestion: No adjustment is required. Or, the report content is: the teamwork score, i.e., the operation evaluation score, is 0.79, the operation stability, i.e., the operation stability score data, is 0.70, and the comprehensive anomaly index A is 0.65; Suggestion: Adjust the parameters to reduce user operation errors.

[0212] The data feedback module can generate real-time feedback information and adjustment instructions based on the evaluation results and anomaly detection. Through real-time feedback, the interactivity of the training can be improved, enabling students and teachers to adjust operations in a timely manner; and through adjustment instructions, teamwork can be optimized and the teaching effect can be improved.

[0213] In another specific embodiment, the data feedback module may further include a data linkage unit. Before transmitting the data to the output module, the real-time feedback report R output f and the adjustment instruction I c can also be integrated with the necessary system metadata to form cross-system linkage data L.

[0214]

[0215] where M is a metadata vector, which may include a timestamp t link , a system status code s, and a version number v. Among them, t link is in microseconds; s is an integer used to represent the current system status, for example, 0 means normal, 1 means warning, 2 means failure), and; v is a string, that is, the metadata vector M is:

[0216] M = [t link s v]

[0217] For example, t link is obtained from the system clock, s is set according to the real-time monitoring results, and v is the current software version of the system, such as v1.2.3.

[0218] Figure 6 This is the second system architecture diagram of the intelligent interactive evaluation and teamwork management system for higher vocational colleges provided by the embodiments of the present invention; as Figure 6As shown, in another embodiment, the intelligent interactive evaluation and teamwork management system for higher vocational colleges further includes an output module, electrically connected to the data feedback module, for formatting the real-time feedback information to obtain target feedback information, in addition to the data acquisition module, data verification module, data fusion module, data weighting module, data evaluation module, and data feedback module.

[0219] In a specific embodiment, the system further includes an output module. The output module is used to process the real-time feedback information and obtain target feedback information, which can be represented in the form of a visual chart. The output module can transmit the cross-system linkage data L to each relevant system in real time through a standardized interface, such as a VR simulation system, a teaching management system, etc., so as to achieve information linkage and feedback correction.

[0220] Specifically, the output module can use the standard API interface to serialize the cross-system linkage data L into the JSON format to obtain target feedback information. The target feedback information can include the data transmission result, which is used to characterize the reliability of data transmission. The target feedback information R t is:

[0221]

[0222] wherein, N ack is the total number of data packets sent; N send is the number of data packets that have received confirmation responses; R t ranges from 0 to 1. If R t ≥0.95, the transmission is successful.

[0223] After the data transmission is successful, the operator and the system management platform can display the real-time feedback information, adjustment instructions, cross-system linkage data, and target feedback information. Among them, the information, instructions, data, etc. can be displayed in the form of data information or in the form of a visual chart, so that the evaluation results are more intuitive and convenient for students and teachers to consult and analyze.

[0224] It should be noted that: the above has described various embodiments of the present disclosure. The above description is exemplary and not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those of ordinary skill in the art in the corresponding technical field without departing from the scope and spirit of the described embodiments. The selection of the terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other ordinary technical personnel in the technical field to understand the disclosed embodiments.

Claims

1. An intelligent interactive assessment and teamwork management system for higher vocational colleges, characterized in that, The system includes: A data acquisition module, configured to obtain initial physiological parameters and initial operation parameters corresponding to a target training scenario, and perform data processing on the initial physiological parameters and the initial operation parameters to obtain initial operation data; A data verification module, configured to perform data verification and correction on the initial operation data to obtain calibrated operation data; A data fusion module, configured to perform data fusion processing on the calibrated operation data to obtain fused operation data; A data weighting module, configured to perform weighting processing based on the initial physiological parameters, the initial operation parameters, and the fused operation data to obtain weighted operation data; A data evaluation module, configured to extract feature information from the weighted operation data and generate operation evaluation information based on the feature information; A data feedback module, configured to generate real-time feedback information corresponding to the target training scenario by combining the operation evaluation information and the weighted operation data.

2. The intelligent interactive evaluation and teamwork management system for higher vocational colleges according to claim 1, characterized in that, The data acquisition module includes: A data acquisition unit, configured to obtain the initial physiological parameters and the initial operation parameters; A data preprocessing unit, electrically connected to the data acquisition unit, configured to perform data preprocessing on the initial operation parameters to obtain operation data to be synchronized; A data synchronization unit, electrically connected to the data acquisition unit and the data preprocessing unit respectively, configured to perform data alignment processing on the operation data to be synchronized and the initial physiological parameters to obtain the initial operation data.

3. The intelligent interactive evaluation and teamwork management system for higher vocational colleges according to claim 1, characterized in that, The data verification module includes: A compensation value calculation unit, electrically connected to the data acquisition module, configured to perform data compensation processing on the initial operation data to obtain a data compensation value; A data correction unit, electrically connected to the compensation value calculation unit, configured to correct the original timestamp based on the data compensation value to obtain a calibrated timestamp; the original timestamp is the timestamp corresponding to the acquisition of the initial physiological parameters and the initial operation parameters; A first data integration unit, electrically connected to the data acquisition module and the data correction unit respectively, configured to perform first data integration processing based on the calibrated timestamp, the initial physiological parameters, and the initial operation parameters to obtain calibrated operation data.

4. The intelligent interactive evaluation and teamwork management system for higher vocational colleges according to claim 1, characterized in that The data fusion module includes: A first data fusion unit, electrically connected to the data verification module, configured to perform first fusion processing based on channel weight data, the number of channels, and the calibrated operation data to obtain a first fusion data set; the channel weight data and the number of channels are determined based on the channels during the transmission of the calibrated operation data; A second data fusion unit, electrically connected to the first data fusion unit, configured to perform second fusion processing on the first fusion data set based on a data fusion formula to obtain a second fusion data set; A second data integration unit, electrically connected to the second data fusion unit, configured to perform second data integration processing based on the second fusion data set and the calibrated operation data to obtain the fused operation data.

5. The intelligent interactive evaluation and teamwork management system for higher vocational colleges according to claim 1, characterized in that The data weighting module includes: A weighting processing unit, electrically connected to the data fusion unit, for performing weighted correction on the calibration timestamp based on a reference time value to obtain a target timestamp; A third data integration unit, electrically connected to the weighting processing unit, for performing third data integration processing on the target timestamp, the initial physiological parameters, and the initial operation parameters to obtain the weighted operation data.

6. The intelligent interactive evaluation and teamwork management system for higher vocational colleges according to claim 5, characterized in that, The data weighting module further includes: A reference time acquisition unit for acquiring the reference time value.

7. The intelligent interactive evaluation and teamwork management system for higher vocational colleges according to claim 1, characterized in that The data evaluation module includes: A feature extraction unit, electrically connected to the data weighting module, for extracting features from the weighted operation data to obtain the feature information; An operation evaluation unit, electrically connected to the feature extraction unit, for calculating the operation evaluation information based on the feature information and an evaluation function.

8. The intelligent interactive evaluation and teamwork management system for higher vocational colleges according to claim 7, characterized in that, The operation evaluation unit is further configured to perform anomaly detection based on the operation evaluation information to obtain an anomaly detection result.

9. The intelligent interactive evaluation and teamwork management system for higher vocational colleges according to claim 8, wherein The data feedback module includes: A data feedback unit, electrically connected to the data evaluation module, for generating real-time feedback information and adjustment instructions based on the operation evaluation information and the anomaly detection result.

10. The intelligent interactive evaluation and team collaboration management system for higher vocational colleges according to claim 1, characterized in that, The system further includes: An output module, electrically connected to the data feedback module, for formatting the real-time feedback information to obtain target feedback information.

Images