22 results about "E-assessment" patented technology

The invention provides an online examination system and method capable of adaptively adjusting cognitive pressure, the system comprises an examinee interaction terminal, a physiological signal acquisition device and a processing device, and the examinee interaction terminal presents examination content to examinees and receives interaction input of the examinees; the physiological signal acquisition equipment acquires multi-modal physiological signals of examinees in real time; the processing equipment obtains a cognitive pressure index representing the cognitive pressure level of the examinee in real time through a pressure evaluation model based on the multi-modal physiological signal of the examinee; dynamically generating a regulation and control instruction according to the cognitive pressure index and a preset self-adaptive rule; and adjusting examination parameters presented to the examinee and / or triggering pressure relief intervention measures based on the regulation and control instruction. According to the method, a closed-loop process including signal acquisition, pressure evaluation, decision regulation and control and intervention execution is constructed, so that the cognitive pressure of the examinee can be objectively quantified and adjusted in real time, personalized self-adaptive examination experience is realized, and the performance of the examinee is improved while the examination validity is ensured.

The application discloses a kind of mobile equipment online examination methods, comprising: the behavior information of triggering at least two events in first event, second event, third event;According to two behavior information, output warning information;Examination program triggers pause event, and examination program is switched to background suspension operation;Heartbeat packet is sent to server;According to whether success of heartbeat packet reception, determine the data submission state of examination program;The data indicated by the input operation of user is sent to server and is stored in local answer database with encryption;When current examination program state is submission failure, supplement in local answer database is identified;Login current examination program, and the data in local answer database is uploaded according to version number.The application not only realizes full coverage monitoring to online examination cheating behavior, but also improves recovery success rate in abnormal submission scene.The application also discloses a system, electronic equipment and storage medium for implementing the above method.

The invention discloses an operation management system suitable for a 9H gas turbine, which belongs to the technical field of direct application of power plant operation and comprises a network learning platform module, an intelligent defect registration module, a data updating and maintenance module, an online examination evaluation module, a live code management module, a defect flow monitoring module and a user authority control module. According to the invention, through visual monitoring, a three-level early warning mechanism and cross-professional cooperative processing, the defect processing timeliness and quality are ensured; a network learning platform is combined with a live code scanning technology to realize parameter query, interactive learning and historical defect tracing of subsystems such as a # 12 gas turbine fuel gas system, the skill acquisition efficiency of operators is improved, data security is guaranteed by authority hierarchical control and multi-factor authentication, real-time synchronization of technical documents is guaranteed by data version management and an intelligent verification function, and the technical efficiency is improved. And the misoperation risk is reduced.

The invention discloses an online examination behavior monitoring method and system based on privacy protection, and belongs to the technical field of online education, and the method comprises the steps: S10, obtaining related data of a target examinee, the related data comprising a head image of the target examinee and an image of an object associated with an online examination of the target examinee, and storing the head image of the target examinee and the image of the object associated with the online examination of the target examinee; the image comprises an image of the computer display screen, acquiring four corner points and a central axis of the computer display screen based on the image of the computer display screen, and generating a two-dimensional image about the head image, the four corner points and the central axis of the target examinee. According to the method, the posture abnormity and plagiarism behaviors of the examinee are accurately detected by combining real-time monitoring of the head image of the examinee and the image of the computer display screen, meanwhile, the accuracy and reliability of behavior recognition are effectively improved by utilizing multi-dimensional data analysis and scientific calculation, and while the privacy of the examinee is protected, the accuracy and reliability of behavior recognition are improved. And the fairness and the seriousness of the online examination are ensured.

This application relates to an automatic grading method for flowchart-based operation questions and an online examination system. The method includes: acquiring examinee answer data and question answer data; constructing a first matrix based on the examinee answer data and a second matrix based on the question answer data; comparing the first and second matrices, and determining the examinee's score based on the comparison result. This method enables automatic grading of flowchart-based operation questions, solving the problem in related technologies where automatic grading of flowchart-based operation questions is not possible, greatly improving grading efficiency and reducing labor costs.

The present application relates to program control system technical field, specifically for a kind of thing internet of things intelligent multimedia integrated education table control method and system, including the following steps: receiving from thing internet of things intelligent multimedia integrated education table original event, the original event is remote forced intervention instruction, online examination task and user autonomous learning request, each event identifier is matched with the preset event priority definition table.Processing logic in the present application, through the structured priority identification of original event, remote intervention, examination task, autonomous learning and other multi-source events are classified by relying on static priority mechanism, realize the structural ordering control between tasks, improve the distinguishability of multi-task scheduling.Introduce preemption judgment mechanism under the priority driving, in combination with task context saving and resource exclusive judgment, form the dynamic switching strategy of condition trigger, so that terminal running logic has the traceability and preemption flexibility.

A method includes receiving, by an electronic communications system, an electronic assessment of a user, wherein the electronic communications system includes memory and a processor. The method includes receiving, by the electronic communications system, historical electronic information. The method includes analyzing by the electronic communications system the electronic assessment based on the historical information. The method includes determining, by the electronic system, a learning disability of the user.

Disclosed herein are systems and methods for proctoring online examinations by determining a gaze of a user. The method includes: performing a calibration process to calibrate a field of view of a user taking an online examination on a computer; after the calibration process is completed, obtaining a gaze origin and a gaze vector of the user using a prepared neural network to obtain facial key points of the user and determining, by a webcam or camera, the gaze of the user in three-dimensional (3D) coordinates to determine whether the gaze vector of the user is within a defined boundary relative to the gaze origin; and based on a determination that the gaze vector of the user is outside the defined boundary for a period of time, transmitting a message that the gaze of the user is outside of the defined boundary.

Provided is a test system, a test method, and a computer-readable storage medium. The test system is capable of implementing an online test while preventing fraudulent behavior. In a test management server (20) connected to a test taker terminal (50) via a network (1), a test question data transmission unit (24), an answer data reception unit (25), a doffing state data reception unit (26) that receives doffing state data detected by a doffing detection device (66) of a non-transmissive head-mounted display (60) worn by a test taker and transmitted from the test taker terminal (50) via the network (1), and a fraudulent behavior determination unit (32) that determines whether the doffing state is appropriate with respect to the test question category of a given test question using the doffing state data of the question presentation period and the doffing state data of the answer period that are received, thereby constituting a test system (10).

Disclosed herein are systems and methods for a machine-learning based method for proctoring online examinations. In one aspect, an exemplary method includes monitoring a user taking an online examination. The method also includes detecting at least one suspicious cheating event from the user from a captured video stream or time-series telemetry data. The method further includes, in response to detecting a plurality of suspicious cheating events from the user, analyzing the detected suspicious cheating events using a trained AI proctoring model. The trained AI proctoring model is configured to: recognize a cheating pattern based on the detected plurality of suspicious cheating events, classify the cheating events based on the detected cheating pattern, and calculate a cheating risk score based on the recognized cheating patterns. The method further includes notifying a proctor of suspicious cheating by the user based on the calculated cheating risk score exceeding a predetermined threshold.

The invention discloses a computer vision-based teaching and training online examination automatic paper marking method, and the core scheme of the method comprises the steps: completing the preprocessing of examination paper images uploaded by multiple terminals / formats through three-channel shadow removal, HSV shadow detection, perspective correction and region normalization; yOLOv5 of an optimized anchor frame is adopted to recognize objective questions, subjective questions including texts and formulas are recognized through a SwinTransform + CRNN-CTC + special feature network, and dynamic scoring is achieved in combination with GNN problem solving logic analysis and Siamese network handwriting verification; and finally, generating a learning condition report, and synchronously executing original data destruction and desensitization storage to guarantee data security. According to the method, the processing time of a single test paper is less than or equal to 0.6 second, the system throughput is greater than or equal to 2000 pieces per hour, the objective question recognition accuracy is greater than or equal to 99.5%, the subjective question text and formula recognition accuracy is greater than or equal to 98% and 97% respectively, the method adapts to various teaching and training scenes such as K12 education and occupational qualification certification, the efficiency, precision, safety and scene adaptability of online examination paper marking are remarkably improved, and the method is suitable for popularization and application. And the efficiency, the precision and the compliance of online paper marking are remarkably improved.

The invention discloses an online examination system, and relates to the technical field of online examination systems. The intelligent question bank generation module is used for automatically generating a question bank by utilizing an intelligent algorithm according to knowledge points, difficulty coefficients and question type information; meanwhile, according to historical answering conditions of the examinees, difficulty and types of questions in the question bank are dynamically adjusted so as to adapt to requirements of different examinees; the intelligent invigilation module is used for monitoring behaviors of examinees in real time through a computer vision technology and automatically identifying and recording suspected cheating behaviors; meanwhile, the natural language processing technology is utilized to analyze the voice of the examinee in real time, and whether the cheating suspicion exists or not is judged. Through the machine learning algorithm, cheating behaviors can be effectively identified and prevented, the fairness of the examination is ensured, and in addition, the scoring accuracy and the reliability of the system are further improved through the application of the auto-encoder and the integrated learning technology.

Aspects of the present disclosure include a method for verifying live user presence in anonline session, comprising obtaining at least one video stream of a user captured during at least one previous presentation of at least one user interface (UI) on a display, obtaining input events representing previous user interactions with the UI, generating a behavioral digital fingerprint profile based on the video stream and the input events, initiating an online exam during the online session by providing, for presentation on the display, at least one additional UI, receiving at least one additional video stream of the user during the exam, receiving additional input events representing user interactions with the additional UI, determining exam-specific behavioral features based on the additional video stream and the additional input events, and verifying whether the user is taking the exam based on at least one of the features or the profile.

The invention relates to the technical field of online examination supervision, and discloses an examination authentication method and system based on face recognition, and the method comprises the steps: collecting the behavior of an examinee and the initial information of an environment, generating a preliminary identity risk clue through processing, obtaining a facial image of the examinee, and carrying out the recognition of the initial identity risk clue. According to the risk clues, performing multi-stage identity verification processing on the face image data, generating an identity confirmation signal, obtaining behavior image data of the examinee in the examination process, synchronously inputting the identity confirmation signal and the behavior image data into a behavior analysis process, performing multi-dimensional verification of a behavior state, generating a behavior abnormal state signal, and outputting the behavior abnormal state signal to the examinee. According to the method, the identity verification intensity is dynamically regulated and controlled through risk clues, the identity state is deeply integrated into behavior analysis, and the overall recognition accuracy and real-time performance of the illegal behaviors of the examination are improved.

The embodiment of the invention belongs to the technical field of artificial intelligence, and relates to a pickup detection method and related equipment based on synthetic lips, and the method comprises the steps: carrying out the lip sequence extraction processing of original video data according to a CNN face detector, and obtaining a lip feature sequence; performing synthetic lip sequence generation processing on the original audio data according to a pre-trained lip generation model to obtain a synthetic lip feature sequence; calculating the difference between the lip feature sequence and the synthesized lip feature sequence in the low-dimensional embedding space to obtain a difference feature sequence; performing action segmentation processing on the difference feature sequence according to a multi-scale time convolution network to obtain an action probability distribution sequence with the same length as the input time step; and performing pickup recognition processing on the action probability distribution sequence according to the classifier to obtain a pickup detection result. The method can be used for carrying out related video processing in a financial science and technology business system, and can effectively detect pickup behaviors in scenes such as online examinations, remote interviews, video conferences and the like.

The invention discloses an anti-cheating monitoring method for an online examination system, and relates to the technical field of examination cheating prevention, audios and videos of an examination room are synchronously collected through a multi-view pickup camera array, and sound source coordinates are positioned through audio noise reduction, human voice screening, time delay inequality and a loudness attenuation rule; the method comprises the following steps: mapping a cheating area to a multi-view video pixel area through space coordinate conversion, unifying the multi-view video pixel area to a main view coordinate system through perspective transformation to realize audio and video cross-modal association, and respectively designing sub-models for audio, face and action features to carry out independent cheating suspicion screening. Three types of feature weights are dynamically distributed through a multi-head attention mechanism to fuse a comprehensive cheating probability, and collective cheating and invigilation cooperative cheating are identified in combination with time sequence correlation analysis; and the cheating judgment result and the audio and video evidence are encrypted and uploaded to the alliance chain for evidence storage, and a non-tampering evidence chain is generated and pushed for graded early warning. According to the method, the cheating identification accuracy and scene adaptability are effectively improved, and technical guarantee is provided for online examination fairness.

This invention discloses an online education system and method based on dynamic constraint verification and a multimodal anti-cheating mechanism. A dynamic learning hour constraint rule engine is introduced into the dynamic learning hour constraint and course recommendation module to complete user course training. In the examination control module, a homogeneous heterogeneous recombination algorithm is used to generate examination papers, while a multimodal behavior circuit breaker mechanism is combined to address cheating and violations in online examinations. Multi-level buffering is used to batch store examination paper data into the database, and a state machine compensation mechanism ensures the validity of examination payments. This invention improves the training efficiency of continuing education, solves the problems of fairness and lack of process monitoring in online examinations, effectively solves the database congestion problem and data loss problem in payment callbacks under the scenario of thousands of concurrent examinations, and significantly improves the robustness of the system.

The invention discloses an online examination real-time anti-cheating method, and the method comprises the steps: responding to an examination starting instruction, and collecting a video stream of an examinee in an examination process; calling a preset visual perception model to detect each frame of picture in the video stream, and if it is determined that the examinee has an abnormal behavior, triggering abnormal early warning; and displaying the abnormal early warning on an examinee interface, and uploading the abnormal early warning to an invigilation background. Therefore, the examination video stream is automatically collected, the preset visual perception model is utilized to detect abnormal behaviors (such as person changing, head turning, mobile phone using and the like) in real time, early warning is displayed at the examinee end in real time, and the abnormal behaviors are synchronously uploaded to the invigilation background, so that automatic identification, real-time intervention and evidence retention of cheating behaviors are realized under the condition of no on-site invigilation, and the examination efficiency is improved. And the fairness and authenticity of the online examination are effectively ensured.

The invention relates to the technical field of examination cheating identification, in particular to a method, a system and equipment for identifying photographing cheating in an online examination and a medium. According to the method, firstly, fuzzy mask processing is carried out on questions and answer contents in an examination interface, and examinees can read the questions only by removing a mask area through mouse hovering or sliding operation; meanwhile, the system records a mouse track and a mask revealing sequence in real time, and original behavior data are obtained; time characteristics such as reading duration, operation duration and static duration are calculated based on the data, and standardized answering speed and operation efficiency are calculated in combination with the word number of the question; and finally, analyzing the features through a pre-trained behavior model, and judging an AI cheating risk level. By forcing the examinee to perform interactive operation on the physical display layer and identifying the abnormality of the operation mode on the behavior analysis layer, dual detection on the physical display layer and the time behavior layer is formed, and the examinee can be effectively prevented from performing intelligent cheating by using an external AI tool.

This application discloses a comprehensive online learning management method, apparatus, electronic device, and storage medium. The method determines the course category for online learning in response to a first operation request from a user, and allocates the corresponding course content to the user's terminal for online learning. In response to a second operation request from the user to take an online exam of the course content, the method allocates the corresponding exam content to the user's terminal for online exams. Simultaneously, it acquires the user's online learning information and exam information, and evaluates the user's online learning based on these information to determine the learning effectiveness. This achieves unified management and quantification of the effectiveness of multiple course types, integrating various course contents, supporting online learning and exams, and effectively evaluating learning outcomes.