36 results about "Distraction" patented technology

The invention provides a concentration training method and device based on visual tracking, and the method comprises the steps: collecting the real-time eye movement data of a user, including the staring point coordinate and the eye movement speed, and initializing the target trajectory of a training task; calculating a concentration deviation between the current gazing point and the target trajectory, and dynamically adjusting the target trajectory through nonlinear mapping based on the deviation to generate a dynamic trajectory; constructing a multi-feature fusion distraction scoring model based on the concentration deviation and the change trend of the concentration deviation in combination with the geometric features of the trajectory, and detecting and marking distraction events; when a distraction event is detected, self-adaptive visual correction stimulation is executed at the event position immediately, and a user is guided to return to a task; and after the training period is finished, dynamically adjusting the task difficulty coefficient of the next period according to the frequency and the average deviation of the distraction events in the period.

The invention discloses an attention monitoring method, device and equipment based on multi-modal sensing and a medium, and relates to the technical field of attention monitoring. The method comprises the following steps: collecting eye movement image data of eyeballs of a user; extracting fixation point stability features, eye movement track features, blink mode features and pupil dynamic features based on the eye movement image data; determining a concentration score of the user based on the fixation point stability feature, the blink mode feature, the pupil dynamic feature and the eye movement track feature; and if the concentration score is lower than a preset threshold value, sending reminding information to a user through the wearable device. The attention distraction behavior of the user in a continuous high attention demand scene can be accurately identified and prompted in time.

The invention discloses a multi-task learning-based driver driving-suitable credibility identification method and system, and relates to the technical field of multi-task learning, and the method comprises the steps: determining the multi-modal data of a driver based on the feature positions of a plurality of key face features, the corresponding feature forms and the real-time face image of the driver; the multi-modal data simultaneously contains the accurate head posture of the driver, the dynamic geometric information of the eyes and the mouth and the visual texture and expression details of fatigue, distraction or specific emotion on the face of the driver, and a preset credibility value is determined based on the previous driving event of the driver, a multi-task learning system and the current state of the driver; the corresponding driving early warning item is triggered based on the real-time comparison of the preset credibility value and the driving-suitable credibility value, so that the real-time performance and the accuracy of the driving early warning item are ensured.

The invention belongs to the technical field of wisdom education, and discloses a student classroom interest intelligent evaluation system and method based on multi-visual perception, and the system comprises a behavior detection module which employs a YOLOv11 model to recognize key behaviors such as side sitting, desk lying, standing and the like; the attention estimation module judges whether the student focuses on a blackboard or not by using technologies such as head posture estimation, and divides attention states into concentration, distraction and separation; the emotion recognition module evaluates the emotion titer and the awakening degree level of the student based on the facial expression; the identity matching module is used for matching the face image of each student with source data collected before class; the quantitative evaluation module converts the extracted related information into numerical scores, and a final interest score is generated after weighted summation and integration. According to the method, the behavior, attention and emotion characteristics are extracted from the visual data in a non-intrusive and non-contact mode, the classroom interest level of students is automatically evaluated, and valuable technical support is provided for intelligent classroom interest evaluation.

The invention belongs to the field of flight personnel state monitoring, and discloses a meta-consciousness ability training method and system based on a neural biofeedback technology. The system can obtain neural activity data directly related to the distraction state in a real and continuous task situation, hysteresis and unreliability caused by dependence on subjective reports or behavioral expressions are avoided, and the accuracy and objectivity of distraction monitoring are improved from the source. The decoding model is embedded into a closed-loop neural feedback training system, so that an acoustic feedback signal can be triggered in time when a distraction state occurs, a trainee is prompted to perceive attention deviation, and the self consciousness state is autonomously regulated and controlled without external guidance. The closed-loop feedback can strengthen a conditioned reflex mechanism paying attention to a regression task, and the self-monitoring and self-adjusting capability of meta-awareness is remarkably improved.

The invention discloses a holographic remote interactive teaching system, and relates to the technical field of teaching systems, and the system comprises an integrated teaching system which comprises a three-dimensional dynamic capturing module, a holographic imaging module, an intelligent interactive processing module and a low-delay communication module. The three-dimensional dynamic capture module is used for collecting three-dimensional holographic data of teachers and students in real time, and the three-dimensional holographic data comprises multi-angle depth images and skeleton joint point data. According to the invention, natural eye contact, body language capture and real-time feedback between teachers and students are realized, a dynamic holographic image with a real space depth is generated, the immersion and interactivity of teaching are effectively improved, the problems of eye contact deficiency and student attention distraction in traditional video teaching are solved, and remote teaching is closer to real classroom experience.

The invention discloses a training device for schizophrenia art therapy. The training device comprises a workbench, the workbench is integrated with a reel, a drawing board and a paper drawing and cutting mechanism, a rotary copying guide template mechanism is arranged at the bottom of a drawing area, and the drawing board is matched with an anti-shake pen. The device forms a closed-loop process of paper supply, creation and arrangement, simplifies operation steps, and adapts to the characteristics of distraction and weak coordination ability of a patient. The copying guide mechanism can flexibly switch patterns with different complexities to realize personalized training; the anti-shake pen can accurately counteract hand shake, smooth and accurate creation is guaranteed, and the contusion feeling of a patient is reduced. The whole device deeply adapts to the clinical requirements of the art therapy through process integration, individuation guidance and precise creation design, assists the patient to recover the cognitive function and adjust the emotion, and provides a professional and efficient auxiliary tool for the schizophrenia art therapy.

The invention relates to the technical field of video generation, discloses a digital human guide type marketing short video generation method and system, and aims to solve the problems of fixed speech speed, lack of dynamic adjustment and low matching degree of content and users in the prior art. The method comprises the following core steps: evaluating user interaction strength based on a user sliding speed and a reviewing rate; evaluating the content complexity based on the keyword density and the numerical information density; integrating the user interaction strength, the content complexity, the platform recommendation score and the real-time conversion rate to calculate the adaptation degree; based on the split-screen state, the continuous watching time and the environment noise level, evaluating the attention distraction degree of the user; and finally, dynamically regulating and controlling the explanation speed of the digital human to a target value according to the adaptation degree, the attention dispersion coefficient and the historical average playing speed multiplying power of the user. The corresponding system module is used for executing the process. According to the invention, real-time personalized adaptation of the explanation speed is realized, and the information transmission efficiency and the user watching experience are improved.

The invention provides a safe driving distraction threshold early warning method based on a multi-modal interaction behavior, and relates to the field of automobile safe driving, the method comprises the following steps: S101, obtaining driving behavior data, facial micro expression data and environment data in real time; s102, identifying distraction actions of the driving behavior data through a space-time convolutional neural network model according to the driving behavior data, and calculating a danger coefficient of the current distraction action; according to the facial micro-expression data, a current facial emotion is recognized through a micro-expression-semantic coupling network model, and an emotion coefficient is calculated; identifying current road conditions and weather conditions by adopting an environment sensing model according to the environment data, and calculating an environment coefficient; s103, calculating a distraction value score according to the danger coefficient, the emotion coefficient and the environment coefficient; step S104, setting a distraction threshold according to the recognized current distraction action, facial emotion and environmental condition; and S105, comparing the current distraction value score with a distraction threshold value, and if the current distraction value score is greater than the distraction threshold value, performing early warning.

The present device aims to create ideal conditions for performing human profiling, assessment and testing processes, in a controlled, simple, accurate, inclusive and distraction-free manner. In order to achieve this aim, the device offers a minimalist, dedicated interface, having a simplified physical keypad that can have various formats depending on the application. During the performance of the test, built-in or peripheral cameras and sensors can collect additional information relating to the attentional, cognitive, physiological and emotional state of the user. This data is processed by the device in order to generate information that can be combined with the other results to produce an even more in-depth assessment of the subject being tested. The entire assessment process can take place in online mode, allowing immediate synchronization with a server, or in offline mode, allowing subsequent synchronization with a server or the downloading of the data directly to a computer. In both cases, an administrative dashboard accessible via the device or via the web can be used to download or create new tests, update the existing tests, register users, view the results and manage the entire assessment process. Finally, the possibility of presenting the test stimuli by means of virtual reality goggles further increases the potential uses and versatility of the equipment.

Methods, apparatus, and systems are disclosed for estimating audience exposure based on engagement level. An example apparatus includes at least one memory, machine readable instructions, and processor circuitry to at least one of instantiate or execute the machine readable instructions to identify a user activity associated with a user during exposure of the user to media based on an output from at least one of a user device, a remote control device, an image sensor, or a motion sensor, classify the user activity as an attention-based activity or a distraction-based activity, assign a distraction factor or an attention factor to the user activity based on the classification, and determine an attention level for the user based on the distraction factor or the attention factor.

The invention belongs to the technical field of fan maintenance, and discloses a fan maintenance auxiliary method based on MR glasses, which is characterized in that sight, voice and posture interaction thresholds are calibrated in a data initialization stage, personnel do not need to frequently switch tools and MR equipment, and distraction is reduced; in the operation guiding stage, an intelligent tool and MR glasses are linked in real time, when torque deviation exceeds a corresponding personnel grade threshold value, an adjustment value is prompted through voice immediately, next-step guiding is frozen, when the heart rate exceeds 80-140 times per minute, operation steps are split, the prompting time is prolonged, the safety of high-altitude operation is guaranteed, and the problem that the tool is used improperly is solved; the MR glasses scan the fan structure through a camera, mark the modification time and material attributes of the non-standard component, and superpose the real-time environment factors of the fan SCADA system to generate a scene label, if the non-standard component is not identified for three times, the artificial auxiliary mark is triggered, and when the deviation between the identification result and the historical archive is greater than or equal to 30%, the window is popped up to prompt confirmation.

In a method and supporting system for intelligent buffering of large scale videos, a video presentation includes a plurality of sub-videos, each associated with a field of view. During presentation of the large scale video, sub-videos within a user's field of view are loaded and presented to the user, and sub-videos in proximate fields of view are loaded for potential presentation. On identifying a change in the user's field of view to one of the proximate fields of view, sub-videos are loaded for presentation within the new field of view. In a method and supporting system for seamless transitions in large scale videos, a video having a plurality of sub-videos is provided for presentation to a user, and distraction levels based on video content and user interactions are tracked. A transition point for the video is identified based on one or both distraction levels, and a sub-video is changed to a different sub-video at the transition point.

The present invention aims to create the ideal conditions for a user to consume and interact with digital content in a simple, effective and distraction-free manner. In order to achieve this aim, it provides the possibility of accessing the content by various means, with particular emphasis on physical media such as content discs or release discs. After accessing the content, the user experiences simplified navigation, free from distractions or interruptions. In addition to providing access to the content, the device has mechanisms to measure the user's level of attention and focus, as well as their stress and emotional state, while they are using the device. Some of these mechanisms are embedded and operate by means of an infrared camera mounted on the main device. Other mechanisms can be included by means of connecting peripherals such as an EEG, a heart rate sensor and a galvanic skin response sensor. The data resulting from these measurements are combined and used to provide feedback to the user and to personalise their content consumption experience. Finally, the user's focus and sense of immersion can be enhanced by means of using a pair of virtual reality glasses as a peripheral. These glasses may or may not have an integrated EEG and when connected to the device, provide new possibilities for viewing and interacting with the content.

The invention is suitable for the technical field of digital publication content auditing, and provides a digital publication content auditing system based on artificial intelligence, which comprises a feedback judgment module, a conflict analysis module, a focusing degree calculation module, a correction coefficient generation module and a display correction module, according to the method, the abnormal advertisement display condition can be automatically identified and corrected according to the characteristic that the attention of the hearing-impaired people is easily interfered when the hearing-impaired people watch the advertisement video, and before the advertisement video is put again, the display conditions such as the limb movement amplitude and the expression exaggeration amplitude of the promotion personnel in the video are quantitatively reduced according to the correction coefficient; therefore, the excessive exaggeration performance is weakened; according to the invention, troubles caused by exaggerated expressions and actions of promotion personnel in the advertisement video to hearing-impaired people can be effectively avoided, the problem that the attention of the hearing-impaired people is distracted when the hearing-impaired people watch advertisements is relieved, and the ability of the hearing-impaired people to acquire price and product key information is improved, so that the watching experience is improved, and the purchase conversion rate of the advertisement video in the hearing-impaired people is improved.

The invention discloses an AR (Augmented Reality) system cognitive security interaction method based on multi-modal large language model reasoning and bidirectional individuation, which utilizes a cross attention mechanism guided by an inertial measurement unit signal to explicitly model and eliminate electroencephalogram signal motion artifacts, and compared with the existing method of directly using electroencephalogram signals or simple filtering, the method has the advantages that the method is simple and convenient to implement, and the efficiency is high. The anti-interference capability of personalized attention perception is high, attention recognition is more accurate, the distraction moment of the user can be accurately captured, and the false alarm rate is reduced. Besides, personalized preference configuration information is generated through man-machine alignment and is embedded into the reasoning process of the multi-modal large language model, so that the subjective preference of the user to the risk is read, the problem of alarm fatigue is solved, and user trust is established. According to the method, a real agent closed loop is realized, and the method is a complete agent architecture with perception (physiological denoising)-cognition (LLM reasoning combined with preference)-action (self-adaptive interaction), and can adapt to physiological features and psychological preferences of different users.

The invention relates to the technical field of safety management, and particularly discloses a pre-class disclosure AI intelligent device. The system comprises a behavior acquisition module which extracts facial sight, limb postures and group interaction features by acquiring personnel video streams, and performs weighted mapping to obtain attention distraction indexes; the overlapping analysis module identifies a pre-class distraction person based on the attention distraction index, and judges and triggers an overlapping analysis signal in combination with environmental interference; the position optimization module constructs a position transfer model through a random forest algorithm, adjusts the position of a distraction person and verifies the feasibility; the pre-class evaluation module calculates distraction optimization coefficients before and after position adjustment and judges information transmission effectiveness; the pre-class optimization module optimizes the time period, duration and content order of the key period based on the personnel content mastering degree and the concentrated distraction time period. The equipment is beneficial for improving the transmission effectiveness of disclosure information before class, and extracting safety and operation guidance before class for engineering construction.

The application discloses a driving distraction state recognition method based on eye movement sequence space-time semantic feature analysis, and relates to the technical field of visual analysis, and comprises the following steps: S1, acquiring eye movement data of a to-be-identified subject during driving; S2, constructing a driving distraction recognition model based on eye movement sequence space-time semantic features; and S3, inputting the eye movement data of the to-be-identified subject into the driving distraction recognition model based on eye movement sequence space-time semantic features which is constructed, and obtaining a distraction detection result of the to-be-identified subject. The application designs a driving distraction recognition model based on eye movement sequence space-time semantic features, extracts time, space and semantic features in visual saccade paths, and combines the features to represent the eye movement mode of a driver, so that whether the driver is in a distraction state can be identified.

The invention provides a method for determining intimacy in a social network, and relates to the technical field of Internet, and the method comprises the steps: obtaining the number of associated users of a target creator from social network data, and converting the number of associated users into a relation score reflecting the influence and attention distraction degree of the target creator; based on the number of fans of the target creator and the number of common fans, determining a first network coefficient representing the connection strength of the target associated user in the fan network; determining a second network coefficient representing the influence of the target associated user in the concerned network based on the total concerned number and the concerned number of the target creator; correcting the relationship score by using the first network coefficient and the second network coefficient to determine a fan relationship score and an attention relationship score; and determining the intimacy based on the fan relationship score and the attention relationship score. By adopting the method for determining the intimacy in the social network, the accuracy of intimacy calculation is improved, and the complexity of data calculation is reduced.

The invention discloses a closed-loop electroencephalogram neural feedback system based on wearable glasses and a closed-loop feedback method of the closed-loop electroencephalogram neural feedback system. According to the system, multi-channel flexible dry electrodes are integrated on nose pads, eyebrow frames and ear retroauricular sites of a glasses frame, and electroencephalogram signals are collected in a non-inductive mode; the signals are processed in real time through edge processing modules integrated in the glasses legs, and cognitive states such as distraction, mood impulse or high-pressure stress are recognized by utilizing a lightweight neural network model; providing instant tactile feedback through a bone conduction vibrator according to an identification result and a preset sperm specifying mode; meanwhile, energy self-maintenance is achieved through thin-film solar cells on the surface of the mirror frame. According to the invention, electroencephalogram sensing, edge calculation and closed-loop intervention are deeply fused into daily glasses, so that the cognitive state regulation and control with ultralow delay and intelligent scene are realized, and the working efficiency and psychological toughness under high mental load are improved.

The application relates to the technical field of safety management, and specifically discloses an AI intelligent device for pre-shift briefing. The system comprises: a behavior collection module which extracts a face visual line, a body posture, a group interaction feature and a weighted mapping into an attention distraction index by collecting a personnel video stream; an overlapping analysis module which identifies pre-shift distracted personnel based on the attention distraction index, and judges a trigger overlapping analysis signal in combination with environmental interference; a position optimization module which constructs a position adjustment model through a random forest algorithm, adjusts the position of the distracted personnel and checks the feasibility; a pre-shift evaluation module which calculates a distraction optimization coefficient before and after position adjustment, and judges information transmission effectiveness; and a pre-shift optimization module which optimizes a period, a time length and a content sequence of a key period based on personnel content mastery and a concentrated distraction period. The device is favorable for improving pre-shift briefing information transmission effectiveness, and extracting pre-shift safety and operation guidance for engineering construction.

The application provides a concentration training method and device based on visual tracking, which comprises the following steps: collecting real-time eye movement data of a user, including a gaze point coordinate and an eye movement speed, and initializing a target trajectory of a training task; calculating a concentration deviation between a current gaze point and the target trajectory, dynamically adjusting the target trajectory through a nonlinear mapping based on the deviation, and generating a dynamic trajectory; based on the concentration deviation and its change trend, combining the geometric features of the trajectory, constructing a distraction score model with multi-feature fusion, and detecting and marking a distraction event; when the distraction event is detected, immediately performing adaptive visual correction stimulation at the event position to guide the user to return to the task; after the training period ends, dynamically adjusting the task difficulty coefficient of the next period according to the frequency and average deviation of the distraction event in the current period.

The invention discloses a digital network interactive teaching method and system, and relates to the technical field of digital network teaching, and the method comprises the steps: obtaining a video stream which is collected by a teaching client and contains the head of a student, and extracting a head motion track and pupil change information; performing correlation analysis on the head movement track and the pupil change information to form attention features reflecting a cognitive state; according to the historical change trend of the attention features and the current teaching progress, dynamically establishing an attention distraction identification reference; when attention distraction is determined based on the identification reference, generating an interaction question directly associated with the teaching content based on the teaching content being taught at present; according to the method, the attention characteristics are formed through correlation analysis of the head movement track and the pupil change information, the cooperative change rule of the head and eye movement is accurately captured, effective behaviors and the real attention distraction state in the learning process can be effectively distinguished, and the accuracy of attention judgment is guaranteed.

Embodiments are directed to aspects of the extended reality environments that are selected or otherwise modified to account for distracting stimuli. Similarly, one or more metrics that reflect, or are otherwise indicative of, a user's ability to focus on a current or upcoming activity may be used to adjust a user's interaction with the extended reality environment. The extended reality environment can generated by an extended reality system that includes a head-mounted display, a set of sensors and a processor configured to enter a focus mode that reduces distraction in an extended reality environment. While in the focus mode, the process or can receive imaging data of a physical environment around a user using the set of sensors and generate the extended reality environment that includes a reproduction of the first region of the physical environment where an identified object is replaced with the additional content.

The application discloses a learning emotion recognition method and device based on facial expressions and context situations. The method uses a visual language pre-training model CLIP to combine the facial expressions of students in video sequences with the context information of learning situations to achieve accurate emotion modeling. Specifically, the application first co-models the facial expressions and the context information in learning situations to significantly improve the ability to recognize the learning states of students (such as focused learning and distraction). Secondly, by using the powerful language and visual feature alignment capability of the CLIP pre-training model, the dependence on large-scale video training data is effectively reduced, and the generalization ability and practicability of the model are improved. The application provides a precise and feasible solution for learning emotion recognition, which is suitable for monitoring and analyzing the learning emotions of students in educational scenarios.

The application provides a method and device for guiding attention state, electronic equipment, medium and product. The method includes displaying target content in a target area of a display screen, obtaining eye movement data representing the relationship between the gaze position of a target object (such as a user) and the target area for displaying the target content (such as learning content), determining the attention state of the target object based on the eye movement data, and distinguishing between a focused state and a plurality of distraction states of different degrees. On this basis, when a certain distraction state (i.e., a target distraction state) is determined among the plurality of distraction states, the target focused guidance content corresponding to the target distraction state can be matched, so that the guidance intensity (or intervention intensity) is adapted to the degree of distraction, reducing the impact on learning continuity and the user's resistance psychology, thereby improving learning efficiency and learning experience.

This distraction characteristic ascertaining system includes: a property selection unit that selects the properties of an object to be superimposed on video; an object presentation unit that generates an object based on the selected properties and presents, to a user, video on which the object is superimposed; an attention level acquisition unit that acquires the attention level of the user viewing the video; and a model training unit that executes training of a distraction model on the basis of an attention level log including object presentation information and the attention level.

The invention discloses an anti-interference concentration training method based on distraction behavior recognition, and relates to the field of anti-interference concentration training. Electroencephalogram signals of a user are collected through an electroencephalogram head ring in advance, behavior data of a device end are synchronously obtained, and original data are preprocessed; presetting a trained convolutional neural network-based distraction behavior recognition model, inputting the preprocessed electroencephalogram features and behavior features, and outputting a distraction behavior type and a distraction degree; and according to the distraction identification result, adjusting interference parameters in the training scene in real time through an interference intensity adjustment strategy. The brain electricity physiological signals and the equipment behavior data are collected at the same time, key brain region features are enhanced through the space attention module of the distraction behavior recognition model, the feature attention module dynamically adjusts the weight of bimodal data, the real concentration state of a user can be more accurately captured, and the limitation of single-dimensional data is avoided.

In a method and supporting system for intelligent buffering of large scale videos, a video presentation includes a plurality of sub-videos, each associated with a field of view. During presentation of the large scale video, sub-videos within a user's field of view are loaded and presented to the user, and sub-videos in proximate fields of view are loaded for potential presentation. On identifying a change in the user's field of view to one of the proximate fields of view, sub-videos are loaded for presentation within the new field of view. In a method and supporting system for seamless transitions in large scale videos, a video having a plurality of sub-videos is provided for presentation to a user, and distraction levels based on video content and user interactions are tracked. A transition point for the video is identified based on one or both distraction levels, and a sub-video is changed to a different sub-video at the transition point.

Methods, apparatus, and systems are disclosed for estimating audience exposure based on engagement level. An example apparatus includes at least one memory, machine readable instructions, and processor circuitry to at least one of instantiate or execute the machine readable instructions to identify a user activity associated with a user during exposure of the user to media based on an output from at least one of a user device, a remote control device, an image sensor, or a motion sensor, classify the user activity as an attention-based activity or a distraction-based activity, assign a distraction factor or an attention factor to the user activity based on the classification, and determine an attention level for the user based on the distraction factor or the attention factor.