89 results about "Visual behavior" patented technology

The invention relates to the technical field of optical elements, and discloses a fog display point diffusion optical system and a preparation method thereof, and the preparation method comprises the steps: obtaining user visual parameters, and building a visual behavior probability density model through kernel density estimation; designing the front surface of the lens based on the model, and generating an asymmetric defocus system coupled with a gazing habit; the rear surface of the lens is designed, and the distribution density of a fog display point diffusion unit is cooperatively modulated by the front surface defocusing amount, the fixation probability and the pupil diameter; and finally integrating front and rear surface design to form an optical lens body. According to the method, the asymmetric defocus field on the front surface and the fog display point diffusion field on the rear surface are subjected to collaborative design, and the defocus intensity and the contrast modulation intensity are accurately applied to the effective retina area of the user through the visual behavior probability density model; the technical problem that a traditional out-of-focus lens is fixed in signal and cannot adapt to individual staring habits and physiological parameter changes is solved.

The invention provides a dynamic data traceability method and system oriented to network security, and relates to the technical field of network security and data governance crossing, and the method comprises the steps: carrying out the real-time visual monitoring of a user interaction interface of a data transaction platform, and capturing the visual behavior information related to data calling; extracting feature parameters based on the visual behavior information to obtain a visual feature data set, and performing structured conversion on the visual feature data set to obtain a structured call log record containing visual behavior associated information; based on the structured call log record, extracting a time sequence, a frequency and a spatial distribution feature of a call behavior as basic indexes; a plurality of feature sampling states are dynamically selected in a monitoring time window, and a dynamic feature evaluation set is constructed based on the feature sampling states. According to the invention, the accuracy and controllability of network security protection in a data transaction scene can be improved.

The invention belongs to the field of advertisement analysis, and provides an advertisement putting effect evaluation and analysis system and method based on data analysis, and the method comprises the steps: constructing a cognitive state vector of a user based on multi-source behavior data before and after the contact between the user and an advertisement; modeling is conducted on user cognitive state vector changes caused by advertisement putting, cognitive intervention vectors of the advertisements are generated, and the cognitive intervention vectors represent the variable quantity of the cognitive states of the users after the users make contact with the advertisements; based on the language feedback, the visual behavior and the emotion track of the user, evaluating the consistency between the user behavior response and the cognitive intervention vector direction, and outputting a multi-modal behavior consistency score; tracking a behavior path of the user from advertisement click to final conversion, forming a conversion chain feature, and identifying a path length, a path node type and a path response time delay; and fusing the cognitive intervention vector, the multi-modal behavior consistency score and the conversion chain feature, and calculating a cognitive effect comprehensive score of advertisement putting for putting effect evaluation.

The invention discloses an inpatient falling early warning and intervention method based on environmental perception, and the method comprises the steps: continuously obtaining the video frames of a patient through a camera, and extracting the coordinates and confidence of seventeen key points through a pre-training deep learning posture estimation model; respectively processing the time sequence and the space-time diagram by using a hierarchical time sequence convolutional network branch and a graph neural network branch, and generating a visual behavior feature vector; in the same risk assessment period, bidirectional cross-modal attention fusion is carried out on the physiological feature vector and the visual feature vector collected by the wearable device, and a multi-modal fusion feature vector is output; then combining historical state features and static archive features in a hospital information system, carrying out unified modeling through a Transform encoder, and mapping to fall risk probability distribution; and when the risk is judged to be high, an intervention instruction is immediately issued to an intelligent sickbed or ward falling prevention execution mechanism through an Internet of Things protocol, and a perception-decision-intervention closed loop is completed.

The present invention discloses a method for early warning of ICU patient self-extubation behavior based on RGB video monitoring, which belongs to the field of computer vision behavior recognition. It includes constructing an ICU patient self-extubation behavior dataset, obtaining a patient self-extubation early warning classification model based on a neural network and based on optical flow behavior features in an ICU scenario based on the dataset, obtaining a video image texture feature classification result by the patient self-extubation early warning classification model in an ICU scenario based on a neural network, and obtaining a patient self-extubation optical flow behavior feature classification result by the patient self-extubation early warning classification model in an ICU scenario based on optical flow behavior features; the above two classification results are fused and used as input to build a dual-stream ICU scenario patient self-extubation early warning model, thereby realizing ICU patient self-extubation early warning work based on RGB monitoring video. The present invention solves the problem of incomplete feature extraction from a single-stream structure, and has the advantages of high real-time performance, high accuracy, full automation and contactlessness.

The embodiment of the invention provides a form generation method, device and system based on AI enhancement and a storage medium, and relates to the technical field of form generation. The method comprises the steps of generating form structure metadata according to a natural language processing technology, a reinforcement learning algorithm and / or a type security verification rule; according to the form structure metadata, the equipment sensor data and / or the user visual behavior data, the rendering priority of each field is determined; and generating a target form according to the rendering priority and the equipment parameters. By generating the form structure metadata which is reasonable in structure and conforms to the type safety specification, the automation degree and reliability of form design are improved. By fusing form structure metadata, device sensor data and user visual behavior data, a rendering strategy can reflect device characteristics and user attention distribution. The target form is generated by combining the rendering priority with the equipment parameters, so that the form layout is adaptively matched with the terminal equipment, and the loading performance and the interaction experience of the form are improved.

The invention relates to an asymmetric scattering myopia control lens based on human eye visual behaviors, which is applied to the technical field of eye vision optics, and has the design core that an asymmetric visual behavior mode shown by human eyes in an actual visual task is deeply integrated into the optical design of the lens. Therefore, an asymmetric optical structure with scattering intensity distribution highly matched with individual visual habits is constructed. According to the lens, scattering characteristics can be accurately configured in a specific area of the lens according to a preset human eye visual behavior data model, especially in the lower half part of the lens, namely a visual field area corresponding to near-distance tasks such as near-distance reading, writing or electronic equipment use of a wearer; the scattering intensity is higher than that of the upper half part (corresponding to a far task view field area), so that the myopia control efficiency is remarkably improved, and meanwhile, the visual comfort and definition of a wearer are effectively considered.

The invention discloses an intelligent diopter training system and method based on a multi-modal physiological feedback and reinforcement learning algorithm. The intelligent diopter training system comprises a multi-modal physiological data acquisition module, a central processing PC, a user terminal and a cloud data platform. Visual behavior data, ciliary muscle state data and autonomic nerve reaction data of a user are collected in real time through a multi-modal physiological data collection module, multi-modal physiological data fusion and feature extraction are carried out, and a refraction state evaluation model is used for calculating a comprehensive score of a refraction state grade, visual fatigue and adjustment sensitivity of the current user. A personalized training parameter set of the next training period is dynamically decided and generated based on a reinforcement learning algorithm, and the user terminal presents visual training stimulation according to the current personalized training parameter set. The cloud data platform stores the data and generates a visual training effect trend chart, a diopter change prediction report and personalized training suggestions to complete training scheme personalization, training means intellectualization and feedback evaluation comprehensiveness.

The invention provides an employee emotion index evaluation method and device based on multi-modal data. The method comprises the following steps: acquiring multi-modal related data of an employee; the related data comprises voice data of the employees, text data in an enterprise communication tool, video data captured by visual behaviors and physiological signals of the employees; carrying out feature extraction on the related data and carrying out cross-modal alignment to obtain multi-modal technical features; calculating a data quality coefficient and a scene correlation coefficient of each mode so as to calculate a final dynamic weight of each mode; fusing the multi-modal technical features based on the final dynamic weight of each modal, and performing analysis to obtain a comprehensive emotion index of the employee; the comprehensive emotional index comprises emotional tendency, emotional intensity and a pressure index. According to the method and the device, the comprehensive emotion index of the employee is obtained by comprehensively analyzing the data of the multiple modes, so that the defects that the current emotion evaluation of the employee is not comprehensive enough and low in accuracy are overcome.

The embodiment of the invention provides a mechanical arm control system and method, and relates to the technical field of robots, the system comprises an execution process control subsystem, at least one mechanical arm behavior control subsystem and at least one visual behavior control subsystem, and the subsystems run in the same equipment. A mechanical arm and a visual device which are connected to the subsystems are deployed in the same working environment, and the execution process control subsystem is used for sequentially sending trigger instructions of control instructions to the target control subsystem according to the trigger sequence of the control instructions recorded by the execution process of a task; the mechanical arm behavior control subsystem is used for responding to the received triggering instruction and controlling the mechanical arm to execute the action indicated by the control instruction corresponding to the triggering instruction; and the visual behavior control subsystem is used for responding to the received trigger instruction and controlling the target visual equipment to execute the action indicated by the control instruction corresponding to the trigger instruction. Communication resources consumed in the mechanical arm control process can be reduced.

The invention provides a'vision + behavior 'information transmission method, which is characterized in that interactive nodes on a data chain are regarded as intelligent agents, a machine observes behaviors of other machines through a photoelectric sensor and receives and accepts information transmitted by the other machines, and data chain information flow is established on a'vision + behavior' information transmission mode. According to the invention, the interaction mode of the data link is innovated, the serious dependence of the data link on radio frequency communication is reduced, and the novel consensus capability of electromagnetic-wave-free communication of the data link is realized. The data chain works in a spectral domain comprising visible light and invisible light, is not decoy and interfered by electromagnetism, and can face strong electromagnetic interference or transmit information under complete rejection. The problem that use of the data chain is limited in a denial environment is innovatively solved, thoughts are expanded for the data chain to seek electromagnetic breakthrough, and the concept category of the data chain is developed.

The invention relates to the technical field of multi-point defocusing, in particular to an optical stable photochromic multi-point defocusing myopia control lens prescription generation method, which comprises the following steps of: based on eyes of a wearer, scanning cornea by using a non-contact optical device, extracting iris and pupil characteristics, monitoring an adjustment reaction, and performing three-dimensional reconstruction and multi-direction light path tracking analysis to obtain a myopia control lens prescription. And the distribution configuration of the annular belt is optimized, and the overlapping area is adjusted by combining the photochromic requirement, so that the fusion function partition structure is formed. Through collection of multi-source visual parameters and combination of spatial modeling and focusing path analysis, cut-through association of individual visual behaviors and structural attributes in lens customization is realized, functional requirements of different areas and photochromic response are dynamically fused through hierarchical adjustment of the spatial structure of an intervention area, and the visual performance of the lens is improved. And the material and microstructure data are synchronously output to a manufacturing link, so that the collaborative matching capability of the visual area partition is enhanced, and the requirements of a wearer on visual comfort and optical reaction are met.

The invention discloses a visual function detection method and system based on a 3D visual imaging technology, and the method comprises the steps: obtaining three-dimensional visual imaging data, carrying out the modeling and rendering of the illumination, texture and geometric structure in a visual environment, and constructing a virtual scene model which is highly similar to a real scene; acquiring eyeball movement characteristics and pupil change data of the user, analyzing visual characteristics of the user according to the data, and adaptively designing a personalized visual stimulation mode matched with the visual characteristics; and processing captured eyeball image data by using a deep learning algorithm, extracting features of the eyeball image through a convolutional neural network, and modeling the eyeball motion trajectory by using a long-short-term memory network, thereby realizing recognition and prediction of the eyeball motion mode. According to the method, the visual behaviors of the user are accurately captured and analyzed through multi-dimensional data fusion and intelligent algorithm analysis, and an effective means is provided for timely discovering potential visual function abnormalities.

The invention provides an intelligent campus security abnormal behavior identification method and system based on machine vision, and belongs to the technical field of campus security protection, and the method comprises the steps: adjusting a sensitivity parameter and a confidence threshold value of a preset visual behavior identification model based on campus schedule context information; inputting the video data of the monitoring area into the visual behavior recognition model to obtain an abnormal behavior recognition result and confidence; judging whether the confidence is smaller than a confidence threshold and whether the abnormal behavior recognition result is a high-risk behavior; if any condition is met, auxiliary data are acquired, and auxiliary judgment information is generated; inputting the abnormal behavior recognition result, the confidence coefficient and the auxiliary judgment information into a preset decision model, and generating a target recognition result and a danger level; if any condition is not met, determining a danger level by querying a preset behavior type danger level mapping table, and taking an abnormal behavior recognition result as a target recognition result; and determining a corresponding target early warning strategy based on the danger level and the campus schedule context information. According to the invention, the accuracy and response efficiency of safety early warning can be improved.

The invention discloses a large yellow croaker feeding behavior monitoring method and system based on target detection, and the method comprises the steps: carrying out the feature extraction of a large yellow croaker feeding video collected in real time, obtaining a visual behavior feature, and carrying out the feature extraction of a large yellow croaker acoustic signal collected in real time, and obtaining an acoustic behavior feature; performing time alignment on the visual behavior features and the acoustic behavior features through a preset cross-modal phase synchronization network to obtain a first feature pair, and performing semantic alignment on the first feature pair through a preset attention mechanism to obtain a second feature pair; performing feature fusion on the second feature pair to obtain a multi-modal feature, and outputting an ingestion behavior recognition result according to the multi-modal feature through a preset first ingestion behavior recognition model; and when the ingestion behavior result belongs to the abnormal ingestion behavior category, performing ingestion behavior abnormal early warning according to a preset grading early warning mechanism. The accuracy of large yellow croaker feeding behavior monitoring can be improved.

The invention relates to the technical field of artificial intelligence, and discloses a digital human driving method based on artificial intelligence, comprising the following steps: step 1, acquiring a voice signal, a facial electromyographic signal, a pupil size signal and a hand motion signal of a student through a wearable device, the wearable device comprising a helmet built-in sensor and a hand motion capture device; step 2, converting the voice signal in the step 1 into a fundamental frequency feature vector, converting the facial electromyographic signal into a 28-dimensional muscle activation degree vector, converting the pupil size signal into a diameter change rate scalar, and converting the hand motion signal into a six-degree-of-freedom pose matrix; according to the method, the multi-mode behavior recognition engine is adopted to fuse micro expression analysis, voice stress detection and skeleton motion capture technologies, the technical effect of recognizing the tiny abnormal reaction of the student in real time is achieved, and compared with a visual behavior recognition scheme based on a preset script in the prior art, the defects that deviation correction response is delayed and the safety knowledge memory effect is poor are overcome.

The present invention discloses a behavior tree-based unmanned vehicle action modeling and control method. The method constructs an unmanned vehicle action model according to a visual behavior tree. When the unmanned vehicle action model is used for simulation, when a target enters the sensor detection range, a target detection node transmits brief intelligence. A target identification node identifies the target model and payload to obtain intelligence information. A target threat analysis node analyzes the threat level of the target based on the identification results of the target identification node and provides treatment recommendations. A target tracking node is used to implement mobile tracking or non-mobile tracking based on environmental conditions, concealment capabilities, and target detection capabilities. When mobile tracking is implemented, the target tracking node controls the speed and direction of the unmanned vehicle to achieve target tracking. A cluster collaborative control node is used to achieve collaborative control between the individual unmanned vehicle entities in the unmanned vehicle cluster. The present invention implements the application of behavior trees in an unmanned vehicle simulation system.

The invention provides a building environment interaction analysis method and device based on virtual-real space synchronous mapping and multi-modal perception, and the method comprises the steps: carrying out the preprocessing of a target region panoramic image set, and obtaining a static target region panoramic image; mapping the panoramic image of the static target area to a double-sphere coordinate system to obtain virtual scene space mapping; obtaining a thermodynamic distribution diagram according to the user eye movement data and the virtual scene space; inputting the panoramic image of the static target area into the trained feature recognition model to obtain all elements contained in the thermodynamic distribution diagram; and generating a visual behavior analysis report according to the staring duration time, the staring frequency and the spatial weight matrix of each element in the thermal distribution diagram in combination with the staring duration time, the staring frequency and the spatial weight matrix of each element.

The invention discloses a classroom behavior detection model and method based on parallel state space model and self-attention, and belongs to the technical field of intelligent education. A convolution unit driven by a TeLU activation function is designed, and the problem of subtle behavior feature weakening is solved through nonlinear mapping of a hyperbolic tangent index linear unit. A mixed feature fusion unit module is constructed, and attitude transformation and scene change are adapted through multi-branch structure integration space and channel reconstruction convolution and dynamic feature transformation. A VCAF module is designed, features are decomposed into three types of sub-features capable of being independently processed, and through long-time timing sequence modeling of Mamba and aggregation of a convolution addition self-attention mechanism, behavior semantic confusion with highly similar visual performance is solved, redundancy of long-time static features is removed, and details of short-time dynamic features are reserved. An efficient and reliable behavior detection scheme is provided for classroom scene multi-target behavior recognition, and technical support is provided for intelligent classroom real-time behavior monitoring and teaching quality evaluation.

The invention relates to the technical field of member identity recognition and service recommendation, and discloses a multi-mode member identity recognition and service recommendation system based on a large model. According to the system, visual, behavior and text data of members are acquired through a multi-modal data acquisition module, initial identity feature vectors are extracted by a member identity recognition engine, and prototype matching and feature enhancement are performed by means of a multi-modal prototype memory bank; the incremental interest distillation module dynamically corrects interest characterization based on member follow-up interaction behaviors, and the service recommendation generation module generates a personalized service recommendation list according to refined interest characterization. According to the invention, high-precision and stable recommendation under a new member cold start scene is realized, and the system self-evolution capability is realized.

The invention discloses a real-time detection and intelligent guiding method for an insurance double-recording process and related equipment, and relates to the field of image extraction and semantic analysis. The method comprises the following steps: acquiring a real-time audio stream and a real-time video stream in an insurance double-recording process, determining a current business process node and loading a corresponding multi-modal detection strategy; the strategy defines visual and speech semantic features to be extracted and associated time thresholds. The method comprises the following steps: respectively acquiring audio and video features, and judging whether the audio and video features fall into the same time interval defined by an association time threshold in real time; if yes, judging that time sequence relevance exists and generating a compliance result; and if not, generating first guide prompt information according to the feature missing type. According to the method and the device, the logical association between the visual behaviors and the voice semantics is constructed on the microscopic time slice, so that the problem of audio-visual asynchronous missing detection caused by lack of time sequence collaboration due to discrete verification of audio-visual characteristics in related technologies is solved, and then real-time accurate verification of the consistency of the double-recording intention and the behaviors is realized.

The invention discloses a game testing method and system based on virtual reality. The method comprises the following steps: determining an optimal layout of a plurality of virtual cameras through an adaptive visual angle prediction algorithm and generating a panoramic test view; constructing a multi-dimensional operation data structure to record test operation at high frequency and realize compression storage; collecting performance data, and generating a visual performance distribution thermodynamic diagram through spatial interpolation; natural gesture interaction and multi-user collaborative labeling are realized based on hand feature recognition; and deploying a plurality of AI models to automatically detect vision, behavior and time sequence anomalies. The system comprises six modules including a VR environment construction module, an operation record analysis module, a performance visualization module, a collaborative interaction module, an intelligent detection module and a data storage module which work cooperatively through a standardized interface. A traditional plane game test is converted into an immersive VR test environment, the technical problems that the view field is limited, the operation record is not accurate, the performance analysis is not visual and the cooperation efficiency is low are solved, and an innovative technical means is provided for guaranteeing the game quality.

The invention discloses a driver target attention method, system and device, a medium and a product, and relates to the field of target detection, and the method comprises the steps: constructing a driver target attention prediction model; the driver target attention prediction model comprises a target recognition model, a driving event classification model and an attention prediction model; the attention prediction model comprises an environment model fusing multi-layer visual memory and a target-level visual attention prediction model; obtaining visual behavior data and driving data of a driver in real time; and inputting the driver visual behavior data and the driving data into the driver target attention prediction model to obtain a visual attention prediction target. According to the method, the adaptive capacity of the driver visual target attention prediction model can be improved, the accuracy and robustness of model prediction are improved, the prediction result better fits the visual search mechanism of the driver, and the practicability of the driver visual target attention prediction model is improved.

The present invention relates to a multi-robot linkage service control method driven by tourist behavior recognition, including: a first robot acquires a video image sequence of a target tourist, recognizes its visual behavior sequence and determines the service behavior state; when the target tourist meets a preset visual continuation trigger condition, visual continuation information is generated; the visual continuation information includes the visual appearance features, image position, target spatial position, moving direction, visual behavior sequence and service behavior state of the target tourist, and the target spatial position is obtained by coordinate mapping of the image position; the visual continuation information is sent to a second robot, and the second robot determines the corresponding target tourist in the video image it acquires based on this, and continues to recognize the visual behavior sequence and service behavior state of the target tourist; a multi-robot linkage service control instruction is generated according to the service behavior state after continuous recognition, and the robots participating in the linkage are controlled to execute service actions.

The present application provides a data recovery method, apparatus, electronic device, and storage medium. The target data type to which the target audio-visual behavior data of the audio-visual application requested to be recovered by the target user belongs is obtained (the target audio-visual behavior data is historical audio-visual behavior data that is not currently stored in the database and has been deleted from the database). According to the target data type, the target audio-visual behavior data can be searched from a blockchain system for storing operation data of the audio-visual application (the operation data includes first operation data representing the audio-visual behavior data of the audio-visual application). Based on this, not only can the queried target audio-visual behavior data be stored in the database, but also the queried target audio-visual behavior data can be returned to the audio-visual application for the target user to view, realizing the recovery of the audio-visual behavior data that has been deleted from the database.

The invention discloses a post-disaster damaged electric power facility intelligent identification method based on visual decision feedback optimization, which comprises the following steps: firstly, constructing a supervision fine tuning data set, and constructing an image-text interactive reasoning process including whole image analysis, local magnification observation and type judgment by marking a damaged electric power facility image (such as power transmission tower collapse); the multi-modal large model is guided to learn multi-round reasoning logic of an observation-judgment-amplification-confirmation mode. Secondly, supervising and fine-tuning the large model by using the data set, so that the large model has multi-modal fusion understanding and step-by-step reasoning capabilities to identify all damaged electric power facility types in the image; and a combined reward function combining recognition correctness, a visual operation strategy utilization rate and a redundant operation penalty term is further constructed, and a reinforcement learning mechanism based on strategy gradient is introduced to optimize a model visual behavior strategy, so that the electric power facility damaged after the disaster can be accurately recognized. According to the method, the reasoning efficiency of the multi-mode large model is improved, and the post-disaster inspection task is assisted.

The invention relates to a small animal visual stimulation eye movement analysis system based on visual movement reaction behavior judgment, and belongs to the technical field of animal visual behaviors. According to the system, a head fixing frame is adjusted to be aligned with eyes according to the body type of a small animal, and a visual stimulation generation module matches stimulation types based on a preset scheme and adjusts parameters to generate stimulation signals; the reaction acquisition module is used for acquiring double-eye dynamic images in parallel through a synchronous triggering technology to generate an eye movement signal data set, and acquiring tremor, displacement and electromyographic signals through a sensor to generate a body reaction data set; the data processing module preprocesses the eye movement signals and the body reaction data, calculates eye movement parameters and associates the eye movement parameters with the body reaction signals to establish an association relation model; and the function judgment display module outputs a difference analysis report through the association relationship model, performs visual display on the data, and supports multi-dimensional comparison presentation. And the visual function experiment of the small animal is changed from experience to standardization and precision.

The invention relates to the technical field of intention decoding and man-machine interaction, in particular to a smartwatch-assisted hybrid intention decoding and man-machine interaction method, which comprises the following steps of: acquiring interaction characteristic data acquired by a smartwatch sensor and electroencephalogram signal data acquired by an electroencephalogram signal acquisition device; based on the interaction feature data, executing coarse-grained action recognition; based on the electroencephalogram signal data, executing fine-grained intention analysis; generating a mixed intention decoding result according to the coarse-grained action recognition result and the fine-grained intention analysis result; according to the method, the action data collected by the intelligent watch sensor and the electroencephalogram data obtained by the special electroencephalogram signal collecting device are utilized at the same time, and organic combination of multi-modal information is achieved. The fusion gives full play to the advantages of different modal data, the action data provides visual behavior information, and the electroencephalogram data can capture deeper intention information.

This invention relates to the field of data processing, and more particularly to a control method and system for constructing a visual behavior simulation model. The method includes: acquiring real-time business event streams, performing protocol decoding and field parsing to obtain structured behavior data; constructing a behavior dependency graph structure based on the structured behavior data and determining edge weights; extracting the current behavior path based on the behavior dependency graph structure; evaluating the path legality and fit of the current behavior path based on the edge weights to obtain an average path fit; and judging the legality of the current behavior path based on the average path fit, correcting and optimizing invalid current behavior paths to obtain an optimized current behavior path, thus achieving process control. This solves the problem that traditional simulation model construction methods lack automated structure recognition and process rationality judgment mechanisms when facing complex business scenarios.