280 results about "Human behavior" patented technology

The invention belongs to the technical field of intelligent perception and mode recognition, and particularly relates to a human body behavior recognition method based on millimeter wave radar and multi-task learning. The method comprises the steps that millimeter wave radar point cloud data and RGB video streams are synchronously collected, and a five-dimensional point cloud scene is generated through three-dimensional analysis and dynamic target extraction; a hierarchical Point Transform network is constructed to extract radar space-time features, and human body key point features are generated by using visual auxiliary attitude estimation; radar and key point features are dynamically fused through a cross-modal attention mechanism, a multi-task joint optimization strategy is combined, behavior classification serves as a main task, attitude estimation serves as an auxiliary task, and a behavior recognition result is output. According to the method, through multi-task cooperation and cross-modal feature interaction, on the premise of ensuring privacy security, the accuracy and robustness of human behavior recognition in a complex scene are remarkably improved, and efficient and reliable technical support is provided for the fields of intelligent monitoring, human-computer interaction and the like.

The invention discloses a human abnormal behavior monitoring method based on a large-model multi-agent, which is executed by a modular multi-agent system deployed on a back-end server, obtains information through a monitoring camera, and comprises the following steps: obtaining a video stream from the monitoring camera by a sensing agent and extracting human body posture features; analyzing the key frame by a scene understanding agent by using a visual large model, and constructing a time sequence dynamic scene graph; the core reasoning agent evaluates the scene semantic conformity based on the pre-trained large model and performs abnormal preliminary judgment; performing fine-grained classification, interpretation generation and risk assessment on the abnormal behaviors; and the report and action agent generates an alarm and records event data. According to the invention, through multi-agent cooperative work and a large model technology, efficient and accurate monitoring of human abnormal behaviors is realized, and the intelligent level of the monitoring system and the abnormal behavior identification accuracy are improved.

The invention discloses a space-time decoupling human behavior recognition method, device and equipment based on a dynamic semantic guide mask. The method comprises the following steps: extracting human skeleton sequence data from an original video and performing data enhancement; based on a dynamic semantic guide mask mechanism, performing mask operation on the skeleton sequence after data enhancement in two dimensions of space and time; respectively sending the skeleton sequence data after mask operation into a query encoder and a momentum encoder, respectively obtaining spatial representation and time representation, constructing cross-domain contrast loss, and carrying out contrast learning training to obtain a human behavior recognition model; and inputting the to-be-recognized video into the human body behavior recognition model to obtain a prediction result of the human body behavior in the to-be-recognized video. According to the space-time decoupling human body behavior recognition method, device and equipment based on the dynamic semantic guide mask, the human body behavior recognition precision and the environmental adaptability are remarkably improved under the condition that manual labeling is not needed.

The invention relates to the technical field of computer vision, in particular to a human body behavior recognition method and system. According to the method, a multi-head space hypergraph convolution module is arranged before each time graph convolution of an ST-GCN model, and a human body behavior recognition model is constructed; the multi-head space hypergraph convolution module constructs a non-uniform hypergraph to represent the topological relation of the human skeleton through the maximum number, which can be contained by hyperedges, of each node, and generates the output of the module in combination with a physical adjacency matrix reflecting the relation of each joint; virtual connection is also added, virtual features which are the same as the input channel dimension and the time dimension of the multi-head space hypergraph convolution module are constructed, and the virtual features and modal data features are spliced along the joint dimension and then serve as module input again, so that global semantic information of real nodes is enriched, generalization information of human body behavior modes is supplemented, and the real-time performance of the multi-head space hypergraph convolution module is improved. And stage dense connection is introduced between different layers to smooth the change degree of the features, so that the human behavior recognition precision is improved.

The invention relates to the technical field of safety monitoring, and discloses a multi-source data fusion-based personnel behavior safety early warning system, which comprises a data acquisition module, a fusion decision module, a dynamic adjustment module, a cross validation and correction module, an accumulated score management module, an early warning comparison module, an early warning response module and an equipment linkage module, the data acquisition module acquires identity permission, dynamic position, environmental perception and video stream data in real time, and encrypts and transmits the data to the fusion decision module, the fusion decision module performs modeling by using an improved D-S evidence theory, identifies illegal behaviors and gives initial scores, the dynamic adjustment module performs weighting according to time and position coefficients to obtain dynamic scores, and the dynamic adjustment module performs decision making according to the dynamic scores. The cross validation module calculates correction scores such as conflict coefficients, the score accumulation module performs rolling accumulation according to 24 hours, attenuation and reset rules exist, the early warning comparison module marks three-level threshold values to determine risk levels, the early warning response module triggers corresponding strategies according to the levels, and the equipment linkage module controls hardware to realize closed-loop control so as to guarantee regional safety.

The invention provides a human behavior recognition method based on fusion of multi-modal data acquired by an unmanned aerial vehicle, and the method comprises the following steps: splicing a joint Tokens with a space CLS Tokens of the same frame after feature extraction is completed by using a space Transform, and obtaining a feature fusion module; performing structure coding on the joint point sequence based on a human anatomy structure, and constructing a human topological structure association module; the method comprises the following steps of: constructing a time sequence cross Transform module; the space Transform, the feature fusion module, the human body topological structure association module and the time sequence crossing Transform module are stacked to obtain a trunk feature extraction network; a 10-layer trunk feature extraction network is adopted to perform deep feature extraction on input early-stage fusion data and feature fusion data, and classification is performed by using a classification head; the features output by the backbone network are mapped to the dimensions with the same number as the behavior categories, a prediction score is output for each category, and a human body behavior recognition result is obtained according to the prediction scores. According to the method, the human body behavior in the multi-modal data acquired by the unmanned aerial vehicle can be effectively identified.

The invention provides a through-the-wall radar human body behavior recognition method and recognition system based on spatial-temporal characteristics, and the method comprises the steps: obtaining and processing through-the-wall radar human body behavior echo sampling signals, and obtaining a corresponding time-Doppler spectrogram as a sample set; and training a constructed TWRMama network by using the sample set, in which the network adopts a CA-Mama block as a core feature extraction module, can efficiently model and input a time sequence dynamic feature and a spatial dependency relationship of a time Doppler spectrogram, and effectively enhance the feature expression ability in a shielding scene, thereby realizing accurate recognition of human behaviors of the through-the-wall radar. Besides, information interaction between patches is introduced into a patch embedding module of the TWRMama network, so that the expression capability of the network can be further improved, and the calculation complexity of the network is effectively reduced.

The invention discloses a human body behavior prediction method and system, and the method comprises the steps: carrying out the skeleton point sequence extraction of a real-time behavior video image of a target person, and obtaining a joint point coordinate set and a skeleton motion sequence; determining a spatio-temporal feature sequence of the joint point coordinate set, and determining a skeleton motion sequence to perform spatio-temporal attention coding to obtain global spatio-temporal dynamic features; fusing the action probability distributions corresponding to the spatial-temporal feature sequence and the global spatial-temporal dynamic features to obtain short-time action probability distribution data; candidate action screening is carried out on the short-time action probability distribution data, and candidate action comprehensive features are obtained; performing feature coding on the historical action sequence of the target person to obtain a historical context vector, and splicing the historical context vector with the candidate action comprehensive features to obtain a fusion feature; and inputting the fusion features into a probability model for intention probability evaluation to obtain a behavior prediction result of the target person. According to the method, the accuracy of behavior prediction is improved.

The invention relates to a behavior recognition method and system based on adaptive sliding window multi-head self-attention, and the method comprises the steps: preprocessing a training set of a human behavior video data set, inputting the preprocessed training set into a neural network model for training, preprocessing a test set, and inputting the preprocessed test set into the trained neural network model for behavior detection, obtaining the detection accuracy of the neural network model; and inputting to-be-recognized human body behavior video data into the tested neural network model for behavior recognition. According to the method, the long-time dependency and global features in the video can be captured, so that the extracted features are more comprehensive, the problems that the receptive field of the convolutional neural network is limited and the long-time dependency relationship in the video is difficult to capture can be effectively solved, and the recognition accuracy of various behaviors is greatly improved.

This invention presents a computer-implemented method for answering polls and surveys using large language models (LLMs), a novel approach that leverages an LLM's ability to emulate a group of human responses for diverse data collection. The system involves training a single or multi-modal LLM on a comprehensive dataset comprising one or more categories of text, image, sound and other sensory input data, which can be continuously updated with current events and trends, to ensure accurate representation of human behaviors and opinions. Utilizing a user interface, the method includes receiving survey and poll questions, posing these questions to a unique instance of the trained LLM and receiving the answers, recording the question-answer sessions, and compiling the results for presentation. Additionally, the system prioritizes data privacy and integrates a feedback mechanism for continuous improvement, providing an efficient solution to answering surveys or polls in the digital age.

The invention provides a radar-based human skeleton estimation method, system and product, and the method comprises the steps: carrying out the target detection of collected radar echo data, and generating a target four-dimensional point cloud containing distance information, speed information and angle information based on a target detection result; dividing the target four-dimensional point cloud into a plurality of human body topology point cloud blocks based on the velocity direction similarity of each point in the target four-dimensional point cloud; and inputting the human body topology point cloud block into a human body skeleton estimation network for human body skeleton estimation to obtain a human body skeleton estimation result. According to the human skeleton estimation method provided by the invention, human topology priori can be constructed from sparse millimeter wave radar point clouds, point cloud block features sensed by a structure are extracted, the modeling capability of a model for the spatial relationship of key parts of a human body is enhanced, diversified and natural daily human behaviors in a non-inductive monitoring scene can be adapted, and the human skeleton estimation accuracy is improved. The human body skeleton estimation with higher generalization ability is realized, and the accuracy and robustness of human body posture prediction can be effectively improved.

The invention discloses an output matching method based on a smart humanization engine, and the method comprises the following steps: S1, defining personality features, and building the association configuration of the personality features and online platform user behaviors on an online platform; s2, acquiring user behavior data on the online platform in real time; s3, according to the association configuration established in the step S1, converting the user behavior data into a personality feature score of the user, and establishing a user portrait big data model according to the personality feature score; s4, for any user, on the basis of the user portrait big data model, carrying out AI model construction to form a simulated digital person based on a smart humanization engine, simulating behaviors of the simulated digital person, and collecting behavior data of the simulated digital person in different virtual environments; and S5, according to the behavior data, collected in the step S4, of the simulated digital human in different virtual environments, predicting the behavior trend and demand of the corresponding user in real life.

A security platform architecture is described herein. A user identity platform architecture which uses a multitude of biometric analytics to create an identity token unique to an individual human. This token is derived on biometric factors like human behaviors, motion analytics, human physical characteristics like facial patterns, voice recognition prints, usage of device patterns, user location actions and other human behaviors which can derive a token or be used as a dynamic password identifying the unique individual with high calculated confidence. Because of the dynamic nature and the many different factors, this method is extremely difficult to spoof or hack by malicious actors or malware software.

The invention provides a human skeleton behavior recognition method based on a multi-modal enhancement converter and a hypergraph structure. The method comprises the following steps: S1, acquiring original skeleton data representing human behavior recognition; preprocessing the skeleton data to obtain four skeleton modal data in total; s2, carrying out single-mode feature extraction on the four types of skeleton modal data, and then carrying out multi-mode feature fusion to form unified skeleton features; s3, performing feature refining and three-dimensional dynamic feature reinforcement on the skeleton features of the unified mode in time and space; and S4, the refined skeleton features are subjected to a global average pooling layer and a full connection layer to obtain a behavior identification prediction result, and the result is a discrete action classification label. According to the method, a lightweight multi-modal converter network and a double hypergraph topological structure are constructed to enhance the multi-modal skeleton data fusion performance and capture the cooperative motion relationship between joint groups, so that the recognition accuracy and recognition efficiency of double interaction behaviors are improved.

The application discloses a kind of spatio-temporal decoupling human behavior recognition method, device and equipment based on dynamic semantic guide mask, comprising: extracting human skeleton sequence data from original video and carrying out data enhancement;Based on dynamic semantic guide mask mechanism, the skeleton sequence after data enhancement is masked in operation in two dimensions of space and time;Skeleton sequence data after masking operation is sent into query encoder and momentum encoder respectively, spatial representation and time representation are obtained respectively, cross-domain contrast loss is constructed, contrast learning training is carried out to obtain human behavior recognition model;The video to be identified is input into human behavior recognition model, and the prediction result of human behavior in the video to be identified is obtained.The spatio-temporal decoupling human behavior recognition method, device and equipment based on dynamic semantic guide mask of the application significantly improve human behavior recognition precision and environmental adaptability without manual label.

The invention discloses an ecological protection area human behavior recognition method and device based on gait feature recognition. An annular first optical fiber detection layer is laid on the periphery of an isolation belt of a protection area; deploying a radial second optical fiber detection layer on the isolation strip towards the center of the isolation area; the three-frequency WiFi probe array is deployed in the isolation zone domain; the intrusion position identification module is used for detecting a vibration signal by using the first optical fiber detection layer, calculating an intrusion position coordinate through a time difference positioning formula, and activating a monitoring channel of a radial second optical fiber detection layer in a corresponding direction according to the position coordinate; the gait feature fusion extraction module is used for extracting multi-scale energy features and generating gait comprehensive features through the multi-scale energy features; and the identity judgment module is used for inputting the gait comprehensive features into a pre-trained classification model, and judging the identity of an intruder according to the gait comprehensive features, thereby realizing the construction of an ecological protection area protection technology system with intelligent perception, dynamic response, global linkage and low cost.

The invention relates to the technical field of people flow simulation analysis, and particularly provides a people flow simulation analysis method and system based on spatio-temporal behavior dynamics, and the method comprises the steps: obtaining urban multi-dimensional spatio-temporal heterogeneous data, and carrying out the standardization; constructing a dynamic coupling mechanism of crowd behaviors, spatial constraints and industrial function supply, and extracting travel decision rules and destination selection logic; by taking the mechanism as a constraint, constructing a space-time behavior dynamic model in combination with subject modeling, simulating group flow space-time evolution and outputting crowd flow characteristic parameters; and based on the parameters, predicting the people flow distribution and aggregation dissipation trend of the target scene, and performing visual display. According to the method, through combination of multi-factor dynamic coupling and subject modeling, simulation accuracy and scene adaptability are improved, a prediction result is visual, and scientific decision support can be provided for urban planning, traffic management, public safety guarantee and the like.

A method of maintaining fidelity of a bond between a person and an artificial intelligence agent bound to the person includes capturing data for behavioral modalities of a person, calculating a score for each behavioral modality, calculating a similarity score from the calculated scores, and comparing the similarity score against the threshold value. In response to determining the similarity score fails to satisfy the threshold value, the method substitutes a snapshot of a Baseline Persona Model of the person for the Baseline Persona Model. The Baseline Persona Model is a machine learning model that encodes the behavioral modality data of a person over time. The snapshot is a copy of the Baseline Persona Model at an instant in time. Subsequently data for the behavioral modalities of the person is captured over time. The Baseline Persona Model is retrained using a set of the subsequently captured data approved by the person.

The invention discloses a human behavior prediction method based on a double-flow space-time diagram convolutional network, and belongs to the technical field of computer vision and deep learning, and the method comprises the following steps: S1, obtaining a human skeleton data set; s2, preprocessing skeleton point data; s3, processing the preprocessed skeleton point data through a double-flow space-time diagram convolutional network; s4, constructing a multi-scale joint point spatial dependency relationship; s5, processing the output features of the first stream through frequency weighting and a channel feature importance attention mechanism, dynamically adjusting the feature weights of high-frequency and low-frequency channels, and generating enhanced spatial-temporal features; and S6, fusing the output features of the double-flow network, generating a final behavior prediction result, and realizing human body behavior prediction. According to the method, through a multi-space category modeling graph convolution module and a frequency weighting and channel feature importance attention mechanism, a multi-space category modeling double-flow space-time graph convolution network is further provided, and the accuracy of behavior prediction is remarkably improved.

The invention discloses a multi-modal feature fusion-based human body behavior recognition method and device, terminal equipment and a storage medium, and belongs to the field of computer vision, and the method comprises the steps: generating a key point feature sequence through recognizing human body key point features of a target person in each video frame of a target video; identifying dynamic change features of the human body key point features according to a time sequence, generating a time sequence feature matrix, constructing a spatial feature matrix and an optical flow feature matrix by identifying spatial features and optical flow features of each video frame in a target video, and fusing the time sequence feature matrix, the spatial feature matrix and the optical flow feature matrix to obtain a fusion feature matrix; and a fusion feature matrix is generated, so that the behavior recognition model pays attention to the action change of the target person and the spatial change of the environment when performing behavior recognition. Therefore, the defect that the current human body behavior identification method is difficult to accurately identify the human action behavior can be solved.

The invention provides a human body behavior real-time recognition system based on an FPGA and a millimeter wave radar. The technical problems that an existing human body behavior recognition system cannot achieve off-line recognition, is insufficient in real-time performance and is low in data transmission accuracy are solved. Comprising a millimeter wave radar and further comprises a radar signal preprocessing module and a neural network identification module which are electrically connected. The radar signal preprocessing module enables the FPGA to be directly connected and controls a data acquisition card in the millimeter-wave radar to acquire radar original echo data, extract a specific sampling point, compress each frame of chirp signal to obtain a one-dimensional vector, respectively perform windowing to obtain windowing data, and perform FFT to obtain frequency spectrum data after FFT; performing normalization and conversion to obtain a binarized distance time graph and a binarized speed time graph, and performing fusion to generate a feature graph; and the neural network identification module stores parameters obtained by feature map training into a neural network model, and deploys the neural network model to the FPGA. The method can be widely applied to the technical field of human behavior recognition.

The invention relates to the field of smart home and smart pension, and discloses a human behavior recognition method based on millimeter wave point cloud data, which comprises the following steps: S1, setting millimeter wave radar parameters, a detection range and a frequency sweeping bandwidth; s2, acquiring millimeter wave point cloud data of different behaviors of a human body, adding behavior tags, and making a standard data set; s3, preprocessing the collected original data; step S4, constructing a behavior recognition model with a self-attention mechanism based on a transformer architecture; s5, training the model, and continuously adjusting a frame extraction and data enhancement strategy; and S6, deploying the model, and performing real-time reasoning on the millimeter wave point cloud data to obtain a behavior recognition result. Based on the architecture design of a Transform self-attention mechanism, the limitation that a traditional algorithm depends on local neighborhood features is broken through, the long-distance spatial relation in the point cloud is captured through global modeling, the semantic understanding ability of falling is remarkably improved, and the innovation of the algorithm is achieved.

A methodology for auditing the visual diversity of unlabeled human face image datasets uses a set of core human interpretable dimensions derived from human similarity judgments. Given a face image, a model can output dimensional values aligned with the human mental representational space of faces, where values not only express the presence of a feature, but also its extent. Since the model can be learned entirely from human behavior, the learned dimensions are not biased toward features that are easier to verbalize or quantify.

The invention provides a human body behavior recognition method and device based on a hybrid neural network. The method comprises the following steps: acquiring multi-channel time sequence data; performing Z-score normalization processing on the phase signal, the Doppler frequency shift and the RSSI signal in the multi-channel time sequence data to obtain corresponding signal data; converting the signal data into high-dimensional vector embedding representation by adopting linear projection matrix multiplication; injecting the time sequence information into the high-dimensional vector embedding representation, and reserving the time sequence information through learnable position coding to obtain the high-dimensional vector embedding representation comprising the time sequence information; the high-dimensional vector embedded representation including the time sequence information is input into a pre-trained human body behavior recognition model to output a corresponding human body behavior recognition result, and the human body behavior recognition model comprises a VIT module and a multi-scale wavelet pool Transformer module; therefore, through combination of the ViT network architecture and the multi-scale wavelet pool Transform, global-local feature joint modeling is realized, so that the recognition accuracy is improved.

The invention provides a cross-individual human body behavior recognition method based on self-training and active inquiry, and the method comprises the steps: obtaining a source domain data set with a label and a target domain data set without a label; processing acceleration data in the source domain data set with the label and the target domain data set without the label; dividing the target domain data into a label-free training set and a test set in proportion; establishing a feature extractor based on a dual-channel convolutional network, and extracting features of time and space dimensions from the input two-dimensional acceleration data at the same time; a cross-individual adaptation algorithm based on a confidence threshold value, sparse query and label propagation is adopted, a model is trained on a non-label training set on a target domain, and the adaptation problem caused by cross-individual data distribution difference is relieved. According to the method, the behavior recognition accuracy of the model in a cross-individual scene can be improved, the development cost and the user burden are reduced, and a more intelligent and adaptive solution is provided for application of wearable equipment such as exoskeleton robots.

The invention relates to a power violation work detection method and device based on a dynamic time sequence hypergraph network, and the method comprises the steps: S1, obtaining n continuous frames of power operation videos, and extracting a power operation image; s2, according to the step S1, obtaining human body behavior postures through a human body posture detection algorithm, wherein the human body behavior postures comprise key points and confidence coefficients; s3, constructing a heterogeneous hypergraph model, and introducing hypergraph convolution and a self-attention mechanism; s4, processing through a time sequence three-dimensional hypergraph convolution module, and capturing a vertex dynamic interaction relationship; s5, constructing a dual-channel model, and optimizing feature learning by using a hypergraph auto-encoder and a graph convolutional network; and S6, inputting the power operation video into the trained violation operation model, and detecting violation behaviors in real time. According to the scheme, the dynamic time sequence hypergraph network is utilized to enhance the violation behavior recognition capability, and the method is suitable for real-time analysis of electric power operation videos.

The present application relates to the technical fields of computer vision and human behavior recognition, and discloses a kind of industrial standard operation step generation method and system based on human behavior sequence recognition;The present application, first, the continuous video of operation area is acquired, and video frame is time-synchronized and spatially aligned;Determine local image area with wrist position, identify the contact relationship and position change between hand, tool and workpiece;According to the continuous change of action state, action segment is divided, and invalid action is filtered out and continuous repeated action is combined according to workpiece state and process sequence before and after action;According to the time sequence of reserved action segment, tool category, action type and workpiece position are determined, and industrial standard operation step is generated;Thereby, subtle action misrecognition, step omission, repetition and sequence error are reduced, and the accuracy of standard operation step generation is improved.

The invention discloses a decision-level-oriented scene information inconsistency elimination system and a decision-level-oriented scene information inconsistency elimination method, and relates to the technical field of artificial intelligence. Comprising a human body behavior data acquisition module, a human body behavior data preprocessing module, a bidirectional long-short-term memory human body behavior recognition network module, an inconsistency detection module, an initial basic probability distribution mapping module, an evidence set conflict degree division module, a self-adaptive credibility evaluation module and a human body behavior information application module which are connected in sequence. The human body behavior data acquisition module comprises an inertial motion sensing unit and a physiological signal monitoring unit. The technical problem to be solved by the invention is to provide a decision-level-oriented scene information inconsistency elimination system and method, which are used for realizing effective fusion of conflict evidences, fully utilizing complementarity of multi-source information and improving reliability and accuracy of decisions in complex scenes.

The present invention discloses a human behavior recognition method based on consistent semi-supervised deep learning, which relates to the field of computer vision. The method comprises the following steps: obtaining a labeled video set X and an unlabeled video set U to establish a training data sample set; performing video data enhancement processing on the training data sample set; building an improved 3D-ResNet18 network, constructing a loss function, training the improved 3D-ResNet18 network based on the loss function using the training data sample set, and using the optimized improved 3D-ResNet18 network to recognize human behaviors in videos. The present invention utilizes the human behavior recognition method to solve the problem that existing human behavior recognition methods lack effective data enhancement methods and thus develop relatively slowly; and the problem that existing human behavior recognition methods do not explore the temporal correlation of actions in videos, resulting in low robustness of trained models.

1. The name of this design product: Feature Recognition Fall Protection Device (Wenda Guard). 2. Purpose of this design product: used to monitor human behavior in real time and send out an alarm signal in time when a person falls. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.