1528 results about "Stream data" patented technology

The invention relates to the technical field of camera linkage alarm, and discloses a camera linkage alarm method and system for intelligent environment monitoring, and the method comprises the steps: synchronously collecting the video stream data of a plurality of cameras and the multi-parameter monitoring data of an environment sensor; executing multi-path feature analysis and cross-modal feature fusion to obtain environment-vision joint features; environment scene self-adaptive classification is executed, and environment-vision joint features are analyzed through an anomaly judgment model to obtain an abnormal event judgment result; executing multi-camera collaborative verification and vision-environment data association analysis to obtain multi-dimensional abnormal event description information; and selecting a multi-camera linkage response strategy and coordinating the plurality of cameras to carry out three-dimensional monitoring on the abnormal area to obtain a linkage response execution result, so that a false alarm mode can be identified and an abnormal judgment rule can be dynamically adjusted, continuous optimization of the performance of the plurality of cameras is realized, and the false alarm rate and the missing report rate of the plurality of cameras in long-term operation are reduced.

The present invention relates to an integrated dispatch decision-making system and method for a hub supporting multi-modal transportation coordination, and a device. The system comprises: a multi-modal hub passenger flow data fusion and analysis module, which is used for arranging and classifying collected multi-modal hub passenger flow data, performing preprocessing, performing conversion and mapping to obtain normalized passenger flow data, and finally extracting a data fusion feature, and using a normalized transport passenger flow model to perform multi-dimensional data fusion and analysis computation; a hub transportation coordination decision-making module, which is used for performing transport capacity and volume assessment on the basis of the fusion and analysis of the multi-modal passenger flow data, and using an optimal decision-making model to compute an optimal strategy result; and a hub coordination dispatch and command application module, which is used for providing an intelligent command assistance function to a rail transit dispatch and command personnel on the basis of information access of hub-line-network, and the normalized transport passenger flow model. Compared with the prior art, the present invention has the advantages of improving the connectivity and coordinated dispatch of multi-modal transportation in a complex hub scenario, etc.

The invention provides a tunnel construction monitoring analysis method and system based on AI video monitoring, and relates to the technical field of artificial intelligence. A tunnel construction original video stream data set is acquired through a multi-view video acquisition device, and a spatio-temporal feature sequence is generated through spatio-temporal feature fusion processing; the spatiotemporal feature unit comprises a pixel region movement track, a personnel wearing identifier and a construction equipment contour feature, then extracting dynamic features of the spatiotemporal feature sequence to obtain a dynamic spatiotemporal feature set, and executing construction personnel statistical processing based on the dynamic spatiotemporal feature set; generating a hole entering personnel quantity statistical result, a personnel distribution statistical result of each construction part and a personnel identity matching result, performing work efficiency comparative analysis according to the personnel statistical result and a preset construction progress plan, and generating a construction progress deviation index and resource allocation optimization strategy; and when the progress deviation index exceeds the first threshold value, early warning is triggered, and a strategy is output to the management terminal, so that effective monitoring and management of tunnel construction are realized.

The invention relates to the technical field of data security management, and discloses a blockchain-based forestry data security management system and method, and the system comprises a data collection unit which is used for comprehensively obtaining a multi-dimensional information flow of forest ecology and resource states; the data processing unit is used for carrying out deep cleaning, standardized regulation and feature value extraction on the originally collected mass heterogeneous data; the block chain storage unit is used for constructing a permanent, tamper-proof and distributed secure storage infrastructure platform of the forestry core data; a verification unit; the safety control unit is used for constructing a covering data transmission, storage and access full-chain depth defense system structure model; a user interface unit; an auditing unit; and a network communication unit. The method is reasonable in design, and the intelligent analysis module is used for processing to form a forest interannual growth trend prediction function distribution map state visual output result set.

The invention provides a graphene super-capacitor capacity energy-saving control method based on an intelligent algorithm, and the method comprises the steps: obtaining the harmonic content data of a power grid, carrying out the spectrum analysis of the harmonic content through a Fourier transform algorithm, and obtaining the change trend of the harmonic content; acquiring historical capacitor bank impedance characteristic data and a corresponding harmonic content change trend, and calculating impedance matching degrees of the graphene super capacitor under different load conditions; according to the impedance matching degree of the graphene super capacitor, generating a capacitor bank switching sequence by adopting a dynamic programming algorithm, and determining a target switching sequence of the graphene super capacitor; switching of the graphene super capacitor according to the target switching sequence is executed through an edge calculation unit, the access state of the graphene super capacitor is adjusted in real time, and harmonic wave changes of a power grid are dynamically matched; the method comprises the following steps: acquiring transient current data of a system, and decomposing the transient current data by adopting a wavelet transform algorithm to obtain a frequency component of transient current;

The invention discloses an intelligent emergency and management and control method for a stadium, and belongs to the technical field of stadium safety management and control. According to the method, video stream data are collected through a monitoring camera array, and coverage areas of all cameras in the array have 15%-20% of overlapping areas; inputting the data into a pre-trained people density identification model to generate a real-time people flow distribution thermodynamic diagram; the retention index of each partition is calculated, and an emergency evacuation mode is activated in combination with a preset safety threshold value; in the emergency mode, the infrared sensor group monitors the instantaneous pedestrian flow speed, and an optimal evacuation path is generated by a dynamic path planning algorithm; the path is converted into a control instruction to drive an electromagnetic access control gate, emergency lighting and an electronic guide identifier, feedback data triggers a path re-calculation mechanism, and a two-dimensional code scanning device counts the number of evacuated people so as to start manual re-checking. Real-time situation awareness, dynamic risk assessment and intelligent evacuation guidance of the stadium are achieved, emergency response and evacuation efficiency is effectively improved, and crowd safety is guaranteed.

The invention discloses an AI-based medical and health care integrated data management method and system and a storage medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the data preprocessing and data standardization of collected multi-source medical and health care data, and obtaining a standardized medical data set; performing classification and semantic annotation on the data of the standardized medical data set by using a preset medical ontology, and constructing a structured medical knowledge graph; performing virtual mapping based on the structured medical knowledge graph by adopting a digital twinborn model to form a virtual medical twinborn body; based on the virtual medical twins, combining real-time monitoring data and historical patient flow data, through multi-dimensional feature extraction and pension mode recognition, dynamically optimizing and presetting a personalized medical scheme and a resource scheduling strategy, and outputting a medical care service optimization scheme; generating a target service list in combination with the analyzed doctor-patient dialogue text, and distributing the target service list to a preset pension service cooperation terminal; the method has the effect of improving the real-time performance and the accuracy of the old people medical care service strategy.

The invention discloses a cable sheath ring current fault positioning in-loop simulation method and system based on LABVIEW. The method comprises the following steps: collecting ring current data of cable sheath monitoring points in real time under the control of LABVIEW, and carrying out digital display and graphical display; decomposing circulation data to obtain a wavelet coefficient and calculating features, and inputting a classification model to obtain a fault type when the features are abnormal; calculating a compensation coefficient considering the influence of the electromagnetic field, and calculating the position of a fault point in combination with a double-end traveling wave method; the operation model switches a typical working condition simulation mode, prediction of a Bayesian reasoning correction model is carried out, and the full-life-cycle operation state of the cable is simulated; and performing fault early warning through the LSTM model and risk assessment. The method can effectively improve the cable operation and maintenance efficiency and reliability, and is widely applied to cable fault detection and guarantee of safe and stable operation of a power system.

The invention belongs to the field of hydrological data processing, and particularly discloses a runoff data interpolation model construction method and system. The method comprises the following steps: constructing a time sequence runoff data set on the basis of spatial and temporal distribution characteristics of hydrometric stations of a river basin; a space-time coupling interpolation model architecture is constructed and comprises an encoder and a decoder, the encoder comprises a Bi-LSTM module and a multi-head attention module, the Bi-LSTM module extracts forward and backward local time sequence characteristics of time sequence data layer by layer through a bidirectional information transmission mechanism, the multi-head attention module is used for capturing a space-time relationship in the time sequence data, and the time sequence data is subjected to time sequence data processing. The decoder adopts a mask self-attention mechanism to combine with a feature weight fusion module to dynamically correct a missing value; and performing model training and optimization on the interpolation model by using the time sequence runoff data set. According to the invention, interpolation of key time sequence dynamic information in the hydrological field can be realized.

The invention relates to a borrower voice interaction risk control method and system based on voiceprint features and lip synchronization. The method comprises the following steps: synchronously acquiring a voice signal and face video stream data of a user through acquisition equipment; performing voice feature extraction on the voice signal to generate a voiceprint feature vector and a voice time sequence feature vector; lip motion feature analysis is carried out on the face video stream data, and lip motion track feature vectors representing lip dynamic changes are extracted; performing identity matching on the voiceprint feature vector and a pre-stored reference voiceprint database to generate a first matching degree score; performing cross-modal time sequence alignment analysis on the voice time sequence feature vector and the lip movement trajectory feature vector to generate a second matching degree score; and generating a comprehensive risk control scoring result according to the first matching degree score and the second matching degree score. According to the scheme provided by the invention, a multi-modal cross validation mechanism can be formed, and the limitation of a traditional single-modal detection scheme is effectively overcome.

The invention relates to the technical field of data acquisition, and discloses a distributed photovoltaic data acquisition method and device based on time synchronization. The method comprises the following steps: performing distributed transmission processing on nanosecond synchronous acquisition reference signals through a time delay compensation network to obtain trigger synchronization signals of a plurality of acquisition nodes, and performing data acquisition processing through a multi-channel parallel sampling circuit to obtain original voltage and current data; and carrying out data verification processing on the original voltage and current data through a digital filtering algorithm to obtain effective acquisition data, carrying out string matching analysis processing to obtain string feature distribution, and carrying out data screening processing through a state evaluation algorithm to obtain real-time performance data of the photovoltaic module. Through high-precision clock synchronization and parallel sampling technologies, nanosecond sampling synchronization of a plurality of acquisition nodes is realized, and the acquisition data is ensured to have a strict time sequence corresponding relation, so that an accurate data basis is provided for performance evaluation and fault diagnosis of the photovoltaic module.

The invention relates to the technical field of computer video processing, and discloses a low-delay video stream real-time processing method and device, and the method comprises the steps: obtaining original video stream data, and processing the original video stream data through employing a lightweight motion prediction method; processing the macro block data set and the predicted coding configuration parameter by adopting multi-thread assembly line coding to obtain a coded data block; establishing a data transmission mechanism to perform data flow control on the unified memory access interface; a heterogeneous task scheduling strategy is adopted to distribute task division results; a lightweight neural network is adopted to carry out parameter adaptive adjustment, and an optimized video stream processing result is obtained; according to the method, a zero-copy data transmission technology is adopted, and optimal configuration and efficient utilization of computing resources are achieved.

The invention discloses a digital human interaction method and device based on multi-modal sentiment analysis and a medium, and relates to the field of artificial intelligence, and the method comprises the steps: collecting multi-modal data of a user in real time through a multi-source sensor device; the multi-modal data comprises face video stream data, voice audio stream data and text dialogue data; calling data analysis engines corresponding to different modalities, and extracting corresponding modal feature sequences; according to the current interaction scene, the modal feature sequence and the historical dialogue context features are fused, and a comprehensive emotion evaluation result is generated; outputting a corresponding multi-modal response data packet based on the modal feature sequence through an interactive response engine corresponding to a comprehensive emotion evaluation result; and executing the multi-modal response data packet. And after feature fusion is carried out in combination with the current interaction scene, the generated response can more accurately fit the current emotion demand and communication context of the user, so that the digital human can be more easily fused into various scenes needing emotion interaction.

The invention discloses a traffic flow prediction method based on a clustering and space-time fusion graph convolutional network, and belongs to the technical field of intelligent traffic. The method comprises the following steps: firstly, acquiring traffic flow data and resampling, and constructing microscopic and macroscopic traffic flow data sets; then constructing a space-time fusion graph convolutional neural network, wherein the space-time fusion graph convolutional neural network comprises a space-time fusion module and a macro-micro interaction module; training the model by using the data set; and finally, traffic flow prediction is carried out by using the trained model. Compared with the prior art, through a clustering algorithm and a unique network structure, the traffic flow time-space information is effectively integrated, the prediction precision is improved, the adaptability of the model to a complex traffic scene is enhanced, more reliable prediction support is provided for an intelligent traffic system, and optimization of traffic management and alleviation of congestion are facilitated.

The invention provides a photovoltaic power station energy storage management system and method, and relates to the technical field of power system energy storage. The photovoltaic power station energy storage management system comprises the following modules: a data acquisition module, a prediction analysis module, an optimization scheduling module, a health management module, a real-time control module, a power grid interaction module and an energy efficiency evaluation module. And the data acquisition module is used for cleaning photovoltaic array output voltage / current data by adopting an improved Kalman filtering algorithm based on an Internet of Things sensing network, integrating environmental parameters such as irradiance and temperature of a meteorological station through a multi-source data fusion technology, and generating a standardized operation data set. According to the method, photovoltaic array output data is cleaned and integrated through an improved Kalman filtering algorithm and a multi-source data fusion technology, a high-precision standardized data set is constructed, a dual prediction architecture of an attention mechanism long-short term memory network and a time convolution network is combined, and the space-time correlation between photovoltaic output and load demand prediction is remarkably improved.

The invention relates to a video frame data segmentation right confirmation and dynamic transaction method and system based on a block chain. The method comprises the following steps: segmenting video stream data according to a preset frame rate to generate independent frame images, and carrying out anti-collision hash calculation on the independent frame images to generate a unique identifier; generating a comprehensive value score through a multi-modal analysis model in combination with the independent frame image and the corresponding script text data; generating NFT assets anchored to the block chain according to the comprehensive value score and the unique identifier; and dynamically adjusting the income distribution proportion of the NFT assets through the smart contract based on the user film watching data. According to the method, uniqueness right confirmation of frame data is realized through precise segmentation and anti-collision hash coding, value evaluation is performed by using a multi-modal analysis model, and capitalization and on-chain right confirmation are completed by means of a block chain technology. In addition, the income distribution proportion is dynamically adjusted in combination with the smart contract, efficient transaction and right distribution of the video frame data are realized, and the commercial value and transaction efficiency of the video data are improved.

The invention discloses an integrated learning classification method and system with a concept drift detection function, and relates to the technical field of machine learning and data stream processing, and the method comprises the steps: obtaining high-dimensional data of an extensible sliding window, carrying out the dimension reduction of the high-dimensional data of the extensible sliding window through PCA, and carrying out the extraction to obtain key feature data; performing real-time monitoring on the key feature data based on an adaptive window early warning detection method, automatically expanding an adaptive window during drifting early warning, and obtaining original data of the adaptive window when concept drifting occurs; and inputting the original data of the adaptive window when the concept drift occurs into a pre-established learning model based on an integrated Hough tree to obtain a trained learning model based on the integrated Hough tree, and performing real-time classification of data streams based on the trained learning model based on the integrated Hough tree. The accuracy of stream data classification can be improved, and the adaptive ability of the model to concept drift is enhanced.

The invention discloses a non-inductive identity recognition and real-time tracking method based on personnel in a video. The method comprises the following steps: S1, acquiring video stream data and extracting a key frame image; s2, key point coordinates are extracted, and a time sequence skeleton sequence is constructed; s3, decomposing gait, action and attitude features to generate standardized features; s4, inputting the standardized features into an improved multi-scale image convolutional neural network, extracting identity representation features, and generating a target identity code; s5, matching identity codes based on similarity measurement, calculating a consistency score, and establishing an identity tracking trajectory; s6, tracking is carried out in combination with identity codes and consistency scores, identity mapping is dynamically updated, and non-inductive recognition is achieved; and S7, updating a track in real time, adjusting a tracking state, and ensuring identity stability. According to the method, the improved graph convolutional network and the consistency measurement technology are combined, the identity recognition precision and tracking stability are improved, and cross-scene non-inductive identity recognition is achieved.

The invention is suitable for the technical field of people flow density detection, and provides a scenic spot people flow density detection and early warning method and system, and the method comprises the steps: collecting real-time passenger flow data through an intelligent device disposed at a key node of a scenic spot; preprocessing the collected data and then constructing a multi-dimensional feature analysis model, wherein the multi-dimensional features comprise people flow composition features, behavior pattern features and environment coupling features; constructing a sample set based on feature vectors output by the multi-dimensional feature analysis model, outputting the sample set to a deep learning model to calculate a people flow density index, and triggering graded early warning when the people flow density index exceeds a first preset threshold value; generating multi-language voice early warning information according to the graded early warning, and performing regionalized broadcasting through directional sound field equipment; and when the people flow density index exceeds a second preset threshold value, generating a tourist shunting scheme including optimized path planning, thereby effectively improving the accuracy of people flow density detection and the timeliness of early warning.

The invention discloses a distributed LED display screen collaborative management system and method, and relates to the technical field of LED display screen control. According to the system, video stream data and equipment log data are monitored, a difference area and a static area are extracted, a high-dynamic display area is identified, a data packet is compressed, an equipment log is analyzed by using a long and short-term memory network, and a fault data packet is output. Different manufacturer device protocol header fields and parameter sets in the compressed data packet and the fault data packet are mapped into a unified standard operation code, a synchronization instruction set with a timestamp is generated, and a device node weight matrix is dynamically adjusted. And in combination with the synchronous instruction set and the node weight matrix, by taking the screen resolution, the node load and the task priority as state spaces, generating a task allocation matrix, reasonably allocating rendering node IDs, transmission paths and energy consumption constraint values, and outputting a delay tolerance threshold and a resource preemption rule. And the resource utilization rate, the fault response capability and the cooperative work efficiency of the LED display screen are improved.

The invention discloses a scenic spot tourism planning and reception integrated management system, and the system comprises a perception access layer which is responsible for collecting tourist distribution, environment data and facility states in real time, and converting fragmented physical information into a standardized data flow; the data intelligent layer is responsible for processing a data stream input by the perception access layer, integrating dispersed fragmented data by using a space-time knowledge graph, constructing a panoramic three-dimensional thermodynamic diagram, performing dominant implicit information, and constructing a tourist digital portrait based on a multi-dimensional data fusion and machine learning algorithm; the service center layer is responsible for constructing an intelligent scheduling platform on the basis of the panoramic three-dimensional thermodynamic diagram to monitor thermodynamic abnormity in real time and trigger graded early warning, and performing scene customization by applying a personalized recommendation engine in combination with tourist digital portraits and real-time thermodynamic distribution; and the interaction touch layer is responsible for receiving and converting the instruction of the service center layer into ground projection navigation and air suspension prompt visual forms and transmitting the ground projection navigation and the air suspension prompt visual forms to tourists.

The invention discloses a traffic network toughness diagnosis method under flood disasters based on a space-time diagram neural network, and relates to the crossing field of traffic engineering and artificial intelligence. The method comprises the following steps: collecting traffic topology, flood monitoring and traffic flow data, and carrying out space-time alignment; a flood coupling dynamic space-time diagram is constructed, a water depth-traffic capacity response mechanism is introduced, and real-time mapping from a disaster physical state to a network topology is realized by utilizing an attenuation function meeting physical monotonicity constraint and dynamically updating an edge weight of a diagram structure according to real-time water depth; inputting the dynamic graph into a pre-trained space-time graph neural network model, extracting space-time evolution characteristics and outputting a toughness diagnosis result; model training adopts a toughness label generated based on an anti-fact baseline to carry out supervised learning, and introduces a physical constraint loss function. According to the method, the problems of decoupling of disaster features and graph structures and unavailability of toughness labels in the prior art are solved, and the physical consistency and accuracy of diagnosis are improved.

The invention discloses a space-time diagram comparison learning method based on big kernel attention traffic flow prediction, and the method comprises the steps: S1, organizing traffic flow data into a time sequence format, and constructing a road network space-time diagram; s2, carrying out feature level, topology level and time interpolation data enhancement on the traffic flow data; s3, coding the road network space-time diagram, and extracting space-time features through large-scale convolution and adaptive feature fusion by adopting a large kernel attention mechanism; s4, respectively designing comparative learning tasks of two dimensions of time and space on the basis of the space-time representation after coding processing in the step S3; s5, inputting the space-time representation after the comparison learning task of the encoder into a decoder; s6, a decoder adopts a multi-layer perceptron structure, and the features are restored to flow predicted values of multiple time steps in the future through a full connection layer; s8, returning to the step S1, and continuing to start training; the method has the advantages that the data missing and abnormity adaptive capacity, the dynamic road network change modeling capacity and the modeling precision are improved.

The invention discloses a cross-domain joint authentication and multi-party signing system and method, and belongs to the technical field of cross-domain authentication. The system is characterized in that a cross-domain authentication request module receives initiating domain request information, determines a target domain, obtains a physical identity registration result, derives a temporary identity token, constructs, signs and packages a cross-domain authentication request packet, and sends the cross-domain authentication request packet; the execution stream verification module obtains target domain execution stream data and generates a verifiable execution stream; the consistency verification module matches the evidence of the initiation domain and the target domain based on a strategy rule to obtain a target evidence set passing verification; and the cross-domain verification module performs hierarchical hash on the target evidence set to generate a synthesized hash value, generates a signature result in combination with the request packet and verifies the signature result to obtain a cross-domain signature verification result. According to the scheme, by generating the verifiable execution stream and the verification evidence data, credible tracking and integrity guarantee of cross-domain operation are achieved, and it is ensured that cross-domain authentication is safe, reliable and auditable in combination with hierarchical hash and signature verification.

The invention provides a method for intelligently judging a standing layering state of a chemical experiment, which is applied to the technical field of chemical experiments and comprises the following steps: collecting experiment video stream data in real time; using a Yolov8 target detection algorithm to accurately identify a liquid layering area, and judging whether a layering phenomenon occurs or not; if the layering phenomenon occurs, judging whether an emulsion layer exists or not by adopting a Yolo-cls image classification technology; if the emulsion layer does not exist, accurately extracting an ROI (Region of Interest) of liquid level layering according to a Yolov8 target detection result; utilizing a DINOv2 model to record the depth semantic features of the liquid level layering area at different moments in real time; acquiring a similarity difference value at different moments by using a similarity algorithm; judging whether the difference value is within a preset threshold range or not; if yes, layering of the liquid level is completed; the prior information of the liquid level position needs to be reflected and known through equipment, and the liquid level can only be placed at a fixed position every time and cannot be judged in real time; in the prior art, the phenomenon that an emulsion layer appears in liquid is not considered, and real-time detection in the whole experiment process cannot be realized based on the liquid standing completion state.

The invention discloses a target detection optimization method based on a multi-modal large model. The method specifically comprises the following steps: acquiring video stream data; inputting the image after frame extraction of the video stream into a preset target detection model, and outputting target detection frame coordinate information contained in the image; if the confidence coefficient of the target detection frame is greater than a preset value, uploading the current picture and coordinate information of the target detection frame to a multi-modal large model together; and the multi-modal large model receives the coordinate information, the image information and the text cue word, and judges and outputs whether the current image contains a specified target or not.

The invention relates to the technical field of multi-sensor detection, and discloses a multi-sensor fusion coal conveying belt coal blockage detection method and device and a storage medium, and the method comprises the steps: collecting a laser point cloud, a first visual image and millimeter wave volume information of a coal flow of a coal conveying belt transfer point, and carrying out the dust environment restoration of the first visual image, obtaining a second visual image; registering the laser point cloud with the second visual image to obtain first fusion data; performing surface projection transformation on the millimeter wave volume information to obtain surface projection data, and integrating the surface projection data with the first fusion data to obtain second fusion data; performing time compensation on the second fusion data to obtain synchronous coal flow data; the coal flow accumulation abnormity identification is performed based on the synchronous coal flow data, the coal flow blockage early warning signal is generated, the accurate identification of the coal flow accumulation abnormity state is realized, and the reliability and the accuracy of blockage detection are improved.

The invention discloses an online detection method for small and special motor winding defects based on pulsed eddy current and deep learning, and relates to the technical field of nondestructive testing, original pulsed eddy current detection data containing time domain signals and frequency domain features are collected through a multi-channel eddy current sensor array, and a Maxwell equation constraint network is used for denoising and feature enhancement of the data, so that the detection accuracy is improved. Generating a defect feature candidate set in combination with a multi-scale defect generative adversarial network to obtain target eddy current data, applying a chaos frequency modulation pulse sequence to the target eddy current data as an excitation signal, and collecting a response signal by using a phase synchronization frequency locking technology to obtain enhanced eddy current data; the method comprises the following steps: extracting a physical feature of a sensor, extracting a corresponding electromagnetic feature vector containing the physical feature and a deep learning feature, comparing the electromagnetic feature vector with a preset defect feature library, and determining a defect detection result by combining dynamic excitation response difference. And constructing a dynamically updated defect feature library and combining with a fine tuning network.

The invention discloses an electric power operation supervision method and system based on AI behavior recognition and semantic analysis, and belongs to the technical field of electric power system safety, and the method comprises the steps: arranging a control architecture and collection equipment of an electric power system, and continuously collecting voiceprint data and video stream data; verifying the identity of an operator through voiceprint recognition, carrying out semantic analysis on a voice instruction based on an electric power standard term library, and judging the consistency between the instruction content and a task issued by a system; identifying the position of an operator through visual positioning, performing spatial matching with the interval number of the target equipment, and detecting the normalization of an operation behavior through video analysis; and generating a voice interaction prompt according to instruction fuzziness, triggering hierarchical alarm through multi-modal data fusion, and synchronously recording and storing violation operation data. The power system supervision efficiency is improved, authorization operation is ensured, human errors are reduced, safety is guaranteed through visual monitoring, alarm is triggered through multi-mode fusion, violation is responded in time, evidence is recorded, and traceable safety management is supported.

The invention discloses an intelligent security and protection video monitoring system for preventing animal attack behaviors, and relates to the technical field of intelligent security and protection, and the system comprises the steps: synchronously collecting a thermal radiation image sequence and an RGB image sequence, and generating a cross-modal video stream data packet; performing multispectral feature extraction on the cross-modal video stream data packet to generate a visible light enhancement feature and an infrared specific feature; cross-modal shared features are extracted from the visible light enhancement features and the infrared specific features through a shared weight convolution layer, and a mixed feature tensor is formed through splicing; horizontally dividing the mixed feature tensor into equal-width regions, calculating region pseudo anchor points, generating a multi-scale candidate frame by improving a YOLOv7 detection head, guiding similar aggregation and heterogeneous rejection loss by the pseudo anchor points, and outputting a high-confidence candidate frame set; and converting bounding box parameters of each candidate box in the high-confidence candidate box set into a state vector. According to the method, the alignment of the time stamps of the cross-modal data is ensured by dynamically adjusting the primary and secondary data streams.