2838 results about "Feature generation" patented technology

The invention discloses a network security analysis early warning system based on artificial intelligence, and the system comprises a data collection layer which captures full flow based on DPI, aggregates firewall logs, terminal behaviors and threat intelligence, and constructs a structured data pool; through TLS fingerprint identification of AI driving, the encrypted traffic is penetrated, and a sampling strategy is dynamically adjusted in combination with reinforcement learning. The intelligent analysis layer is used for carrying out cross validation on known threats and abnormal behaviors; the time sequence CNN extracts encrypted traffic features, and a novel threat detector is rapidly generated by using historical attack fragments in combination with a meta-learning framework; sHAP value driving dynamic feature selection and optimization feature vector input; the decision-making early warning layer is used for fusing multi-source features through a Bayesian network and generating 0-100 score risk scores; a self-adaptive threshold module is combined to adjust a score threshold in real time, and a high-risk event is pushed; the collaborative response layer is used for triggering a preset decision tree, deploying a GAN dynamic honeypot to trap an attacker and reversely tracing; the Neo4j visually restores the attack path, and blocking is executed after the threat is confirmed by a progressive response mechanism.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses an enhanced decision method, device, equipment and medium based on thinking chain annotation, which comprises the following steps: extracting core information features to generate a structured data set, loading a basic language model and executing supervision fine tuning to generate a fine-tuned model, fusing multi-modal input to generate fusion features, constructing a state observation space to receive the fusion features as input, generating reward signals based on a double reward mechanism and optimizing model parameters to generate an optimized model, deploying a monitoring module to dynamically adjust parameter configuration to generate an adaptive decision model, and outputting a decision response result. According to the method, multi-source data extraction, structured expression, multi-modal fusion, reinforcement learning optimization and dynamic adaptive mechanism fusion are carried out, so that the understanding ability of the model to complex data, reasoning transparency and the adaptive ability of the model to coping with environmental changes are remarkably improved.

The invention relates to the technical field of power equipment fault diagnosis, in particular to a power equipment fault intelligent diagnosis method and system based on deep learning. The method comprises the following steps: automatically learning high-dimensional space-time correlation features in original time series data through a deep feature extraction network, and generating feature vectors representing potential abnormal modes of equipment; performing adaptive weight distribution on the high-dimensional space-time correlation features by using an attention enhancement mechanism, and marking a fault sensitive area to form enhanced fault features; inputting the enhanced fault features into a multi-level classifier for joint fault mode recognition and severity evaluation, and outputting a diagnosis result tensor containing a fault type and confidence; and an equipment maintenance decision signal is triggered based on the diagnosis result tensor, and the feature extraction network and classifier parameters are iteratively optimized according to feedback data, so that the intelligent level of operation and maintenance of the power equipment can be comprehensively improved.

The invention relates to the technical field of PC (Personal Computer) terminal AI (Artificial Intelligence) computing, and discloses a method and a system for dynamically scheduling generative AI heterogeneous computing resources of a PC terminal. The system comprises a resource state acquisition module, a scheduling graph generation module, a resource fluctuation entropy analysis module and a scheduling decision engine module. The resource state acquisition module captures running state parameters of a GPU kernel, a CPU thread and a memory block in real time, and generates a resource state feature tensor through normalization processing; the scheduling atlas generation module analyzes and computes the node connection topology, extracts the correlation between the devices, and constructs a multi-dimensional scheduling atlas; the resource fluctuation entropy analysis module separates the load feature vectors, calculates the entropy of each calculation unit and generates a heterogeneous resource entropy matrix; and the scheduling decision engine module jointly analyzes the atlas and the matrix, identifies bottleneck node resource competition characteristics, generates a dynamic scheduling instruction set, adapts to generative AI task requirements, and ensures efficient and stable operation of the task.

The invention relates to the technical field of manufacturing process control, and discloses a multi-dimensional process data co-simulation control method and system and a storage medium. The method comprises the following steps: firstly, collecting a multi-dimensional process parameter set of a plurality of process equipment in a manufacturing production line, carrying out cross-dimensional feature extraction, and generating a comprehensive feature matrix containing a time sequence feature, a spatial distribution feature and an energy consumption feature; according to feature relevance of different dimensions in the comprehensive feature matrix, a process parameter dynamic coupling model is constructed, co-simulation is carried out on interaction between process equipment, and a process state evolution sequence is output; extracting abnormal fluctuation characteristics in the sequence, and generating a process parameter adjustment instruction set; and finally, according to the adjustment instruction set and real-time process feedback data, dynamically correcting model simulation parameters, generating an optimized process control strategy, and executing the optimized process control strategy. According to the method, collaborative analysis and dynamic control of multi-dimensional process parameters are realized, and the accuracy and adaptability of process control are improved.

The invention discloses a substation equipment rare defect simulation and identification method and system and a storage medium. The method comprises the following steps: constructing an equipment reference feature library; marking dynamic features of rare defects in historical inspection according to a spatial-temporal feature enhancement algorithm, generating a knowledge graph, and constructing a dynamic defect learning library; the method comprises the following steps: learning space association and environmental factor influence of defects and equipment through a bimodal generation network, and generating initial defect data matched with a weak area of the equipment; generating high-credibility defect fusion data through physical constraint-intelligent detection double screening; constructing a three-dimensional mixed data set, and screening high-quality training samples through a dynamic defect evolution algorithm and hierarchical cognitive evaluation; and constructing a multi-algorithm collaborative fine tuning network by using a federated learning framework, simulating and labeling defect information, and outputting a multi-dimensional identification prediction report. The method aims at solving the problems that the model is insufficient in rare defect recognition precision and lack of evolution prediction ability, and high-quality simulation of rare defect samples and high-precision recognition of the model are achieved.

The present application provides a data processing method and apparatus, an electronic device, a computer readable storage medium and a computer program product. The method comprises: acquiring historical interaction information and a predicted interaction text corresponding to the historical interaction information; extracting a first acoustic feature and a first semantic feature of the historical interaction information, and extracting a second semantic feature of the predicted interaction text; performing fusion mapping on the basis of the first acoustic feature, the first semantic feature and the second semantic feature to obtain a first paralanguage feature; denoising initial noise on the basis of the second semantic feature and the first paralanguage feature to obtain a second acoustic feature of the predicted interaction text; and on the basis of the second acoustic feature, generating a voice signal corresponding to the predicted interaction text.

The invention relates to the technical field of digital economic risk control, and discloses a digital economic risk identification system and method based on artificial intelligence. A risk data acquisition engine of the system obtains transaction behavior data streams from a plurality of digital economic transaction platforms in real time, and converts the transaction behavior data streams into a structured transaction feature matrix; an abnormal mode detection engine extracts time sequence abnormal features through a deep residual network to generate an abnormal feature vector set; the risk association analysis engine constructs a risk propagation path map through a graph neural network, and outputs a risk association degree scoring matrix; the dynamic threshold adjustment engine performs adaptive threshold calibration according to the historical risk event database to generate a dynamic risk threshold vector; and the risk decision engine compares the scoring matrix with a dynamic threshold value, marks risk transaction nodes and generates a risk early warning instruction set. The system can adapt to digital economic transaction characteristics, and the comprehensiveness and accuracy of risk identification are improved.

The invention discloses a mechanical transmission system fault trend prediction system based on dynamic feature recognition, and relates to the technical field of mechanical state monitoring. Comprising the following steps: synchronously acquiring a load torque signal and a lubrication state parameter signal of a transmission system and vibration acceleration signals of a plurality of measuring points through a signal acquisition module; the working condition decoupling characteristic generation module carries out time-frequency analysis on the vibration signal, calls a pre-stored load disturbance spectrum template according to a load torque signal to carry out adaptive differential processing so as to eliminate load fluctuation interference, and calls a correction rule set according to a lubrication state parameter signal to carry out form recombination on the signal so as to compensate the lubrication state influence; and finally outputting a working condition decoupling feature representing the health state of the mechanical part. And the trend prediction module calculates and obtains fault development trend and residual life estimation data through a pre-trained fault prediction model. According to the method, the dynamic characteristics representing the essential degradation of the part are effectively extracted, and the accuracy and reliability of fault trend prediction of the mechanical transmission system are improved.

The invention relates to the technical field of artificial intelligence, can be applied to service scenes of pension service, financial science and technology, medical health and the like, and discloses a multi-level heterogeneous integrated chip task processing method, device, equipment and medium, and the method comprises the steps: constructing a multi-level heterogeneous integrated chip composed of a perception processing layer, an intelligent decision-making layer and a driving control layer, the layers are connected through a vertical interconnection structure; receiving multi-modal task data and extracting features to generate feature vectors; inputting the feature vector into a neuromorphic processing unit to determine a task decision result; converting the decision result into a driving signal to control an execution device; adjusting synaptic weights based on the feedback signal; and monitoring chip operation state parameters and dynamically adjusting processing frequency and structure parameters. By integrating multi-modal sensing, neuromorphic decision and a dynamic feedback mechanism, data sensing, decision and execution processing are completed in a chip, and the real-time performance and the calculation efficiency are improved by combining operation state monitoring and adjusting frequency and structure.

The invention discloses a self-adaptive data knitting performance optimization method based on artificial intelligence. The method comprises the steps of obtaining multi-source heterogeneous data based on a data source list and analyzing the multi-source heterogeneous data to generate a metadata set at least comprising technical metadata, business metadata, operation metadata and management metadata; based on the virtual table interface, performing virtual table abstraction and packaging processing on the metadata set to generate a logic data carrier; determining an operational attribute of the metadata set to generate a data knitting path of the logical data carrier based on the operational attribute; monitoring the data access task queue and the access index feedback in real time, extracting resource load association features from the data access task queue and the access index feedback based on the constructed resource scheduling model, and generating a resource scheduling strategy according to the resource load association features; and optimizing the data knitting path of the logic data carrier based on a resource scheduling strategy to obtain an optimized data knitting path so as to perform data knitting on the multi-source heterogeneous data.

The invention provides a body armor composite interlayer defect positioning method and system based on multi-modal nondestructive testing, electronic equipment and a storage medium, and relates to the technical field of nondestructive testing. Ultrasonic guided wave, pulsed eddy current and infrared thermal wave excitation signals are synchronously applied to a body armor composite interlayer, and multi-modal response signals of all positions are collected; and generating an original multi-modal response signal set. And inputting the signal into a pre-trained deep convolutional neural network, determining a target frequency band parameter and a target noise suppression parameter of each modal response signal, and outputting an adaptive modulation parameter group. Performing frequency domain filtering and noise suppression processing on an original signal set to generate an optimized signal set, inputting spatial frequency features into a cross-modal feature fusion model, adaptively associating defect sensitive features of different modals through an attention mechanism in the model, and generating a three-dimensional defect distribution diagram of the composite interlayer, thereby realizing millimeter-level precision defect positioning. The precision and efficiency of body armor composite interlayer defect positioning can be improved.

The invention provides a wind turbine generator voiceprint fault recognition method, and relates to the technical field of wind turbine generator state monitoring and fault diagnosis, and the method comprises the steps: carrying out the noise reduction of an original audio signal through variational mode decomposition, screening a target mode of which the frequency, energy and kurtosis accord with features, and reconstructing the signal; extracting a Mel frequency cepstrum coefficient and a sensing noise robust coefficient, and generating multi-dimensional voiceprint data in combination with statistical characteristics such as a frequency spectrum gravity center, a spectrum entropy, energy, kurtosis and a zero-crossing rate; constructing a support set based on the prototype network, realizing small sample fault classification by calculating the Euclidean distance between the feature vector and the prototype vector, and outputting a preliminary result; judging whether the voiceprint is abnormal according to a preset threshold value, if so, storing the voiceprint into a dynamic abnormal voiceprint knowledge base; frequently occurring abnormal samples are manually labeled and added into a support set, the prototype network is retrained to update the model, and continuous optimization of the fault recognition capability is achieved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a task instruction generation method, device and equipment based on cross-modal fusion, and a medium, and the method comprises the steps: carrying out the decoding and noise reduction of an input video, generating a frame sequence, and recognizing a plurality of key frames based on the inter-frame similarity; extracting spatial features of the key frames to form a sequence, and generating video spatial-temporal features in combination with time features; performing semantic preprocessing on the input text to obtain text semantic features, and acquiring motion sensor signals to obtain motion features; fusing the video spatio-temporal features, the text semantic features and the action features to generate fused features; and generating a perception vector based on the fusion feature and outputting a task instruction. According to the method, multi-modal fusion is realized through key frame extraction and space-time fusion mechanisms in combination with text semantic features and action features, and the perception expression ability and the task instruction generation accuracy are improved by using time sequence information and multi-source perception input of the video.

The invention relates to the technical field of smart city traffic, and discloses a smart city traffic dynamic optimization system and method based on digital twinning. The system obtains urban traffic network multi-dimensional data from a plurality of heterogeneous data sources through a traffic multi-dimensional data acquisition module and integrates the urban traffic network multi-dimensional data into a traffic related data warehouse; a traffic digital twinning model construction module extracts features from the data warehouse to generate a traffic related feature matrix, and a digital twinning traffic dynamic model is constructed according to the traffic related feature matrix to output a theoretical traffic state value; the traffic flow map construction module determines a dimension link map of each dimension and constructs a traffic flow link map; the traffic core feature screening module screens a traffic core feature sequence based on the map; the traffic multi-dimensional optimization analysis module performs multi-dimensional difference analysis on the theoretical traffic state value and real-time actually measured traffic data, and generates a region-level difference coefficient matrix in combination with the core feature sequence; and the traffic event association positioning module can realize accurate management and dynamic optimization of urban traffic.

The invention discloses a traffic operation and maintenance fault intelligent scheduling method and system based on an AI large model, and belongs to the technical field of traffic control. The method comprises the following steps: collecting a vehicle driving track GPS coordinate set, a traffic flow density matrix, a vehicle-mounted camera monitoring image frame sequence and a fault vehicle owner speed anomaly detection result in real time; constructing a traffic operation state analysis model, and outputting real-time traffic operation state characteristics; generating a traffic fault probability distribution curved surface in a future time window; generating a comprehensive fault positioning confidence coefficient matrix; and planning an optimal maintenance resource path according to the pheromone updating rule, and updating the optimal maintenance resource path to the visual scheduling platform in real time. According to the method, space-time diagram convolutional network dynamic modeling is constructed according to multi-source data, so that the limitation of a space blind area of a single data source is broken through, the fault positioning speed is improved, and the problems of incomplete coverage and low positioning speed in the prior art are solved.

The invention discloses a flexible stone texture defect identification method based on a multi-scale convolutional neural network, and the method comprises the following steps: collecting images of the surface of a flexible stone, and carrying out the batch classification; selecting a first image of each production batch as a batch first sample, and generating batch configuration parameters; performing texture feature extraction by using the batch configuration parameters and the to-be-detected image to generate a texture map; respectively inputting the to-be-detected image into a spatial domain convolution branch and a frequency domain convolution branch of the space-frequency neural network model, and extracting spatial domain features and frequency domain features according to the scale control information; the spatial domain features and the frequency domain features are fused; and generating candidate areas based on the fused features, performing positioning and confidence evaluation, removing the candidate areas with confidence smaller than a preset threshold, and generating a flexible stone texture defect detection result. According to the method, the surface defects of the flexible stone can be accurately detected, the detection efficiency and robustness are improved, and the manual detection cost is reduced.

The invention discloses an ecological restoration effect evaluation and simulation system after polluted soil restoration, and relates to the technical field of soil restoration, and the system comprises a soil feature generation module which generates an ecological feature data set; the ecological restoration evaluation module is used for establishing a multi-dimensional evaluation model by using an analytic hierarchy process and a fuzzy comprehensive evaluation method based on the ecological characteristic data set, and generating an ecological restoration effect index; the dynamic simulation prediction module is used for constructing an ecological restoration dynamic simulation model and simulating the evolution trend of a soil ecological system under different environment conditions; and the restoration strategy optimization module is used for generating a targeted ecological restoration optimization scheme by combining a preset restoration strategy library according to the ecological restoration effect index and the dynamic simulation prediction result. According to the method, a closed-loop system integrating multi-source data acquisition and processing, multi-dimensional evaluation, dynamic simulation prediction and stepped strategy optimization is constructed, and accurate evaluation of the ecological restoration effect after contaminated soil restoration and scientific optimization of the restoration strategy are achieved.

The invention provides a multi-dimensional data fusion system for operating truck risk rating, and relates to the technical field of data processing, and the system comprises a data collection module which is used for obtaining the dynamic operation data and historical static information of a target operating truck; the data preprocessing module is used for performing field alignment, abnormal value elimination and format standardization; the feature analysis module is used for extracting dynamic behavior features of vehicle operation and performing statistical calculation in a preset time window; the event identification and risk assignment module is used for identifying a single event or a combined event, assigning an event risk weight to the single event or the combined event, and determining a corresponding road condition risk level in combination with the vehicle position information; the multi-dimensional fusion module is used for fusing features and generating time serialized multi-dimensional risk feature vectors; the risk rating module is used for scoring the multi-dimensional risk feature vector and outputting a corresponding risk rating result; according to the invention, the accuracy of the multi-dimensional data fusion system is improved.

The invention relates to the crossing field of hydraulic engineering hydrological monitoring technology and machine learning prediction technology, discloses a sediment concentration prediction method based on deep learning, and aims to solve the problems that in existing sediment concentration prediction, hyper-parameter manual tuning is low in efficiency, key feature attention is insufficient, local and time sequence information is difficult to consider by a single model and the like. Accurate prediction is realized through five core modules: a data preprocessing module performs missing value filling, abnormal value processing and derivative feature generation on hydrological data; the feature selection module screens key features based on mutual information; the time sequence construction module generates time sequence data through a sliding window; the hyper-parameter automatic optimization module adopts Bayesian optimization iteration to obtain an optimal hyper-parameter; the CNN-LSTM-attention prediction module fuses CNN local feature extraction, bidirectional LSTM time sequence dependence capture and multi-head self-attention mechanism key feature focusing capability, is suitable for scenes such as river channels and channels, and provides efficient decision support for hydrological regulation and control.

The invention discloses a data auditing method based on big data, and relates to the technical field of big data, and the method comprises the steps: obtaining multi-modal data in a big data platform form, extracting features of the multi-modal data to generate a feature set, creating a rule base based on the feature set, and constructing a cross-form dependency graph according to the feature set and the rule base; cascade auditing is executed through a cross-form dependency map, when auditing fails, an affected field is reversely positioned according to the connection direction of the map, and incremental state rollback and re-auditing are executed on the affected field; when it is detected that the high-frequency data is changed, an anti-rollback storm mechanism is started, a cascade load index is obtained, and a rollback instruction set is generated through cascade blocking based on the index; and executing distributed fault-tolerant control, constructing a node collaborative protection system through cascade loads, and outputting a fault-tolerant operation instruction.

The invention relates to the technical field of intelligent fire safety linkage control, in particular to an intelligent locking linkage control system and method based on fire monitoring, and the system comprises an acquisition module, a modeling module, a simulation engine module, a decision center module and an execution module. The acquisition module acquires physical quantity data of a key area of a building, wherein the physical quantity data comprises high-temperature radiation spectrum offset, aerosol particle swarm distribution characteristics and local heat convection intensity. The modeling module generates an environmental interference confidence index through convolutional neural network fusion features, and starts an incremental clustering algorithm to update an interference knowledge base when the confidence is insufficient. And the execution module dynamically compresses the delay window according to the risk map, and triggers a cross-level linkage mechanism through a people flow density threshold. And the environment sampling frequency adjustment coefficient is fed back to the acquisition module, the execution state data reverse drive modeling module iteratively updates the knowledge base, a Bayesian optimizer is combined to screen high-value characteristics to reconstruct simulation parameters, and full-link closed-loop learning and continuous evolution of the false alarm suppression capability are realized.

The invention relates to the technical field of enterprise office collaboration, and discloses an enterprise series intelligent office collaboration data processing system based on edge computing. The system comprises a collaborative data acquisition module, a collaborative feature analysis module, an edge task scheduling module and a dynamic storage optimization module. The collaborative data acquisition module is deployed at a local edge node of an enterprise, captures a collaborative operation behavior flow of the multi-source office terminal in real time, and extracts space-time distribution features to generate an original collaborative feature vector; the collaborative feature analysis module analyzes the coupling strength of related data through a multi-dimensional correlation analysis engine, quantifies the frequency fluctuation amplitude of a communication session, and fuses to generate a collaborative efficiency quantized value; the edge task scheduling module dynamically divides task load levels based on the value, and matches execution priorities to generate a distributed calculation task allocation strategy; and the dynamic storage optimization module responds to the strategy, monitors the throughput delay of the storage nodes, reconstructs a high-frequency access data storage index, and generates a cross-node storage topology configuration.

The invention relates to the technical field of financial risk control, and discloses a telecommunication fraud risk identification method based on a bank card transfer scene. The method comprises the following steps: a basic feature construction stage: acquiring multi-source data of historical victim users, extracting multi-dimensional features, and processing the multi-source data into standardized time sequence data through feature coding and a DTW algorithm; in the multi-modal fusion and adversarial learning stage, a core layer containing a multi-modal analysis engine, a risk reasoning model and an adversarial generation model is constructed, and multi-modal feature fusion, risk probability output under an RLHF framework and simulated fraud feature generation driven by WGAN-GP are achieved; in the strategy output stage, risk scores are mapped through a double-layer scoring system, and three-level interception is triggered; in the model management stage, model iteration is achieved by means of a monitoring instrument panel and a rolling time window, the online effect is guaranteed by combining gray release and A / B testing, the telecommunication fraud in the transfer scene can be accurately recognized, and the risk control efficiency is improved.

The invention provides a multi-modal information fused steel pipe inner surface defect area segmentation method and system, and the method comprises the steps: obtaining a steel pipe inner surface defect RGB image and a depth map at the same time, and carrying out the preprocessing and marking; constructing a support data set and a query data set; the support and query image feature extractor is used for respectively extracting support image multi-scale aggregation features FS, support image multi-mode semantic features IS, query image multi-scale aggregation features FQ and query image multi-mode semantic features IQ by sharing the multi-mode feature extraction backbone network; the FS, the IS, the FQ and the IQ are input into a multi-feature fusion device, a graph semantic guide module is supported to generate class guide features FA by using the FS and the MS, a similar prior feature generation module is supported to generate similar prior features FM by using the IS, the IQ and the MS, the FA, the FM and the FQ are spliced on a channel dimension, and a fusion feature graph is output and decoded by a multi-mode decoder to obtain defect area segmentation output. The method can be used for segmenting the defect area on the inner surface of the steel pipe.

The invention discloses a camouflage target detection method based on feature selection attention and frequency domain edge guidance. According to the method, four-level features of a camouflage target image are extracted through a backbone network SMT and are respectively screened; the high-level features are input into a semantic information supplement module, and after semantic features are enhanced, the high-level features and the trunk features are sent into a spatial feature enhancement module together. And inputting the obtained fine-grained features into an edge feature sensing module, and finally fusing multi-scale features through a multi-scale jump connection technology to generate a mask pattern with higher discrimination. The method has the advantages that the network parameter quantity is reduced and key information is reserved through a feature selection mechanism; a spatial feature enhancement module is used for enhancing multi-scale feature representation and remote dependence modeling; the dilution of the semantic context is relieved by means of a semantic supplement module so as to improve the positioning precision; and an edge feature enhancement module is adopted to enhance edge semantic perception and improve boundary integrity. According to the method, the camouflage target detection performance is remarkably improved with relatively low calculation cost.

The invention discloses a traffic flow prediction method and system based on spatio-temporal hierarchical mixing, and relates to the technical field of traffic prediction, and the specific steps are as follows: obtaining an original traffic flow spatio-temporal sequence, mapping the original traffic flow spatio-temporal sequence, fusing spatial embedding and time period embedding, and generating an input feature; extracting time sequence features and multi-scale region features based on the input features, performing parallel extraction of node-level features and region-level features on the region features of each scale, and outputting the node-level features and a plurality of region-level features; fusing the region-level features step by step based on a hierarchical feature propagation mechanism, downloading the region-level features to the node-level features, generating space fusion features, and fusing the space fusion features layer by layer to generate time sequence fusion features; and fusing the highest-layer feature of the spatial fusion feature and the time sequence fusion feature to generate a fused spatial-temporal feature, and performing traffic prediction by using the fused spatial-temporal feature. According to the method, the efficiency and the prediction precision are improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as personal intelligence, financial science and technology, medical health and the like, and discloses a task execution strategy generation and adjustment method, device, equipment and medium. Encoding the visual information, the audio information and the language instruction information to obtain a visual feature, an audio feature and a language feature, fusing the visual feature, the audio feature and the language feature to generate a comprehensive feature, generating an initial task execution strategy based on the comprehensive feature and executing a corresponding action, and in the execution process, according to real-time feedback information of the environment, executing the corresponding action according to the initial task execution strategy. And dynamically adjusting the initial task execution strategy by adopting a reinforcement learning model to obtain an updated task execution strategy. Through multi-modal information fusion and reinforcement learning dynamic adjustment, optimization and flexible updating of a task execution strategy in a complex environment are realized, and the autonomous decision-making capability of the intelligent equipment is improved.

The invention provides an alloy bearing unsteady-state damage detection and evaluation method based on digital twinning. The method comprises the following steps: constructing an alloy bearing multi-physical field digital twinning model; the method comprises the following steps: acquiring operation state data of a bearing under an unstable working condition based on a sensor network, preprocessing the acquired data to obtain multi-source features, and fusing the multi-source features to generate a comprehensive health index; inputting the preprocessed data into a digital twin model for forward simulation, generating a prediction observation vector, comparing the prediction observation vector with a sensing measurement value to generate a residual error, and performing damage state assimilation based on the residual error; and based on the assimilated state, predicting a damage evolution trajectory under an unsteady state working condition, and evaluating probability distribution of residual life. According to the method, the reduced-order proxy model for dynamic mode switching is constructed, the mode basis is automatically expanded and the sub-models are switched when the load suddenly changes or the rotating speed jumps, and the problem of feature drift of a traditional fixed basis function model under variable working conditions is effectively solved.