753 results about "Knowledge transfer" patented technology

The invention relates to a knowledge graph construction method and system based on a large language model, and the method and system achieve the automatic construction and dynamic maintenance of a knowledge graph through multi-modal data fusion, reinforcement learning and comparative learning joint optimization, teacher-student model knowledge migration, time sequence dynamic analysis and an incremental updating mechanism. Constructing a reinforcement learning framework, and taking accuracy and integrity as reward indexes to train a large model to extract an entity relationship; a large-scale knowledge graph is used as a teacher model, and conflict resolution and semantic alignment of newly added knowledge and an existing graph are realized through a graph attention network; a verification rule is dynamically generated based on historical data and domain knowledge, and relation periodicity and mutation points are detected in combination with Fourier transform and a CUSUM algorithm; and finally, generating a traceable knowledge graph through incremental updating and version control. And the multi-modal data processing precision, the entity relationship extraction dynamic adaptability and the knowledge graph maintenance efficiency are improved.

The invention discloses an AI model training parameter dynamic optimization system, and relates to the technical field of artificial intelligence model training optimization. According to the scheme, by monitoring gradient norms in real time and fusing a frequency weighting mechanism, dynamic gradient self-adaptive cutting is achieved, the limitation of a fixed threshold value is broken through, and the model precision is guaranteed while the batch scale is expanded by 30%; a weight matrix is innovatively decomposed into a low-rank factor matrix, the internal storage is compressed to O (n + m), a strategy perception distillation technology is synchronously combined, a reward signal is dynamically generated by utilizing comparative learning to replace manual preference labeling, and collaborative optimization of parameter lightweight and knowledge migration is realized; aiming at a heterogeneous equipment environment, designing a computing power perception parameter group automatic division mechanism, and reducing communication redundancy by 40% by adopting asynchronous weighted aggregation; and constructing a data-parameter joint adjustment and optimization closed loop, and integrating a real-time data cleaning framework and a parameter normalization module to dynamically adjust the hyperparameters of the optimizer. According to the system, an efficient solution is provided for edge calculation and large model training by using a full-link adaptive architecture.

The invention relates to the technical field of industrial Internet of Things, in particular to a machine equipment online state monitoring and fault diagnosis system, which comprises the following steps of: acquiring multi-source heterogeneous sensing data through an edge computing node deployed on an equipment body, performing adaptive noise filtering and feature dimension reduction processing on original data, and acquiring multi-source heterogeneous sensing data; outputting a standardized equipment state vector set; inputting the equipment state vector set into a dynamic knowledge graph engine, constructing a fault evolution network comprising space-time correlation characteristics based on an equipment operation entropy change quantification model, and generating a graph node connection relationship with a weight coefficient; and inputting the fault evolution network into a migration reinforcement learning module, and outputting a diagnosis decision set comprising a fault type, a severity degree and an evolution path through knowledge migration of a cross-device fault mode. According to the method, the problems of edge redundancy and single feature expression in traditional rule-based atlas construction are effectively avoided, and the structuring ability and physical traceability of fault recognition are improved.

The invention provides an automatic heuristic algorithm planning method based on a large language model, and the method comprises the following steps: carrying out the initialization and problem modeling, starting from a basic heuristic mode through guiding the large language model, generating a candidate algorithm set in combination with a plurality of cognitive perspectives, and providing diversified starting points for a search space; configuring core parameters of Monte Carlo tree search; in each iteration process, planning is started in a heuristic space by utilizing Monte Carlo tree search, and the process is composed of five core stages of selection, reflection, expansion, simulation and back propagation; and after all iterations are completed, the path with the highest average reward and the corresponding optimal heuristic algorithm are returned, and the global optimality of the final solution is ensured. According to the method, the effective experience can be automatically extracted from the heuristic strategy generated historically, and real-time feedback adjustment and strategy induction optimization of the heuristic structure are realized, so that the knowledge migration and generalization ability in the search process is remarkably enhanced.

The invention discloses a multi-mode interaction method for an accompanying robot, and relates to the technical field of robot interaction.The multi-mode interaction method comprises the steps that voice, visual and tactile signals are converted into quantum states through multi-mode quantum state coding, emotion weights are dynamically fused, and unified quantum representation is constructed; the dynamic quantum decision engine analyzes environmental noise and user emotion intensity in real time based on a quantum measurement theory, generates an adaptive strategy through dynamic modal weight distribution, and solves a multi-modal instruction conflict; holographic reinforcement learning optimization is combined with quantum acceleration calculation and classical reinforcement learning, the reward function weight is dynamically adjusted, cross-modal knowledge migration is achieved through the quantum tunneling effect, and the system strategy is continuously optimized. The problems that a traditional multi-mode interaction system is rigid in mode switching, high in emotion recognition error rate, lack of self-adaptive optimization of a feedback strategy and the like are solved, and the interaction efficiency and the user experience are improved.

The invention relates to a large-scale road network traffic control method based on a deep reinforcement learning large model, and belongs to the technical field of intelligent traffic control. The method comprises the following steps: sensing real-time multi-modal road network information including urban road intersections, highway entrance ramps and emergency lanes, and generating a space-time fusion representation vector representing a current traffic network state by fusing a space diagram construction method and a time sequence embedding method; the space-time fusion representation vector and historical state memory are spliced to serve as input, a backbone network of a pre-training large language model is used for state feature distillation so as to enhance state representation, and a traffic control decision is output through a strategy network with a layered action space; through cross-modal knowledge migration and a progressive course learning strategy, a training process of a deep reinforcement learning algorithm is guided and optimized so as to improve model training efficiency and generalization ability. According to the method, the generalization performance and the accuracy of the control strategy are improved while the real-time response speed is ensured.

The invention discloses a multi-modal traffic large model real-time regulation and control method and system for vehicle-road cooperation, and relates to the technical field of artificial intelligence, and the method comprises the steps: combining multi-modal data fusion, edge intelligent reasoning, federated learning, cross-regional knowledge migration, reinforcement learning optimization and adaptive closed loop iteration; and efficient and accurate vehicle-road cooperative regulation and control are realized. The model is adopted to perform space-time alignment and high-dimensional feature extraction on vehicle-mounted, roadside and cloud data, so that the environmental perception precision is improved; cross-regional traffic knowledge sharing is realized through gradient aggregation and decentralized training, and data privacy leakage is avoided; a transfer learning and self-supervision mechanism is adopted, so that the model can quickly adapt to different cities and different road environments, and the generalization ability is improved; by adopting cloud multi-agent reinforcement learning, the optimal decision of signal lamp timing and path recommendation is realized, the traffic flow change is dynamically adapted, and the problem that efficient and real-time model adjustment cannot be realized in consideration of privacy and global optimization in the prior art is solved.

The invention relates to the technical field of language translation, in particular to a low-resource language translation method and system based on deconstruction distillation, and the method comprises the steps: obtaining parallel corpus data of a low-resource language and a general language; the method comprises the following steps: constructing a teacher model by taking parallel corpus data as input, constructing a student model trunk based on a pre-trained BERT big language model and optimizing the student model, calculating cross-task attention alignment loss based on the teacher model and the student model, and outputting and executing logits distillation based on the teacher model and the student model. Deployment of low-resource language translation is completed based on the trained student model, a high-quality knowledge migration source is provided for the student model by constructing the BERT teacher model subjected to full-parameter fine adjustment, and meanwhile, the problem of translation precision caused by insufficient low-resource language data is effectively solved by means of dual supervision of cross-task attention alignment and logits distillation.

The invention relates to a cross-domain knowledge migration cold start recommendation method based on dynamic intention perception. A system model of the method comprises a decoupling feature extractor based on graph convolution, an intention bridging network, a self-adaptive knowledge fusion mechanism and a recommendation generation unit. The method comprises the following steps: firstly, decomposing expressions of a user and an article into a plurality of intention subspaces through a decoupling feature extractor; then, establishing a soft mapping relation between intention subspaces of a source domain and a target domain by using an intention bridging network to realize intention alignment of fine granularity; the migration degree of source domain knowledge is dynamically adjusted through an adaptive knowledge fusion mechanism, and differentiated migration strategies are adopted for different users and articles; and finally, stable learning and smooth knowledge migration of the intention mapping relation are ensured by adopting a three-stage progressive training strategy of a recommendation generation unit. The problems of non-correspondence of intention semantics, negative migration and the like in traditional cross-domain recommendation are effectively solved, the recommendation effect is remarkably improved, and the method is particularly suitable for a cold start scene with sparse target domain data.

The invention relates to the field of data detection, in particular to a network traffic anomaly detection method based on aggregated mimicry distillation. According to the method, protocol level analysis is carried out on traffic through a multi-branch feature extraction network, and a unified representation vector is generated through a cross-layer fusion mechanism; calculating a first abnormal score based on a protocol perception weighted confrontation soft contrast mechanism; a heterogeneous teacher model is constructed and dynamically weighted and aggregated, and the student model generates a second abnormal score through knowledge distillation learning; forming a heterogeneous redundant detection pool by the student model, the teacher model and the rule detector, dynamically selecting the detector and applying adaptive disturbance to obtain a third abnormal score; and dynamically fusing the three types of abnormal scores to output a detection result. According to the method, the problems of protocol semantic segmentation, weak boundary sample discrimination, knowledge migration simplification and defense path predictability are effectively solved, and the detection accuracy, robustness and dynamic defense capability are remarkably improved.

The invention discloses a missing mode gamma collaborative retrieval diffusion method for an open environment, and belongs to the field of multi-mode learning and missing mode processing. According to the method, a human brain multi-source context completion mechanism is simulated, and robust multi-modal learning is realized through three innovative modules: a context retrieval enhancement module: a multi-modal memory library is constructed, related instances are retrieved through similarity calculation under a gating mechanism, and context representation of a missing mode is enhanced; the prompt drive diffusion generation module is used for constructing a semantic prompt based on a retrieval result, fusing a de-noising diffusion probability model through an attention mechanism, and realizing context-aware knowledge migration and missing modal generation; and the inverse gamma noise optimization module is used for establishing a mixed normal-inverse gamma distribution model, dynamically sensing noise, realizing uncertainty estimation in multi-modal fusion and ensuring robustness and reliability of a regression result. According to the method, the dependence of the model on the available modal quality is effectively reduced, and the cross-modal knowledge migration effect and the multi-modal learning task performance are improved.

The invention discloses an optical storage charging station cross-site heterogeneous data fusion health state early warning method, which adopts transfer learning and domain adaptation technologies, measures the data distribution difference between a source site and a target site through the maximum mean value difference, realizes knowledge transfer and improves the generalization ability of a model. And on the basis of an Attention-LSTM feature fusion mechanism, feature weights are adaptively allocated, and the fault feature extraction capability is enhanced. And designing a fault mode sharing module, coding the fault mode of the source site into a knowledge base, and rapidly matching similar faults of the target site. A model compression technology is introduced, lightweight deployment is realized through knowledge distillation and a parameter quantification method, and operation of edge equipment is effectively supported. And furthermore, an online learning mechanism is adopted to dynamically update model parameters to ensure that the model adapts to the environment change of the target site. According to the method, the accuracy and robustness of cross-site fault prediction are remarkably improved, the model deployment time is shortened, and the method is widely applied to intelligent operation and maintenance of the optical storage charging and discharging integrated power station.

A system and method for cross-domain knowledge transfer in federated compression networks. The system enables efficient lossless data compression across diverse data types by intelligently sharing compression strategies between domains. A cross-domain knowledge transfer system identifies relationships between different data domains, adapts compression parameters accordingly, and optimizes learning processes to maximize knowledge reuse. The architecture may include a knowledge repository for storing domain features and compression patterns, domain mapping components that identify similarities, and transfer learning optimization that enables efficient adaptation with minimal examples. This approach significantly accelerates model training for new domains while improving compression performance. Applications include satellite telemetry systems where efficient compression is critical for transmitting large information sets between distant locations. The system may employ probability prediction driven arithmetic coding paired with long short-term memory networks, enhanced by cross-domain knowledge sharing that adapts successful compression strategies from one domain to another while preserving domain-specific optimization.

The invention relates to the technical field of intelligent scheduling, and discloses an intelligent scheduling method and system for a factory production plan, and the method comprises the steps: carrying out the three-dimensional scanning and sensor data collection of a factory environment, and obtaining a digital twin model and a real-time production data flow; according to the digital twinborn model and the real-time production data flow, performing prototype comparison learning processing on a double-tower encoder to obtain a pre-training scheduling model; performing knowledge constraint and knowledge distillation processing on the pre-trained scheduling model to obtain a knowledge enhanced scheduling model; according to the knowledge enhanced scheduling model, constructing a double-loop coordinated scheduling system comprising a production intelligent control loop and a resource dynamic allocation loop; and performing multi-objective optimization and predictive scheduling calculation based on the double-loop coordinated scheduling system to obtain a production plan scheduling scheme. Therefore, the problem of knowledge migration of a traditional scheduling system when production conditions change is effectively solved, and the scheduling accuracy in a dynamic production environment is improved.

The invention relates to the technical field of artificial intelligence, and discloses an agent rapid construction method and system based on enhanced retrieval, and the method comprises the steps: constructing a multi-dimensional task analysis system, retrieval task characteristics are automatically represented through characteristics such as data distribution, query complexity and semantic requirements; executing a progressive architecture evolution algorithm, and automatically searching an optimal architecture meeting multi-dimensional balance of retrieval precision, calculation complexity and memory occupation based on the task characteristic vector; constructing a hierarchical knowledge distillation transfer chain, and realizing efficient knowledge migration from a large model to a small model through feature matching and attention guidance; implementing mixing precision quantification and structured pruning on different hierarchies based on sensitivity analysis, and adapting to a target deployment environment; according to the method, the model volume is reduced, the reasoning speed is increased, the energy consumption is reduced, and the enhanced retrieval agent can efficiently operate on resource-constrained equipment.

The invention discloses a distribution line unmanned aerial vehicle edge end real-time visual identification and target detection method and system based on lightweight AI. The method is based on a YOLOv8 architecture, and constructs a complete lightweight detection framework comprising a feature extractor, an enhancement module and a simplified detection head by introducing a space structure maintaining assembly, a separated large kernel convolution and a weighted reconstruction feature pyramid. A cross-dimension semantic relation model is constructed by utilizing a combined attention structure, multi-level feature fusion is realized by reconstructing a feature pyramid network, model training is performed by adopting a hybrid optimization function and a dynamic sample adjustment mechanism, and the model is deployed on a mobile computing platform after being optimized by a hierarchical knowledge transfer method. According to the method, the detection speed is remarkably increased while high precision is kept, and real-time identification and anomaly analysis of the power line element are effectively realized.

The invention discloses a zero-sample industrial anomaly detection method based on knowledge distillation, and belongs to the technical field of image detection. The method comprises a training stage and a testing stage. In the training stage, normal industrial images and abnormal industrial images in any type of industrial products are selected; constructing a knowledge distillation network architecture which comprises a teacher model, a student model, an image encoder and a text encoder; training the teacher model by using the training set data, and transferring knowledge in the trained teacher model to the student model; and in the test stage, constructing an industrial anomaly detection model, and inputting the to-be-detected picture in the test set into the industrial anomaly detection model to obtain a detection result. According to the method, efficient zero-sample anomaly detection can be realized in industrial detection tasks with unknown categories and various anomaly forms, and a solution which is efficient, high in generalization and excellent in robustness is provided for industrial visual detection.

The invention is suitable for the technical field of machine learning, and provides a feature selection method and system based on domain adaptation and domain adversarial training, and the method comprises the following steps: obtaining source domain data and target domain data, constructing a source domain feature selection target function, and generating a binary feature mask vector; constructing a deep transfer learning framework based on a domain adversarial neural network, training the domain adaptive neural network by using the source domain tagged data and the target domain untagged data in a domain adversarial form, and constructing a cross-domain shared feature representation space of the source domain and the target domain; and feature selection knowledge migration from the source domain to the target domain is realized through decoding conversion. According to the method, the feature distribution difference between the source domain and the target domain is effectively eliminated through the adversarial training strategy driven by the gradient inversion layer, the method has remarkable advantages in a target domain data scarcity scene, the data annotation cost can be reduced, cross-domain potential association can be captured, and redundant features and over-fitting risks are reduced.

The invention provides a robot social adaptive navigation knowledge learning and migration method and system, and relates to the field of mobile robot navigation. Aiming at the problems that an existing path planner lacks time sequence memory and neglects pedestrian social intent, a man-machine co-fusion scene is constructed, a training set containing an expert demonstration path is made, and a recursive generation model is input; designing a recurrent neural network embedded RRT, generating an RNN-RRT planner, and fusing historical information and pedestrian convergence probability in training; new scene loading training parameters are finely adjusted to realize knowledge migration, loss convergence or output RNN final parameters after reaching a preset round number. According to the method, the path anthropomorphism and generalization ability are improved, and the method is suitable for complex human-computer interaction scenes.

The invention provides a big data artificial intelligence AI comprehensive corrosion collection computing power platform method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting data through a distributed corrosion sensor, carrying out the space-time marking, and calculating a space-time correlation matrix to achieve the adaptive fusion of heterogeneous data; constructing a corrosion environment knowledge migration framework based on a graph neural network, and establishing cross-environment knowledge migration; and inputting the fused data into the prediction model to obtain a corrosion state prediction result. According to the method, efficient fusion and accurate prediction of corrosion data are realized, and the cross-environment corrosion monitoring precision is improved.

The invention discloses an energy storage battery health feature extraction and state evaluation method based on transfer learning. The method comprises the following steps: S1, constructing a source domain health feature library and pre-training a model; according to the method, dependence on complete cyclic data is broken through, high precision and robustness are still achieved under the conditions of data sparsity and working condition difference, and the method is suitable for intelligent operation and maintenance and predictive maintenance of an energy storage power station. And meanwhile, common incomplete and partial charge and discharge data fragments under actual working conditions can be directly utilized for feature extraction and state evaluation, dependence on complete charge and discharge cycles is avoided, and the application scene of the data driving method is greatly widened.

The invention discloses a small sample self-learning accurate identification method based on distillation knowledge migration. The method comprises the following steps: S1, extracting deep semantic features of a source domain and shallow features of a small number of samples of a target domain, and calculating a mapping matrix; s2, calculating an entropy difference distillation excitation function based on the initial alignment features; s3, executing domain knowledge distillation and generating staged distillation representation; s4, constructing a composite fitness function and initializing a parameter population; s5, performing iterative optimization by adopting a variable step size dynamic feedback compression strategy; s6, loading the optimal parameters and performing coupling alignment with the historical distillation representation; and S7, performing combined fine adjustment on the distillation weight and the model parameters through self-learning feedback. According to the method, through adaptive knowledge distillation and dynamic optimization feedback closed loop, high-precision and adaptive identification under extremely few labeled samples is realized, the generalization ability of the model is remarkably improved, and overfitting is effectively inhibited.

The invention discloses a foundation pile intelligent detection cloud platform based on image recognition, and relates to the technical field of foundation pile intelligent detection, the platform comprises a data acquisition module, an image preprocessing module, a time sequence image recognition module, a feature fusion mapping module, a cloud knowledge graph module and a visual display module; the system constructs an image time sequence tensor by collecting a construction site image sequence and construction parameters, extracts defect evolution characteristics based on an improved three-dimensional convolution and attention mechanism, and constructs a causal atlas in combination with the construction parameters to realize defect identification, risk modeling and visual analysis. The platform has the advantages of high recognition precision, high traceability and cross-work-point knowledge migration capability, and the intelligent level and engineering applicability of foundation pile detection are remarkably improved.

The invention discloses a remote sensing rotating target detection method and system based on comparative heterogeneous knowledge distillation. The method comprises the following steps: constructing a comparative heterogeneous knowledge distillation network detection framework; the Token sequence of the teacher network is converted into a two-dimensional feature map, and the two-dimensional feature map is matched with the inductive bias of the CNN of the student network to obtain transformed teacher features; converting the two-dimensional feature map of the student network into a Token sequence, and inputting the Token sequence into a teacher network for global interaction to obtain converted student features; constructing an assistant transformation model by sharing teacher network weight fusion transformation teacher features and student features; dividing positive and negative sample sets by cooperatively enhancing feature expression through space attention and channel attention and combining cosine similarity matching and a dynamic threshold division strategy; and combining a teacher network, a student network and an assistant transformation model, constructing comparative learning knowledge distillation in combination with positive and negative sample sets, realizing knowledge migration through feature distillation loss and logic distillation loss, and outputting a detection result image.

The invention provides a risk control cross-domain risk prediction method and system in combination with transfer learning, and the method comprises the steps: carrying out the domain difference measurement of a source domain and target domain risk control scene, generating a domain difference measurement matrix, building a hierarchical knowledge transfer channel based on the domain difference measurement matrix, and carrying out the prediction of the risk control cross-domain risk. And selectively migrating the source domain risk prediction model parameters, generating a target domain initialization risk prediction model, and carrying out dynamic adaptive training on the target domain initialization risk prediction model by adopting a target domain risk sample to obtain a cross-domain risk prediction model. And inputting the to-be-evaluated sample of the target domain into the cross-domain risk prediction model to generate a preliminary risk prediction score, and finally performing cross-domain calibration on the preliminary score based on the domain difference metric matrix to generate a final risk prediction result, thereby improving the accuracy of risk control cross-domain risk prediction.

The invention discloses a micro-grid user load modeling method and system based on deep transfer learning, and relates to the technical field of smart grids, and the method comprises the steps: collecting micro-grid user data, and carrying out the data preprocessing and initialization; carrying out source domain pre-training, and constructing a deep transfer learning framework; carrying out feature extraction by using an improved deep convolutional neural network; carrying out domain adaptation loss calculation, introducing a dual attention mechanism, and constructing a load prediction model; and incremental learning optimization is set, and the strategy is optimized through an improved algorithm. According to the method, technologies such as field adaptation loss, incremental learning optimization and knowledge distillation are combined, and the problems of data scarcity, poor field adaptability and over-fitting in the prior art are effectively solved. According to the method, effective knowledge migration between the source domain and the target domain can be realized through the migration learning framework, the precision and the stability of load prediction are improved, and the method has relatively high adaptability when new data and changing scenes are processed.

The invention relates to the field of robot operation and three-dimensional perception, in particular to a monocular image-based three-dimensional perception robot operation knowledge distillation method, which comprises the following steps of: establishing a strategy learning framework comprising a student model and a teacher model; constructing a strategy prediction model in the strategy learning framework; training the strategy prediction model, wherein a three-level knowledge distillation mechanism is adopted in the training process to complete knowledge migration between the teacher model and the student model; combining the three distillation losses with strategy optimization losses to form a total loss function, and performing end-to-end training on the student model until convergence to obtain a deployable monocular strategy model; the deployable monocular strategy model only retains a student model, and generates a robot operation instruction. The method has the beneficial effects that the robot under monocular RGB input has three-dimensional perception and high-precision operation capabilities while the reasoning efficiency is kept, the task success rate and generalization performance are remarkably improved, and the effectiveness and robustness of the method are verified.

The invention discloses a large spacecraft lightweight control system based on knowledge distillation, which comprises a spacecraft control knowledge distillation training system and a spacecraft control knowledge graph, and realizes lightweight of a control algorithm by optimizing a knowledge distillation loss function through a dynamic knowledge migration mechanism. According to the method, a lightweight method optimization model based on knowledge distillation is adopted, a dynamic training data set is constructed, and computing resource occupation and power consumption are reduced; the knowledge association precision is enhanced and optimized through the atlas; and meanwhile, the accuracy loss is controlled by adopting attention weighted fusion cross-task knowledge, so that efficient, real-time and low-power-consumption operation and response are realized.

The invention relates to the technical field of data privacy protection, in particular to a cross-domain agent knowledge migration and privacy barrier system, which comprises a migration request analysis and sensitive marking unit, an original migration module extraction and identification, authority control and domain exclusive elements marking unit, an operation log containing a domain label and a timestamp generation unit, and a privacy barrier unit. The dynamic privacy barrier processing unit replaces an identity label with a generalization identifier, deletes violation elements according to a target domain sovereignty rule to generate a compliance knowledge module, separates, encrypts and stores a domain label and a timestamp, performs hash processing on a log operation type, and stores the log operation type; the privacy disclosure blocking unit scans residual identity labels and undeleted permission elements through secondary verification, and inputs a compliance block into a migration channel after verification is passed, and the system realizes accurate desensitization and compliance verification of cross-domain knowledge migration, prevents privacy disclosure, and ensures cross-domain collaborative security of agents.

The invention discloses a knowledge distillation method for target detection. The knowledge distillation method comprises two major designs including a dynamic teacher-student mutual learning mechanism and interpretable feature decoupling. The RGB detector is used as a teacher guidance event detector to learn static semantic knowledge in a conventional illumination scene, and the event detector is used as a teacher guidance RGB detector to learn dynamic robust features in an unconventional illumination scene, so that dual-mode collaborative optimization is realized; and the original teacher and student feature space is decoupled into three parts of mode universality, mode specificity and mode irrelevance, and effective knowledge migration based on the mode universality feature is carried out between the two modes by constructing bidirectional distillation loss. The objective of the invention is to enable an RGB detector and an event detector to have a more accurate target recognition effect.