444 results about "Pooling" patented technology

Disclosed in the present invention is a four-network integration architecture for an unmanned swarm system. The four-network integration architecture has the capabilities of heterogeneous platform resource pooling, intelligent dynamic computing power allocation, and timely decision planning, so as to maximize the overall benefit. The present invention focuses on abstracting and integrating independent submodules to form a mesh topology of a swarm. The present invention designs a four-network integration architecture for an unmanned swarm system, which comprises a computing power network, a perception network, a decision network and a communication network as core modules. The structure aims to achieve efficient cooperation of all parts in the swarm, thereby improving the overall performance and adaptability of the system. The system integrates environmental perception, a swarm network modeling component, a knowledge base and a resource pool, providing an intelligent environmental perception strategy and a network modeling strategy for the interior of the swarm. Therefore, the perception of environments, tasks and networks by nodes can be facilitated, thereby completing establishment of intelligent networks, so as to ensure the characteristics of the stability and flexibility of networks.

The invention belongs to the technical field of electric power data security management and intelligent question answering, and particularly relates to an electric power data security policy large model question answering system and method based on relation pooling. The system comprises a power data security policy knowledge base, a language model, a question processing module, an answer generation module and a user output module. Data of the electric power data security policy knowledge base comes from an electric power data security policy file; the language model converts a natural language problem into a structured query for knowledge base retrieval; the question processing module retrieves policy terms related to the natural language question to serve as retrieval results; the answer generation module generates a final answer according to the natural language question and a retrieval result of the knowledge base; by introducing the intelligent question-answering system combining the large language model and the knowledge base, the problems of low efficiency, inaccurate interpretation, incapability of dynamically updating and the like in the existing power data security policy query and management are solved.

The invention relates to a supporting structure stress state monitoring method based on artificial intelligence, and belongs to the technical field of artificial intelligence and data processing. The method comprises the following steps: acquiring and marking strain data of a supporting structure; after abnormal values are removed, normalizing the multi-sensor data to generate a normalized strain sequence; a state monitoring model is constructed, a deep time sequence neural network architecture is adopted, and the state monitoring model comprises an input layer, a self-adaptive wavelet attention feature mapping layer, a time domain gating convolution module, a global maximum pooling layer, a dynamic feature importance reweighting layer and a full-connection classification layer; inputting a normalized data training model; optimizing a loss function through a quantile interval adaptive learning rate and a momentum updating strategy; after real-time monitoring data is processed, inputting the data into the training model according to time window slices, outputting four types of probabilities, and taking the maximum value as a prediction state; and if a plurality of continuous windows are early-warning and dangerous, triggering the terminal to give an alarm. The accuracy of monitoring the stress state of the supporting structure can be improved.

The invention provides an operational research course knowledge graph construction method based on multi-source data fusion. The method comprises the following steps: firstly, discussing logical association of courses, majors and students, collecting data such as textbooks, exercises and teaching programs by taking operational research knowledge points as a core and utilizing technologies such as OCR (Optical Character Recognition) and crawlers, and carrying out preprocessing and manual labeling; then, an improved deep learning model is adopted for entity recognition and relation extraction, BERT + BiLSTM + CRF is adopted for entity recognition, and a dynamic context pooling enhancement model is fused to improve the capture ability of a complex knowledge boundary; bERT + BiLSTM is adopted for relation extraction, a multi-head attention mechanism is combined, and hidden logical relation mining is enhanced. And finally, constructing a multi-level knowledge network which takes knowledge points as nodes and logic relations as edges, and embedding the multi-level knowledge network into a Neo4j graph database for visualization. The map can optimize a teaching path, provides personalized learning recommendation, and is widely applied to the fields of wisdom education, knowledge retrieval and the like.

The invention discloses a hybrid expert and KAN-based cyclic attention network time sequence prediction method. The method comprises the following steps: S100, inputting time sequence data needing to be predicted; s200, constructing a graph structure by using an attention mechanism, learning basic correlation characteristics among variables of the input time sequence data through an adaptive and learnable graph convolutional network, and then performing global averaging and maximum pooling on the basic correlation characteristics along a time dimension to obtain complementary time domain statistical information, so as to provide effective time-space correlation characteristics for the follow-up process; s300, after feature learning is completed, collaborative modeling of the KAN and an attention mechanism is brought into full play, rapid and efficient time sequence modeling is carried out on data by adopting a cyclic attention network embedded based on the KAN, and a foundation is laid for subsequent time sequence prediction; and S400, establishing a hybrid KAN expert-based time sequence prediction network, and adaptively fusing differentiation prediction results by a gating mechanism. The time sequence prediction method is designed from the three aspects of feature learning, time sequence modeling and time sequence prediction.

The invention discloses a hyper-converged server resource pooling method and system, and belongs to the technical field of resource scheduling, and the method comprises the steps: collecting spatial information, generating a multi-dimensional resource topological graph, abstracting edge node and core node resources into virtual units with position labels, constructing a virtual resource pool, and generating a three-dimensional metadata table; constructing an independent double-queue architecture, configuring a token bucket, triggering a queue clearing mechanism based on a control period, and performing micro-batch merging on edge node short transactions; binding adjacent virtual units by taking the physical position of the equipment as a fragmentation primary key, monitoring cross-virtual unit access traffic, migrating a high-frequency data copy and redirecting a write request, and adjusting fragmentation granularity according to data relevance; the virtual unit closest to the equipment group is selected as a main node in the data fragments, write operations are combined, low-delay paths are selected for synchronization, an asynchronous confirmation mechanism is adopted to respond to edge nodes, the local resource hit rate and the task processing efficiency are improved, and the real-time performance and reliability of industrial control are guaranteed.

The invention discloses an intelligent computing power integration service management method and platform based on cloud side-end cooperation, and relates to the technical field of computing power integration management, and the method comprises the steps: sensing the computing power resource state of a side-end cooperation port and terminal equipment in real time at a cloud controller, and building a resource topological graph; a dynamic task demand is introduced, and a computing power scheduling vector is generated; carrying out lightweight segmentation on the cloud training model, and determining adjacent edge nodes under hierarchical limitation to form a regional elastic cluster; and deploying a digital twin simulation engine rehearsal computing power distribution scene, establishing a heterogeneous resource pooling mechanism, and carrying out computing power integration service management. The technical problems of low management efficiency and insufficient utilization rate of heterogeneous computing power resources in the prior art are solved, and the technical effects of realizing efficient management of intelligent computing power integration services and improving the utilization rate of the heterogeneous computing power resources are achieved.

The invention provides a satellite resource dynamic allocation method under a cloud-native hybrid cloud architecture, and the method comprises the steps: packaging satellite load resources and cloud resources through a containerization technology, so as to form a unified virtual resource pool; constructing a deep learning model, predicting resource demands of each beam coverage area in a future time period based on satellite task historical data and real-time demands, and generating a resource matching scheme; a reinforcement learning algorithm is adopted to dynamically adjust the beam radius, channel allocation and time slot scheduling so as to match the real-time load change of cloud resources; according to the method, a satellite and cloud digital twin model is constructed, a scheduling strategy is simulated and predicted based on a resource matching scheme through the satellite and cloud digital twin model, a resource state is mirrored in real time, and a strategy library is updated according to simulation feedback data of the satellite and cloud digital twin model, so that multi-satellite task automatic recombination is realized. The invention further provides a satellite resource dynamic allocation system under the cloud and native hybrid cloud architecture and a computer storage medium. According to the method, three-dimensional cooperation of dynamic resource pooling, intelligent prediction and elastic scheduling is realized, and the problem that satellite task response time, resource utilization rate and safety cannot be achieved at the same time can be effectively solved.

The invention discloses a computer network experiment environment dynamic construction method based on virtual simulation, which belongs to the field of computer network experiment teaching and virtual simulation technology application, and comprises the following steps: analyzing experiment scene description to generate a modular construction instruction; creating and initializing a virtual machine instance and a basic network; generating a required virtual network device and constructing a corresponding virtual connection; configuration parameters, service scripts and security policies are comprehensively applied to the virtual machine and the network equipment; and integrally outputting the experimental environment to a user interaction interface. According to the method, the demand-driven instruction arrangement, virtual resource pooling scheduling and multi-layer automatic configuration technologies are adopted, so that a diversified and deeply interactive virtual computer network experiment environment can be quickly and flexibly constructed according to specific experiment demands of a user; and the resource utilization rate, the scene construction efficiency and the flexibility of the teaching mode of network experiment teaching are obviously improved.

The invention provides a multi-receptive-field network abnormal flow detection method and system based on endogenous security attributes, and relates to the technical field of network security and abnormal flow intelligent detection. The method comprises the following steps: firstly, performing multi-scale flow representation, preprocessing and data enhancement on network flow data to obtain enhanced input flow data; local features are extracted through basic convolution, and local and global fusion features are obtained based on a double-branch network comprising a multi-receptive field convolution branch and a Mama-self-attention branch; deep fusion representation is formed through multi-round feature extraction and tensor fusion, and finally binary classification and fine-grained classification results are output through global pooling and a linear classification layer. According to the method, high-precision, high-robustness and high-real-time detection of the abnormal traffic of the complex network is realized under low calculation overhead.

The invention provides a building identification method and system based on three-dimensional point cloud, and particularly relates to the technical field of computer vision and three-dimensional target identification, and the method comprises the steps: carrying out the undersampling, oversampling and data enhancement preprocessing of inputted building roof point cloud data, and carrying out the T-net network space alignment to output the aligned data. Then, an NEWPCT model is obtained by improving a PCT model, aligned data are input into the NEWPCT model, a point cloud feature matrix is generated through a linear coding layer, query, key and value matrixes are obtained through linear transformation, multi-head attention output is calculated by introducing an offset matrix, intermediate correlation features are obtained after splicing and fusion, and a global feature vector is generated through global maximum pooling; and finally, inputting the vector into a classifier, and outputting a building roof type, and the method solves the technical problems of geometric transformation sensitivity and local feature loss while improving the precision and robustness of three-dimensional point cloud building identification, thereby effectively improving the identification precision and robustness.

Dynamic provisioning of resources in a datacenter improves the utilization efficiency of compute, memory, storage, and network resources, while maintaining flexibility to meet changing demands. Embodiments herein disclose protocol-aware provisioning of resources over Compute Express Link (CXL) fabrics, enabling multi-protocol pooling and disaggregation of resources, including memory and workload-specific accelerators such as GPUs and DSAs. In some embodiments, a Resource Provisioning Unit (RPU) facilitates intent-based protocol translations and mappings between address spaces, potentially enabling the creation of large-scale compute-memory fabrics that may utilize both coherent and non-coherent Non-Transparent Bridging (NTB) between multiple protocols in a single system, serving as the underlying infrastructure for executing workloads such as Large-Language Models (LLMs) and Deep Learning Recommendation Models (DLRMs). Some embodiments also optimize low-latency communication between processes running on different nodes by enabling host-to-host memory provisioning for libraries such as OpenMP, Pthreads, or CUDA, which can utilize shared memory.

The invention discloses a scheduling method for heterogeneous GPU resource pooling and dynamic computing power preemption, and relates to the technical field of data process.The method includes the steps that priority coefficient evaluation is conducted on a computing task, a computing power resource value and a computing priority required by the computing task are obtained, and the computing power resource value and the computing priority required by the computing task are calculated according to the computing power resource value required by the computing task; the method comprises the following steps: configuring driving programs of different heterogeneous resources, performing resource abstraction on virtual heterogeneous resources to generate a tree-shaped resource pool, and performing hierarchical matching on corresponding resource types from a root resource pool of the tree-shaped resource pool according to a computing power resource value required by a computing task and a computing priority; meanwhile, task related information can be analyzed according to the calculation task, the trend of the calculation task can be predicted, the estimated calculation task expansion amount is obtained, the estimated calculation power resource value needed in the next task requirement is calculated through the calculation task expansion amount, the resource expansion trend is evaluated in combination with the calculation power resource value needed by the calculation task, and the calculation efficiency is improved. And the tree-shaped resource pool is re-divided according to the resource expansion trend.

The invention provides an intelligent machine tool cutter wear state recognition and machining parameter adjustment method and system, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: collecting the working condition data of a machine tool machining process, carrying out the sliding window segmentation, denoising and normalization processing, extracting a time sequence feature sequence through a bidirectional gating circulation unit, and carrying out the recognition of a machining parameter; the method comprises the following steps: acquiring an intrinsic mode component by combining Hilbert-Huang transform decomposition, extracting a frequency domain feature sequence by utilizing four-layer spatial pyramid pooling, determining a fusion weight based on mutual information entropy to obtain a tool wear state feature vector, and inputting the feature vector into a pre-training extreme learning machine to predict the wear loss and the residual life. And determining an initial adjustment scheme in combination with observation sharing information of a parallel agent structure, predicting a processing quality score through a capsule network and feeding back the score as a reward signal, and obtaining an optimization correction strategy for adjusting working parameters of a machine tool.

The invention discloses a VAGCN-based complex industrial process operation state evaluation method. The method comprises the following steps: collecting process data and carrying out standardization processing; performing data division on the data by using a sliding window to obtain a time sequence; the method comprises the following steps: converting time sequence data into cross-time-space variable interaction graph structure data through a variable interaction graph structure, and then capturing variable interaction characteristics and local space-time dependency in each time window by using a moving window; time pooling is used, advanced features of variable interaction are extracted and then input into the operation state evaluation model, posterior probabilities of the online data belonging to different operation state evaluation grades are obtained, and a final evaluation result is a state grade corresponding to the maximum posterior probability at the current moment; and performing similarity analysis on the variable interaction graph structure in the non-optimal state and the optimality graph structure in the optimal state so as to evaluate the variable dynamic offset degree in the non-optimal state. According to the method, the interaction among the variables at different time points can be captured, and more accurate process operation state evaluation can be realized.

The invention provides a hit probability prediction method and device, computer equipment and a storage medium, and the method comprises the steps: replacing a random number sequence in a white shark optimization algorithm WSO with a chaotic mapping sequence determined by a chaotic mapping function, and carrying out the population optimization of the white shark optimization algorithm WSO, and obtaining an improved white shark optimization algorithm CWSO; a KAN layer and a fuzzy pooling layer are introduced into a convolutional neural network CNN, and a hit probability prediction model of the KCNN underwater launching device is constructed; obtaining influence factor training data, and performing parameter optimization on the KCNN model through an improved white shark optimization algorithm CWSO by adopting the influence factor training data to obtain a CWSO-KCNN model; and obtaining influence factor target data, and inputting the influence factor target data into the CWSO-KCNN model to obtain a hit probability prediction value of the underwater launching device. Therefore, the CWSO is obtained by improving the optimization algorithm, and the CWSO is adopted to perform parameter optimization on the KCNN model to obtain the CWSO-KCNN model, so that the prediction precision of the hit probability is effectively improved.

The invention relates to the technical field of action recognition, in particular to a skeleton action recognition method based on a space-time dependency enhanced network, which comprises the following steps: acquiring a graph containing skeleton action articulation points; constructing an AMGC-IBM-CNN network: establishing a space-time diagram by taking joints as nodes and skeletons as edges, performing global feature vector and local feature vector extraction on the space-time diagram by using the AMGC network, inputting the global feature vector into an IBM module, then inputting the global feature vector into the CNN network, performing addition operation on the output feature vector of the CNN network and the local feature vector, and finally obtaining the AMGC-IBM-CNN network. And performing global average pooling, and outputting an action category through a classifier after FC. According to the method, the problems that time and space convolution layers are separated in a traditional model, cross-space-time information exchange is obstructed, and the cross-space-time dependency relationship of the joint points is difficult to obtain are solved.

The invention discloses a feature pyramid time sequence prediction method based on cross attention. The method comprises the steps of performing normalization preprocessing on time sequence data; carrying out feature extraction on the time series data by using a convolutional neural network, and carrying out global average pooling operation after each convolution; performing multi-stage feature extraction on the extracted features, extracting trend features by using average pooling, taking the output of the previous step as the input of the next average pooling, letting x1 = x, performing average pooling operation on x1 to obtain x2, repeating the operation until x4 is obtained, and performing processing construction by using a feature pyramid module to obtain a multi-scale time sequence feature expression X; a plurality of full-connection layer prediction target sequences Y = [y1, y2, y3, y4] are introduced, the output yi of the current layer and the output yi-1 of the previous layer are spliced, and the full-connection layer is used for processing so that the output dimension of the full-connection layer can be matched with yi; and carrying out prediction by using a Transform based on cross attention. The method can effectively capture the long-distance dependency relationship of data, and improves the prediction accuracy.

The invention relates to a traffic detection method based on a spiking nerve-bidirectional LSTM network, and the method comprises the steps: introducing a time sequence modeling module, a spiking neural network module and a self-attention mechanism module, constructing a to-be-trained network, carrying out the training of each sample traffic, and obtaining a traffic anomaly detection model, the dynamic characteristic modeling capability of the spiking neural network is combined with the time sequence dependence characteristic capturing capability of the bidirectional long-short-term memory network, the time sequence characteristics and behavior patterns of the encrypted traffic can be extracted more accurately, parameters are optimized through global average pooling and a full-connection layer in the network, the classification performance and generalization capability can be remarkably improved, and the classification efficiency is improved. According to the invention, a corresponding system is designed at the same time, modular design is carried out for a network structure, modular application of each link of the detection method is realized, and the detection efficiency of abnormal traffic in practical application is further improved.

The invention discloses a punching machine bearing fault diagnosis method and equipment. The method comprises the following steps: establishing a diagnosis mechanism fusing time-frequency domain feature extraction and multi-branch depth feature modeling; original vibration signals are respectively converted into GADF images to capture time sequence dependence, CWT is adopted to extract transient frequency change, STFT is utilized to obtain frequency spectrum characteristics under a stable working condition, and joint input of a multi-view time-frequency graph is realized. On a model structure, a Swin Transform branch is designed for local space detail modeling, a global perception branch is constructed by combining a CNN module and a GAM module, and multi-category fault classification is completed through self-adaptive pooling and a full connection layer on fusion output. User-defined data loading and a standardized process guarantee the consistency of training data, multi-core maximum mean difference is introduced for feature distribution alignment, and the migration ability of the model under different working conditions and the decoupling recognition ability of composite faults are improved.

A resource pooling system is provided. The resource pooling system comprises a plurality of resource pools, each resource pool comprises a plurality of resource modules used for processing data or a plurality of resource modules used for storing data, and each resource module comprises an electronic integrated circuit chip with a PCIe physical interface and at least one optical module, the PCIe physical interface of the electronic integrated circuit chip is electrically connected with the electric port of the at least one optical module, and the optical port of the at least one optical module is used as the optical port of the resource module; and a switch having an optical port interconnected with the optical port of each resource module in the plurality of resource pools, the switch being configured to select at least a portion of resource modules from the plurality of resource pools and to transmit signals with the at least a portion of resource modules. The at least one optical module converts a first electrical signal from the PCIe physical interface of the electronic integrated circuit chip into a first optical signal and provides the first optical signal to the switch. And the at least one optical module converts a second optical signal from the switch into a second electric signal, and provides the second electric signal to the corresponding electronic integrated circuit chip through the PCIe physical interface.

The invention discloses a multi-source heterogeneous time series data compression and motor fault prediction method and system, and the compression method achieves the intelligent compression and feature enhancement of time series data through the cooperation of multi-scale feature extraction, SE weighted fusion, mixed pooling and aggregator collapse. According to the architecture, reasonable reduction of the sequence length and effective improvement of the feature depth can be completed at the same time, on the premise that key fault features are reserved, the technical problem of multi-source heterogeneous sensor data fusion in an industrial scene is solved, and the limitation of serious information loss of a traditional dimension reduction method is overcome.

The invention relates to a pooling and up-sampling fusion CAM method based on information entropy and an attention mechanism. The method comprises the steps of image preprocessing, feature extraction, information entropy calculation, attention weight matrix design, weighted feature graph and pooling, up-sampling and residual connection, category weight assignment, CAM generation and the like. By introducing the information entropy theory, the complexity and importance of information in the feature map can be accurately evaluated, attention weight design is guided, key information is focused, redundancy is suppressed, and the capability of processing complex images by the model is remarkably improved. And in combination with an attention mechanism, feature representation is more effective and accurate. Through pooling and up-sampling technology fusion, the size of a feature map is flexibly adjusted, key features are reserved, and subsequent tasks are facilitated. Through the application of global average pooling and a pre-training classifier, a class activation mapping graph is generated, the performance and accuracy of a computer vision task are improved, and the explanatory performance of a model on picture processing is improved.

The invention discloses a dynamic space-time diagram flow prediction method and system based on course learning, and relates to the technical field of supply chain logistics data analysis, and the method comprises the steps: building a space-time matrix based on historical multi-source data, generating a dynamic adjacent matrix through learning, and carrying out the smooth fusion through combining a static diagram, and forming a dynamic diagram structure. And then space and time features are respectively extracted by using a graph convolutional network and a gating loop unit, and deep interaction and fusion are realized through a bidirectional cross attention mechanism. A multi-dimensional difficulty estimator is innovatively introduced, the prediction difficulty of each training sample is quantified from three dimensions of space, time and time-space coupling, the selection sequence of the training samples is dynamically adjusted based on an adaptive course scheduler, and progressive learning is realized. And finally, feature representation is obtained through global pooling, and multi-step traffic prediction is realized by adopting a parallel independent decoder, so that error accumulation is avoided. According to the invention, prediction precision and model training efficiency in a complex supply chain logistics scene are effectively improved.

The invention relates to the technical field of language models, in particular to a double-retrieval model generated based on extension questions.The double-retrieval model comprises the following steps that S1, query standardization is conducted on query of a user through a 5W1H framework; s2, a sentence converter encodes each standard and extended query as an embedding, and the embedding is combined into a single group embedding by using mean pooling. According to the double-retrieval model generated based on the extended questions, the retrieval precision of question answers based on LLM (Large Language Model) is improved and the illusion is reduced through the HIYO-Encoder double-retrieval model, and the HIYO-Encoder is combined with an element to overcome the limitation of a traditional RAG model, namely, double-retrieval design: the retrieval between direct search and extended search is balanced, and the retrieval efficiency is improved. In one embodiment, the method comprises the following steps of: establishing a database using context and query embedding so as to enhance response relevance and reduce hallusion, enriching the retrieval through 5W1H sub-problems so as to capture additional semantic depth in a user search, constructing the database using context and query embedding, and thus allowing multi-dimensional retrieval alignment to obtain maximum accuracy.

The invention discloses a collaborative recommendation method and device fusing lightweight relation path completion and dynamic negative sampling, equipment and a medium, and relates to the technical field of recommendation. The collaborative recommendation method comprises the following steps: acquiring historical interaction data of a user, and constructing an interaction relationship knowledge graph; vectorizing the interactive relationship knowledge graph, and then dynamically constructing a multi-hop relationship path based on a lightweight relationship path completion mechanism to obtain a path completion representation. According to the lightweight relation path completion mechanism, a path order L belongs to {1, 2, 3} is set according to the sparse degree of a user-article pair, and a first-order, second-order or third-order reasoning path is constructed. And then performing intelligent feature fusion on the constructed path through a triple pooling strategy. And projecting the embedded representation of the entity to the corresponding relation subspace through orthogonal projection based on the path completion representation. And calculating a recommendation score according to the embedded representation after projection, and obtaining an article recommendation list.

The invention relates to the field of offshore platform pipeline leakage identification, and discloses a pipeline leakage identification method based on an improved convolutional neural network, which comprises the following steps of: firstly, constructing a pipeline leakage model in a laboratory, collecting leakage signals under various working conditions, acquiring real background noise at positions of 19m and 29m of a ''lychee 3-1'' offshore platform, and acquiring a pipeline leakage model; the method comprises the following steps of: acquiring a leakage signal of a laboratory, injecting real background noise into the leakage signal of the laboratory to simulate a real working environment, and finally, improving a traditional one-dimensional convolutional neural network with the core of introducing residual connection to increase the training stability, introducing maximum pooling and average pooling to reduce the size of a feature map and reduce the calculation amount, and using a Dropout regularization technology to prevent model overfitting. According to the method, the network weight is adjusted by using an adaptive moment estimation optimization algorithm, and then the convolutional neural network structure is subjected to adaptive design, so that the method realizes high-accuracy pipeline leakage identification and has good robustness, and the problems that a traditional machine learning method seriously depends on manual intervention and the identification process is complex are solved.

The invention belongs to the technical field of industrial risk identification, and provides an industrial risk identification method based on a hotspot clustering algorithm and an industrial large model agent, which combines the clustering algorithm with a large model, discovers useful information under mass data, and accurately identifies industrial risks. The method comprises the following steps: firstly, realizing vectorization of text semantics through a hotspot clustering algorithm, position weighted average pooling and a bias tensor contrast fine tuning method, and finding out a hotspot topic from massive industrial text data through connected graph clustering and split optimization; and secondly, based on the semantic understanding ability of the large model, constructing an industrial large model agent, and judging the hot topics through the industrial large model agent, including sentiment analysis and industrial judgment, so as to screen out the hot topics related to industrial risks. And thirdly, summarizing the industrial development suggestions according to the summarized industrial risk hot topics by applying the summarizing and summarizing capability of the large model.

The invention provides a link prediction method and system based on a double-branch fusion network, and belongs to the technical field of link prediction. The core of the method comprises the following steps: 1) a KAN network is adopted by a graph attention branch to replace a traditional edge weight, and the fitting ability to a complex relationship is enhanced through a learnable nonlinear basis function; and 2) fusing attention branches and connecting SE and CAM channel attention modules in parallel, capturing a long-term dependency relationship through global average pooling, and improving the sensitivity to high-frequency emergence association in combination with double pooling so as to realize local and global feature complementation. And after the two branch features are fused, calculating a node interaction score through a decoder, and outputting a link existence probability. Experiments show that the AP and AUC indexes of the method on data sets such as Yeast are superior to those of a mainstream method. The system executes the processes through a memory and a processor, is suitable for scenes such as social networks and recommendation systems, and has remarkable application value.

The invention relates to the technical field of power grids, and provides a multi-modal feature-based fault diagnosis method and a multi-modal feature-based fault diagnosis system for a network construction type energy storage system, which are used for sequentially carrying out normalization, multi-scale convolution, dynamic weighting of an attention mechanism, spatial-temporal feature extraction of a bidirectional long-short-term memory network and weighted pooling of the attention mechanism on acquired multi-modal data. According to the multi-modal-feature-based fault diagnosis method for the network-building type energy storage system, through multi-scale convolution, attention mechanism dynamic weighting, bidirectional long-short-term memory network spatial-temporal feature extraction and attention mechanism weighted pooling, each modal feature can be effectively extracted, the multi-layer network depth extension requirement of deep learning is avoided, and the fault diagnosis efficiency is improved. Model parameter quantity can be effectively reduced, dependence on cloud computing is reduced, and the method can be conveniently deployed on edge equipment; and transient faults and progressive faults in the multi-modal features can be effectively identified, and the fault diagnosis precision is guaranteed.