12results about How to "Efficient mapping" patented technology

The invention relates to the technical field of intelligent building management, in particular to an intelligent building operation and maintenance management system and method based on a BIM platform. The method comprises the following steps: performing equipment connection topology network construction according to acquired target BIM building model data, and generating equipment physical connection topology data; performing automatic logic conflict elimination on the equipment physical connection topological data to generate equipment connection topological data; performing fault influence link analysis on the equipment connection topological data to generate fault propagation link data; performing fault severity evaluation on the fault propagation link data to generate equipment fault severity data; and performing intelligent operation and maintenance path planning according to the equipment fault severity data to obtain intelligent equipment operation and maintenance path data. Through fine division of the operation and maintenance equipment management space and analysis of the equipment fault propagation link, intelligent scheduling of the fault operation and maintenance task is realized, and the operation and maintenance efficiency and the resource allocation precision are remarkably improved.

The invention discloses a hypersonic flight vehicle adaptive attitude control method based on near-end strategy optimization, and belongs to the technical field of hypersonic flight vehicle control, and the method comprises the steps: building an air-breathing hypersonic flight vehicle longitudinal dynamic model considering power; performing reinforcement learning training on the obtained environment model by using a PPO algorithm to obtain an optimized control strategy; selecting a proper state representation and action space, and designing a strategy network and a value network for the processed model, so that an original complex attitude control problem is converted into a reinforcement learning problem which can be effectively learned; and training the reinforcement learning model by using an improved PPO algorithm to obtain a final control instruction. According to the method, the model is trained by using the PPO algorithm, so that the defects of complex controller design, strict requirement on model precision and the like of a traditional control method can be effectively overcome. A simulation experiment verifies that pitch angle tracking can be effectively realized, and the stability of an execution mechanism is guaranteed.

The invention discloses a multi-user revocable and searchable encryption method based on a block chain, and relates to the technical field of block chains and searchable encryption, and the method comprises a system establishment stage, a user management stage, an updating stage and a searching stage. And by adopting the block chain technology and IPFS decentralized storage, the tampering resistance of the system information is ensured, and the privacy leakage risk is reduced. By introducing the homomorphic XOR function, the user identifier is packaged and then verified, so that a multi-user application scene is realized, the interaction efficiency of the system is improved, and the safety and reliability under multiple users are also ensured; by introducing a Bloom filter and a pseudo-random puncture function, the operability of a file identifier is improved, and a safe and efficient key generation and transmission mechanism is cooperatively designed; and aiming at file deletion and addition of a revocation mechanism, a secondary search mechanism is designed emphatically at the same time, so that the updating and search overhead is reduced, and the overall performance of the system is improved.

The invention discloses a rapid magnetic resonance imaging reconstruction and segmentation method and system, a medium and a product, and relates to the technical field of image processing. The method comprises the following steps: decomposing original three-dimensional magnetic resonance data into a plurality of independent two-dimensional magnetic resonance data slices along a slice sequence; image reconstruction is carried out on the two-dimensional magnetic resonance data slices through a pre-trained forward generator in the frequency domain Schrodinger bridge diffusion model so as to generate a two-dimensional magnetic resonance image, and the forward generator integrates a Fourier convolution module and is used for carrying out frequency domain transformation and feature enhancement processing on feature mapping in the image reconstruction process; inputting each two-dimensional magnetic resonance image into a pre-trained segmentation model in sequence, performing segmentation of a target region and a preset dangerous organ, and generating a corresponding two-dimensional segmentation mask; all the two-dimensional segmentation masks are rearranged and stacked according to the slicing sequence, and a three-dimensional segmentation result is generated through three-dimensional fusion operation. By implementing the technical scheme, magnetic resonance imaging reconstruction and segmentation can be quickly and accurately carried out.

The invention discloses a greenhouse digital twinning and equipment operation and maintenance system based on a knowledge graph and data driving, which comprises a physical greenhouse, a greenhouse digital twinning platform and a greenhouse knowledge graph, and is characterized in that the physical greenhouse comprises an environment information acquisition system, a video acquisition system and an equipment state recognition model which are deployed in the physical greenhouse; the greenhouse digital twin platform is used for deploying the control platform, the virtual greenhouse scene model and the fault judgment module; the greenhouse knowledge graph performs information extraction on data acquired by a physical greenhouse, and converts acquired greenhouse environment information, greenhouse structure information, equipment association information and equipment state information into structured data information so as to facilitate identification and processing of a greenhouse digital twin platform. According to the invention, the state operation of the greenhouse equipment can be analyzed, and the fault diagnosis and processing efficiency of the greenhouse equipment can be improved, so that the overall management level of the greenhouse and the agricultural production efficiency are improved.

The present invention discloses a personalized method for federated learning based on contrastive learning, which achieves personalization by weighing the global model trained on the entire data set and the local model trained on the local subset. The local update is corrected by the consistency loss of the representation learned by the current local model and the representation learned by the global model, thereby achieving personalization of federated learning. The representation of the global model, the representation of the model obtained by local data training, and the representation of the local model trained by the current model are calculated simultaneously, and then the distance between the three representations is standardized through personalized parameters, that is, contrastive learning is achieved at the model level, so as to correct the global model to adapt to tasks on different clients. The present invention can adapt to different tasks of the client and meet the requirements of personalized customization of federated learning.

The application provides a unified systolic array computing unit for ANN and SNN, comprising a shift-add computing processing unit and a systolic array formed by arrayed deployment of the shift-add computing processing unit; an execution of artificial neural network operation or pulse neural network operation is switched through a configuration mode selection signal terminal; in the artificial neural network mode, multiplication operation is unfolded in the time dimension, and a shift register and an adder constitute a time division multiplexing operation sequence to complete multiplication and accumulation operation; in the pulse neural network mode, a weighting accumulation is directly completed through multiplexing of an addition link, and a neuron time step dependent chain is decoupled through a soft reset mechanism to realize cross-time step weight multiplexing; control signals and data are propagated in the same direction in the systolic array, which is used for realizing control logic array level multiplexing, and fixed data flow is adopted for the output, so that partial sums are preferentially resident in the array interior; the working frequency can be improved, the bandwidth and power consumption can be reduced, and the area efficiency and timing convergence can be improved.

The application discloses a five-dimensional seismic data interpolation method and system based on coordinates, constructs a point-by-point seismic data interpolation model based on a NeRF theory, modifies an MLP framework by combining an additional convolution layer on the basis of the point-by-point interpolation model, constructs a profile-by-profile seismic data interpolation model, introduces kernel norm regularization to construct an objective function, reads original five-dimensional seismic data D obs and inputs the five-dimensional seismic data with missing traces into the network to realize reconstruction of the five-dimensional seismic data. The application eliminates the need for additional labeled data, utilizes unique characteristics of seismic data, enables a convolution network decoder to output data profile by profile, can significantly improve data processing efficiency by 40 times, and increases kernel norm regularization in the objective function, so that the noise resistance and robustness of the model can be effectively improved.

This invention relates to the fields of biomedical imaging and spatial metabolomics, specifically to a method and system for registering spatial metabolomics images with HE-stained images. The method includes the following steps: acquiring two adjacent frozen sections of the same tissue sample; performing image preprocessing using the frozen sections; obtaining the extraction and matching results of key point features in the images; performing rigid image registration and obtaining a rigid registration result; performing non-rigid image registration and obtaining a non-rigid registration result; and obtaining the spatial location information of the spatial metabolic imaging using the non-rigid registration result. This invention, by combining advanced image processing technology and machine learning algorithms, automatically registers metabolic imaging images with HE-stained images, significantly improving registration accuracy and efficiency. It effectively solves the problems of large errors, low efficiency, and strong operational dependence in existing manual registration methods, meeting the needs of high-throughput, high-precision spatial metabolomics analysis and supporting large-scale data processing.

Provided are an LDPC decoding method, apparatus, device, storage medium and program product, the LDPC decoding method comprising: determining a first scaling factor according to a first SINR of a communication link transmission symbol, the first scaling factor being used for processing a first log-likelihood ratio LLR, the first LLR being a floating point LLR; performing fixed-point quantization processing on the first LLR according to the first scaling factor to obtain a second LLR; inputting the second LLR into a decoder, and decoding the second LLR by using an LDPC decoding algorithm according to a first sequence to obtain a decoded bit message output by the decoder; the decoder comprises multiple layers of decoding structures arranged in sequence; the first sequence is an inverse sequence of the arrangement sequence of the multiple layers of decoding structures. According to the invention, through a layered LDPC decoding algorithm combining fixed-point quantization and inverted processing, the decoding performance is improved, and the complexity of the LDPC decoding algorithm is reduced.

This application discloses a discrete simulation method for process flow, electronic equipment, storage medium, and products, relating to the field of industrial manufacturing technology. This application constructs workpiece entities and process information components through a physical component system, achieving efficient mapping between data and simulation tokens. Through Petri net state space decomposition, key process states are mapped to locations, and actions are abstracted into transitions, forming a logical topology and decoupling process states from control flow. Combining equipment constraints, general resources, and dynamic and fixed-time components, transition execution is divided into four standard types, and asynchronous event simulation is driven by standardized lifecycle templates, achieving accurate workpiece state updates and rational resource scheduling under high concurrency. This application can provide real-time response, process flow analysis, and bottleneck identification in large-scale simulations, providing efficient and flexible technical support for process optimization and digital twin systems.

The present invention discloses a block-type KV storage method and system based on a configurable MMU, and relates to the technical field of data storage. The method comprises: selecting and configuring the NSID type required in the MMU, determining the corresponding section size and Hash type; determining the size of the Hash table according to the Hash type, and calculating the number of sections; allocating a pointer to each section, and using a memory block to store pointers corresponding to different sections; submitting all parameters through the MMU configuration interface, and the hardware automatically manages the mapping relationship between the Hash table and the physical address space according to the configured parameters, and dynamically adjusts and optimizes. The present invention realizes flexible management of the physical address space while improving the system read and write performance by dynamically configuring and optimizing the NSID and its corresponding section.