28 results about "Domain space" patented technology

The invention discloses a traffic state prediction method and device based on surface domain spatial semantics, and belongs to the field of intelligent traffic and space-time big data analysis. Comprising the steps of fusing traffic flow, time embedding and remote sensing semantics to obtain uniform node features; a road short-distance graph is constructed according to the actual distance between the sensors, a semantic long-distance graph is constructed according to the functional area proportion similarity, and a global static adjacency matrix is subjected to weighted synthesis; a dynamic adjacency matrix updated along with time is generated through a self-attention mechanism, and multi-order diffusion and time localization are combined; performing multi-order graph convolution by using the static and dynamic adjacency matrixes to capture spatial dependence; extracting a short-term change, mining a long-term period, and capturing time dependence; and finally, dynamically balancing the contribution of space and time dependence through a space-time decoupling module, and outputting a prediction result. According to the method, the functional area difference is described through the surface domain space semantics, and the prediction precision and adaptability in the non-stable traffic scene are improved by combining static and dynamic graph modeling and layered time modeling.

The invention relates to a space domain space-time grid chart generation method, system and device, a medium and a program product. The method comprises the steps that the element type, size information and speed information of each space domain element in a target space domain are acquired; according to the speed information and the element type of each airspace element, determining the size of the airspace element in the time dimension and the airspace occupation duration; according to the size information of each spatial domain element, determining a geometric model corresponding to the spatial domain element and the sizes of the geometric model in three dimensions of latitude, longitude and height; generating a space-time grid corresponding to each spatial domain element according to the size of each spatial domain element in each dimension, the corresponding geometric model and the spatial domain occupation duration; and combining the space-time grids corresponding to all the spatial domain elements to obtain a spatial domain space-time grid chart. According to the method, the resolution capability of the airspace graph in the time dimension and the timeliness of data expression are improved, the problem of excessive coverage of full-path space occupied in the whole time period in a static modeling mode is avoided, and the expression precision of the low-altitude airspace graph is effectively improved.

An access point computes, for user devices in each group of a plurality of groups of user devices, a plurality of start times of future enhanced data privacy (EDP) epochs during which identifiers from the user devices in each group are to be rotated. Based on the plurality of start times, it is determined that transitory periods will occur at a same time for at least a threshold number of groups of the plurality of groups of user devices. The AP transmits a message to user devices in at least one group of the at least a threshold number of groups instructing the user devices to perform one or more actions to prevent the transitory periods from occurring at the same time.

The invention discloses a cross-domain multi-modal dynamic reasoning and generating method and system for space sensing equipment linkage, a terminal and a storage medium, and the method comprises the steps: carrying out the weighted fusion and space-time alignment of multi-source heterogeneous equipment sensing data, and forming a cross-domain space sensing data flow with a unified reference; based on real-time spatial topology and business constraints, dynamically dividing semantic collaboration areas and establishing visual mapping; for each region, fusing spatial semantics, text and visual information, and generating a region cooperative control strategy; rendering the visual content in parallel according to the mapping relation and synchronizing the equipment state; and outputting a result through area-level quality reflection evaluation, if all the data reach the standard, carrying out protocol adaptation and linkage output, otherwise, starting a local regeneration protocol for an area which does not reach the standard, re-calibrating data, updating a strategy and rendering. According to the invention, multi-device collaborative millisecond response, cross-protocol non-stop adaptation and anomaly localization repair are realized.

This specification provides a method and apparatus for generating multiplicative quintuples. Multiple parties engage in a first data interaction based on secure multi-party computation, enabling each party to obtain a first secret share of the triples within a specified domain space. Next, through a second data interaction based on secure multi-party computation, for each element in the triples, based on the first secret share held by each party, samples are taken from multiple equivalence classes within the specified domain space. This results in each party obtaining an adopted secret share, which serves as a second secret share for the remaining elements in the quintuple to be generated. The second secret share and the first secret share constitute the secret share of the quintuple to be generated.

The invention relates to a remote sensing image change detection method and device based on Mama region-space-semantic channel modeling, and the method comprises the steps: inputting an obtained remote sensing image data set into a constructed Mama-based region perception, dual-domain space and semantic channel modeling network (S3Mama) for training, and obtaining and storing the trained S3Mama; and inputting a remote sensing image to be processed, and performing prediction through the trained S3Mama to obtain a dual-temporal change prediction map. According to the method, the precision and the performance of remote sensing image change detection are remarkably improved through the design of coupling of triple collaborative modeling mechanisms.

The application provides a building group energy consumption prediction method and system based on space-time graph convolution and adversarial domain adaptation, comprising: obtaining source domain related data and target domain related data, preprocessing to obtain initial input data, etc.; constructing a space-time graph convolution network model and pre-training to obtain a pre-trained space-time graph convolution network model, splitting the model into a space-time feature extractor and a predictor; performing weight initialization and adversarial training on the target domain space-time feature extractor and the target domain predictor to obtain a trained target domain space-time feature extractor and a trained target domain predictor; inputting a target domain test set into the trained target domain space-time feature extractor and the trained target domain predictor to obtain a target domain regional building group energy consumption prediction result; and the application captures the spatial dependence relationship between buildings based on graph convolution and graph attention mechanism, adopts a transfer learning strategy to transfer source domain prediction related knowledge to a target domain, and accurately predicts energy consumption by using a small amount of data.

The present application relates to the technical field of wind turbine operation and maintenance, and particularly relates to a wind turbine defect cross-domain guidance collaborative detection method and system, comprising: acquiring global scanning data of wind turbine blades and tower drums of non-stop wind turbines after a drone is calibrated by cross-domain space-time synchronization; acquiring near-domain reference data collected by a climbing drum robot at a preset reference position of the tower drum; taking the near-domain reference data as an anchor point, splicing the global scanning data to determine a defect suspected area and a spatial position; scheduling the climbing drum robot to a target site for spot detection, and acquiring multi-modal detection data; and combining real-time wind field conditions and unit operation parameters to perform interference compensation on the multi-modal data to obtain defect characteristic information. Through the present application, space-time unification and collaboration of the detection data of the drone and the climbing drum robot are realized, and the reliability of wind turbine defect identification and positioning is improved.

The application relates to the technical field of hydrology and water resources prediction, and discloses a large model driven hydrology model parameter automatic calibration method, which comprises the following steps: calling a large language model to analyze natural language demand text and basin model metadata, constructing a topological feasible domain space of high-dimensional physical parameters and a calibration strategy configuration file; performing adaptive Box-Cox transformation on original observation data to generate a stationary data sequence and cutting the stationary data sequence into a calibration set and a verification set; screening high-sensitivity parameters, extracting constrained physical parameters, performing topological transformation based on simplex mapping to generate an initial parameter vector population, performing concurrent optimization calculation on the calibration set to output parameter posterior samples; calling a Gaussian mixture clustering algorithm to cluster the parameter posterior samples to generate a structured feedback object containing a state field; and recalculating or outputting a final delivery object of the model according to the state field. The application narrows the initial search space range and quantifies the phenomenon that different parameters have the same effect.

The invention discloses a three-layer two-domain space-time affair graph construction method oriented to the public security field, which comprises the following steps of: pre-constructing public security security field ontology knowledge, mining space-time characteristics of events and entities, constructing event and instance knowledge sub-graphs from top to bottom based on a large model according to three layers of'abstraction layer-instance layer-space-time layer ', and oriented to'event domain' and'entity domain '; and meanwhile, the method has the capabilities of guiding extraction of instances such as events and entities based on public security ontology knowledge and complementing public security ontology knowledge based on instance information clustering, and the accuracy and efficiency of event and relationship mining in the public security field are improved.

This application provides an asset visualization display method, device, electronic device, medium, and program product, which can be applied to the fields of big data technology, spatial information technology, and fintech. The method includes: acquiring asset information of multiple assets; obtaining asset hierarchy relationship information based on the relationships between the asset information; acquiring business identification information of multiple business domains; associating the business identification information with corresponding system service entry addresses to obtain business entry association information; acquiring asset operation relationship information; determining target assets participating in the operation of each business domain based on the business entry association information and the asset operation relationship information; associating the business identification information with the asset identification of the corresponding target asset to obtain business asset association information; and obtaining asset layered display information based on the asset hierarchy relationship information and the business asset association information.

The application relates to the technical field of positioning, navigation and timing, and discloses a positioning method and device based on a multi-layer domain space-time network service architecture, wherein the multi-layer domain space-time network service architecture comprises an ecological integration domain and an intelligent service domain; the method comprises the following steps: determining a target scene requiring a space-time network to be constructed; based on the ecological integration domain, integrating equipment resources corresponding to the target scene to obtain resource integration information; based on the intelligent service domain, determining positioning requirements corresponding to the target scene, and based on the resource integration information and the positioning requirements, determining target service capabilities meeting positioning service conditions; based on the resource integration information and the target service capabilities, constructing a target space-time network corresponding to the target scene; and when a target service request corresponding to the target scene is detected, based on the target space-time network, providing a target service matched with the target service request and at least including positioning service. It can be seen that the application can provide positioning service to users flexibly and stably, and improve positioning accuracy.

The invention discloses a method for predicting distribution of microscopic inclusion and pore defects in an LPBF printed piece, and relates to the technical field of laser powder bed melting additive manufacturing, and the method comprises the following steps: delimiting a computational domain space based on a laser powder bed melting LPBF processing range, and carrying out grid division on the computational domain space; the LPBF powder laying process is simulated, the powder particle distribution state is obtained, and a powder particle distribution entity is extracted to serve as a base material powder layer; distributing laser energy to grids on the surface of the powder layer on a laser beam path according to the laser radius; the surface appearance of the molten pool is obtained through a fluid volumetric method; putting defect particles with corresponding information in a region corresponding to the surface appearance of the molten pool, traversing all the defect particles, and updating current time step information of the particles; and repeating the steps to finally obtain a prediction result of microscopic inclusion and pore defect distribution. The method not only can reproduce the macroscopic morphology of the molten pool, but also can quantitatively simulate the generation, migration and solidification process of inclusion particles, and reduces the manufacturing and detection cost of parts.

The invention discloses a wind power plant wind speed prediction method and system based on double-domain space-time dynamic local sensing. The method comprises the following steps: integrating fans in a wind power plant, a connection relationship and time sequence characteristics of the fans to form a space-time diagram; constructing a depth model comprising a plurality of DDL layers, wherein each DDL layer comprises a cross-domain filter, a dual-domain encoder and a dynamic local sensing recursive predictor; and projecting time-space diagram data, performing depth feature extraction on projected signal features through a plurality of DDL layers in the model, and averaging outputs of the plurality of DDL layers to form a final prediction result. The wind power plant wind speed prediction precision can be significantly improved, and the dynamic change rule of the wind speed can be effectively captured.

The invention provides a self-adaptive high-domain space expansion table and method, and relates to the technical field of space expansion, the self-adaptive high-domain space expansion table comprises a main plate, two auxiliary plates and an adjusting assembly, the two auxiliary plates are symmetrically arranged on the two sides of the main plate, the adjusting assembly comprises two main rods, the two main rods are arranged in the main plate in parallel and at intervals, and the main rods are in running fit with the main plate; the two ends of any main rod are sleeved with auxiliary rods in threaded fit with the main rod, the auxiliary rods are in limiting sliding fit with the main plate, and the auxiliary rods are connected with the side auxiliary plates of the auxiliary rods. The platform can effectively expand the space utilization rate of the office table cabinet.

The invention discloses a radar echo extrapolation method integrating physical guidance and a diffusion coupling mechanism, and relates to the technical field of meteorological short-term and imminent forecast. The method comprises the following steps: firstly, coding radar echo data by using a physical guidance network, capturing long-distance space-time dependence through a multi-scale gating axial block, and generating a preliminary prediction sequence with macroscopic physical consistency in combination with a multi-domain space-time evolution module and an explicit physical advection guidance mechanism; and then, adopting a channel decoupling and cascade diffusion strategy, taking the preliminary prediction sequence as a physical prior skeleton, extracting guide features by using a double-flow spatio-temporal context network, and executing reverse iteration denoising and refined texture repair through a diffusion model. According to the method, the physical guidance composite loss function is introduced, the problems of image blurring and physical evolution logic deficiency existing in a traditional method are effectively relieved, and the forecasting precision and image fidelity of severe convective weather are improved.

Implementations of post-tessellation blender hardware perform both domain shading and blending and while some vertices may not require blending, all vertices require domain shading. The blender hardware includes a cache and / or a content addressable memory and these data structures are used to reduce duplicate domain shading operations. In the event of a cache miss for a UV coordinate of a domain space vertex, a cache outputs the UV coordinate to a domain shader, where the domain space vertex comprises UV coordinates of neighbor vertices that are not inherent from the UV coordinates of the vertex itself.

An access point computes, for user devices in each group of a plurality of groups of user devices, a plurality of start times of future enhanced data privacy (EDP) epochs during which identifiers from the user devices in each group are to be rotated. Based on the plurality of start times, it is determined that transitory periods will occur at a same time for at least a threshold number of groups of the plurality of groups of user devices. The AP transmits a message to user devices in at least one group of the at least a threshold number of groups instructing the user devices to perform one or more actions to prevent the transitory periods from occurring at the same time.

This application provides a method and apparatus for forwarding packets, relating to the field of communication technology. The method is applied to an ingress PE node and includes: receiving a first Internet Protocol (IP) packet, the first IP packet supporting Explicit Congestion Notification (ECN); determining a first Multiprotocol Label Switching (MPLS) packet based on the first IP packet, the first MPLS Network Action (MNA) in the first MPLS packet including a first ECN field; and forwarding the first MPLS packet. The method in this application embodiment can avoid conflicts between MPLS packets carrying ECN tags and the DiffServ domain space.

The embodiment of the invention provides a GPU cache structure, a resource allocation method and device, electronic equipment and a storage medium. The GPU cache structure comprises a private domain space associated with a specified task and a shared space of full tasks. According to the embodiment of the invention, different tasks can be isolated and mutual influence can be avoided through the private domain space associated with the specified task, and different tasks can be used and GPU resources can be utilized to the maximum extent through the shared space of the total tasks, so that resource fragmentation caused by different tasks can be reduced, and the resource utilization rate can be improved.

The invention discloses a distributed private domain space intelligent security system and method, and the system specifically comprises an acquisition and recognition assembly, a data transmission module, a single-machine offline AI analysis and decision assembly, a pronunciation module and a real-time expelling assembly. Precise identification and behavior prediction of outdoor personnel are realized, experimental data shows that the false alarm rate is reduced to below 1%, networking is not needed due to single-machine offline design, response delay is remarkably reduced, data privacy risks are eliminated, and the progressive security defense response of a private domain space is ensured by a hierarchical expelling mechanism. According to the method, the legality, security and comprehensiveness of attack and repelling behaviors of a security defense system are solved, unique integration of encryption transmission and gait analysis effectively prevents technical bypassing, intrusion is blocked, the system does not need to be networked, the response time is short, the false alarm rate is low, and the method is suitable for various private domain security and protection scenes.

The embodiment of the present specification provides a secret sharing packaging method and device. A plurality of participants respectively encode vectors formed by secret sharing of k data owned by each participant in a specified domain space to obtain first domain elements owned by each participant, wherein the first domain elements have a data structure satisfying additive homomorphism. Then, through the first data interaction based on secure multi-party computation between the plurality of participants, the secret sharing addition operation is performed based on the first domain elements owned by each participant, so that the plurality of participants respectively obtain: the secret sharing of the first sum value of the first domain elements owned by each participant. The secret sharing of the first sum value is used as the secret sharing of the second domain element obtained by encoding the vector formed by k data in the specified domain space.

The application discloses a remote sensing image change detection method and device based on a Mamba-based region-space-semantic channel modeling, and the method comprises the following steps: inputting an obtained remote sensing image dataset into a constructed Mamba-based region perception, dual-domain space and semantic channel modeling network (S3Mamba) for training, obtaining a trained S3Mamba and saving the same; inputting a remote sensing image to be processed; and performing prediction on the remote sensing image to be processed by using the trained S3Mamba, so as to obtain a dual-time-phase change prediction map. The application improves the precision and performance of remote sensing image change detection by means of a three-way collaborative modeling mechanism coupling design.

The invention relates to the technical field of electric digital data processing, and discloses an infrastructure material supply and demand matching method and system based on multi-objective optimization, and the method comprises the steps: collecting and standardizing the fragmented supply and demand information of cross-domain space-time; constructing a space-time constraint and business rule model; a multi-objective optimization model with the minimum total cost, the highest time satisfaction degree and the maximum matching stability as the core is established; an improved NSGA-III algorithm is adopted to solve and obtain a Pareto optimal solution set; a decision maker is assisted in selecting and executing a final matching scheme in a man-machine interaction mode; the corresponding system comprises a data integration module, a knowledge base module, an optimization engine module, a decision support module, a scheduling feedback module and the like. Through combination of a resource optimization algorithm and an intelligent decision-making process, the problem of low matching efficiency caused by cross-region and cross-time information fragmentation is effectively solved, the matching precision can be remarkably improved by more than 30%, the matching period is shortened by more than 50%, and accurate, efficient and intelligent scheduling of capital construction materials is realized.

The application provides a miRNA-disease correlation prediction method based on an enhanced hypergraph convolution self-encoding algorithm, and comprises the following steps: S1: obtaining an adjacency matrix A of miRNA-disease, and describing the correlation relationship between the two through the miRNA-disease adjacency matrix; S2: calculating miRNA Gaussian similarity MG, miRNA cosine similarity MC, disease Gaussian similarity DG and disease cosine similarity DC through the adjacency matrix A, and taking them as the features of miRNA and the features of diseases respectively; S3: using weighted K-nearest neighbors to obtain graph hidden correlation information according to the Gaussian similarity, so as to obtain an enhanced hypergraph correlation matrix; S4: mapping the features of miRNA and the features of diseases to the same domain space through a full connection layer, and training to obtain embedding features in a hypergraph convolution mode; and S5: decoding the embedding features using a bilinear decoder, and calculating the correlation score, so that the application can more accurately predict the correlation information of miRNA-disease.

The application discloses a shield tunneling parameter prediction method based on multi-source domain transfer learning, comprising the following steps: obtaining real-time tunneling data of a target project, and loading pre-stored multi-source domain tunneling data set; performing geological field division and steady-state feature extraction to obtain target domain space-time feature sequence and multi-source domain space-time feature sequence; inputting the same into a pre-trained space-time attention feature extraction model to extract corresponding domain-invariant feature representation; generating a transferability evaluation weight corresponding to each sample in the multi-source domain according to a pre-constructed transferability evaluation strategy; processing the target domain space-time feature sequence by using a pre-trained regression prediction model, dynamically adjusting the space-time attention feature extraction model, and outputting a target domain tunneling parameter prediction value. The application realizes dynamic self-adaptive transfer of shield tunneling samples, effectively suppresses the negative transfer risk caused by stratum mutation, and improves the generalization prediction accuracy and construction safety of the model under complex and variable working conditions.

An AI-based audio compression method for use with audio formats, alone or in combination with other audio compression and enhancement approaches. A combination of audio pre-processing, sound to visual transcoding of audio, and a sequence of AI-enabled methods enabling maximal entropy order extraction applied within the sound and dimensionally extended visual domain projection of the audio significantly increases the degree of compression of audio files, thereby reducing storage, transmission and processing overhead associated with audio. A unique AI-driven domain conversion is leveraged together with domain-specific AI processing stages to reduce file size, while supporting optional use of standard and proprietary audio encoding, decoding, compression, and other methods. Support for native mode photonic computer processing of the higher-dimensional order representation of media enables further optimization via photonic computing methods that would not be possible if the audio was not extended into higher order visual domain space.

The application provides a multi-domain space fusion knowledge graph embedding method, system, device and medium, and relates to the field of knowledge graph embedding.The method comprises the following steps: (1) constructing a training set; (2) performing initialization processing on the training set; (3) performing sampling processing on the training set to construct a training subset; (4) importing the training subset into a knowledge graph embedding model to obtain triple scores and attention scores in different number domain spaces; (5) iteratively training the knowledge graph embedding model using the triple scores and attention scores in different number domain spaces until convergence; and (6) inputting triples of a knowledge graph into the iteratively trained knowledge graph embedding model for completion.The application combines attention mechanisms with calculations in real number domains, complex number domains and quaternion number domains to capture feature information of entities from different spaces and deeply depict spatial representations of entities and relationships, thereby improving the accuracy of triple matching in a knowledge graph completion task.