204 results about "Spatial computing" patented technology

The invention discloses a cross-platform virtual-real fusion scene construction method and system based on AI space calculation, and relates to the technical field of artificial intelligence and space calculation, and the method comprises the steps: carrying out the multi-scale feature fusion based on a received cross-modal conversion instruction set, and generating an initial image sequence; carrying out implicit field coding on a target object by combining a three-dimensional reconstruction algorithm to obtain an initial parameterized model; performing space-time alignment on the multi-view video stream, loading a digital scene asset package in combination with physical sensing data and a preset spatial index structure, and establishing a bidirectional data channel between a virtual scene and a physical sensor; performing rendering and illumination parameter adjustment on the initial parameterized model to obtain an optimized parameter model; performing differential coding processing on the optimization parameter model to obtain a target virtual-real scene fusion model; and distributing the target virtual-real scene fusion model to a preset terminal. The invention provides a virtual-real fusion construction method for end-to-end collaborative optimization, which is suitable for cross-platform live broadcast or dynamic interaction scenes.

Methods and systems enabling multimodal inputs for interacting with a live digital object are provided. The system receives the live digital object which includes a digital artifact extracted from a digital model file through a model representation. The system receives a user's security level and determines the user's access permission and modification permission to access and modify the digital artifact. The system accesses a multimodal interface configured to receive a conversational input and a spatial input, outputs the digital artifact to the multimodal interface based on the access permission, receives from the multimodal interface a conversational input and a spatial input from the user, and generates a modified digital artifact from the digital artifact via the digital model representation, based on the modification permission and on the conversational or spatial input. The multimodal interface may include conventional interfaces (GUIs / APIs), conversational interfaces (text / voice), and spatial computing interfaces (VR / AR / MR / gestural).

The invention belongs to the technical field of industrial operation and maintenance term processing, and provides a big language model training method based on a knowledge graph, and the method comprises the steps: carrying out the cooperation with operation and maintenance personnel in advance to set a fault dictionary, collecting fault instances, carrying out the classification and preprocessing, extracting causal trigger words of the fault instances, and setting a text dependency relationship rule. Splitting and extracting a triple of the fault instance, and importing to form a knowledge graph; mapping the instance attribute into a node feature vector, outputting an embedded representation of a node, and fusing the embedded representation with the multi-modal feature vector to form a fused feature embedded representation; replacing semantic and degree words with fault instances in the knowledge graph to generate positive samples, randomly replacing subjects, objects and causal relationships to generate negative samples, inputting the negative samples into a semantic encoder, mapping the negative samples to the same metric space, and calculating similarity to obtain a comparison loss value to adjust graph convolutional network parameters; and after the fusion feature embedding representation retrieval of the fault instance is carried out and a subgraph is generated, maintenance suggestions are given step by step along a causal chain.

The invention relates to the technical field of power equipment operation and maintenance and state monitoring, in particular to an optical fiber transformer health state assessment method and system based on feature fusion. According to the invention, sampling signals of a plurality of optical fiber current transformers are collected and preprocessed; constructing a historical data matrix for principal component analysis, establishing a principal component space and calculating a square prediction error control limit value; constructing a simulated fault data set and projecting the simulated fault data set to a principal component space to calculate a square prediction error time sequence; performing wavelet packet decomposition on the square prediction error time sequence to extract a normalized energy feature vector, and training a one-dimensional convolutional neural network model; projecting the real-time sampling signal to a principal component space to judge whether the real-time sampling signal exceeds the limit or not; if yes, the health state level is output through the trained model. According to the invention, accurate grading and real-time online evaluation of the health state of the optical fiber transformer are realized.

System and method for managing information compliance and relevance using autonomous artificial intelligence (AI) agents in data transfer and communication environments. Some embodiments may include a core orchestration engine with multiple autonomous AI agents configured to manage and evaluate the compliance and relevance of information in communication and data transfer environments. The system may use weighted metrics to assess if information and actions comply with regulations and are pertinent to recipients, monitor email and data transfer, ensure regulatory compliance, and enhance information and knowledge sharing within organizations. The system may use semantic embeddings, part-of-speech analysis, and language models to extract and apply regulatory rules efficiently. These features may significantly reduce search space, computational overhead, and manual effort while improving security and accuracy.

The invention discloses a power load prediction method based on a dynamic expert pool and a load balancing mechanism MoE, and belongs to the field of power load prediction, and the method comprises the following steps: collecting multi-dimensional input data needed by power load prediction, detecting and repairing an abnormal value in the input data, and obtaining a power load prediction result; constructing a time-feature matrix by using the repair data; projecting the time feature matrix into three subspaces of Q, K and V, calculating attention weights among feature dimensions, and obtaining enhanced features through attention weighting; the enhanced features are input into a routing layer of the MoE model, selection probability distribution of experts is calculated, the MoE model adopts a dynamic expert pool and introduces a load balancing mechanism, and a Top-2 expert selection strategy is randomly distributed in the reasoning stage; and when the MoE model is migrated to a new scene, updating the attention weight of the MoE model by adopting a meta-learning strategy. According to the method, complex factors influencing the power load can be comprehensively captured, and the power load prediction precision and the cross-scene adaptive capacity are remarkably improved.

The invention discloses a virtual power plant and resource matching method and system based on cooperation preference in the field of virtual power plant resource matching, and the method comprises the steps: building a photovoltaic, energy storage and air conditioning load multi-mode cooperation preference scoring model, and quantifying the economic effectiveness, equipment loss, user comfort and other multi-dimensional features; a double-tower representation and contrast learning technology is adopted, and resource attributes and service requirements are mapped to a unified semantic space to calculate the matching degree; in combination with an entropy regular optimal transmission algorithm, many-to-many flexible matching is realized on the premise of considering grid power flow safety constraints; and a rolling multi-cycle optimization mechanism is introduced, and a Bayesian update and reinforcement learning dynamic adjustment strategy is adopted, so that the technical problems of insufficient cooperation intention quantification, complex cross-time constraint and difficult security risk control in distributed resource scheduling under high-proportion new energy access can be solved, and the economy and security of virtual power plant scheduling can be effectively improved. And the performance stability of the system under the new energy fluctuation is enhanced.

The invention provides a digital twin enabling air-ground integrated dual power supply network supply-demand game method and system, and belongs to the technical field of intelligent management and control of energy and communication convergence networks. Comprising the following steps: constructing a digital twin system of an energy-communication fusion network, and accessing and mapping dynamic data from an energy network and a communication network in real time; based on the dynamic data, an energy side observation space and a communication side observation space are defined in the digital twin system, and the comprehensive supply and demand imbalance degree of the system is calculated; the energy side intelligent agent and the communication side intelligent agent output control instructions in a continuous action space according to respective observation spaces, and respectively aim at maximizing own long-term accumulated benefits; a final solution of the coordinated game framework is an optimal strategy combination meeting a Nash equilibrium condition; carrying out centralized training and distributed execution on the coordinated game framework by adopting a multi-agent depth deterministic strategy gradient algorithm based on supply and demand perception; and the intelligent agent carries out collaborative decision making based on the global supply-demand imbalance degree and local observation.

The invention relates to the technical field of computer vision, in particular to a complex scene object recognition system based on multi-scale feature fusion, which comprises a feature extraction module, a Riemannian geometric feature pyramid module, a candidate region generation module and an instance recognition and positioning module, and is characterized in that the feature extraction module extracts multi-scale spatial features; the Riemannian geometric feature pyramid module maps spatial features to a Riemannian manifold space, calculates curvature distribution of feature manifolds, dynamically adjusts feature extraction levels and fusion strategies, and realizes geometric consistent fusion of different scale features through geodesic line feature fusion; the candidate region generation module generates an object candidate region based on the fusion features; and the instance identification and positioning module completes final object classification and positioning, introduces a differential geometry theory to construct a Riemannian geometric feature pyramid, realizes geometric representation and adaptive fusion of features, solves the problems of scale change, partial occlusion, background interference and the like in a complex scene, and effectively improves the accuracy and robustness of object identification.

Aspects of the disclosure relate to using machine learning models to automatically prioritize and orchestrate spatial data. A computing system may generate, based on inputting scene data and spatial positioning data into a machine learning model, a prioritized context that indicates physical objects that are significant within a physical environment. The scene data may comprise images of the physical environment and the spatial positioning data may comprise an indication of states of a user in the physical environment. Based on the prioritized context meeting user criteria, generate indications associated with the prioritized context. Based on the scene data, one or more spatial anchors at which to position the one or more indications of the prioritized context within a virtual environment based on the physical environment may be generated. The virtual environment comprising the indications of the prioritized context positioned at the one or more spatial anchors may be generated.

Dynamic allocation of work and data on a spatial compute architecture in which a lead dispatch node dynamically assigns a task of an application to a selected compute tile, and routes a corresponding active message to a local data memory pool of the selected compute tile. The active message may include instructions, data, and / or configuration parameters to enable the selected compute tile to execute the task. If there is insufficient space in the local data memory pool, the lead dispatch node routes the active message to shared memory or to a local data memory pool of another compute tile, and subsequently routes the active message to the local data memory pool of the selected compute tile when space is available. Alternatively, the lead dispatch node may forward the task and the active message to another lead dispatch node.

The invention relates to the technical field of digital twinning and computer simulation, in particular to a power transmission and transformation project optical cable connection information operation and maintenance system based on a logic model, which comprises a model fusion module for constructing a digital twinning anchor point set by fusing a three-dimensional physical model and a secondary system logic model of a power transmission and transformation project; when the simulation analysis module receives a logic loop alarm, the physical path is reversely traced based on anchor point data, physical field simulation operation is executed, and a physical degradation risk point is output; the augmented reality module realizes spatial registration of a three-dimensional physical model and a live scene through a spatial computing technology, and visually presents logic loop and risk point information. According to the method, the space-time twin anchor points are constructed, the physical field simulation operation is driven, and the diagnosis result and the operation and maintenance instruction are superposed on the live scene through the augmented reality technology, so that the intelligent operation and maintenance closed loop of the optical cable connection information of the power transmission and transformation project is realized, and the troubleshooting efficiency and accuracy are improved.

The invention relates to the technical field of generalized quantum evidence theory and image processing, in particular to a ship image data target identification method based on the generalized quantum evidence theory, which comprises the following steps: converting synthetic aperture radar ship image data into complex field synthetic aperture radar data, and constructing training data; generating a composite quantum evidence label according to the potential structure; training the quantum evidence neural network to obtain a standard quantum evidence neural network; inputting to-be-recognized complex field synthetic aperture radar data into the standard quantum evidence neural network, and extracting a complex field feature vector of a to-be-recognized sample; normalizing the complex field feature vector into a generalized quantum basic probability amplitude function, and defining a proposition space under a quantum identification framework; and calculating generalized quantum basic probability distribution of the proposition in the proposition space, and executing double judgment to obtain a recognition result of the original synthetic aperture radar ship image data to be recognized. According to the method, the accuracy of ship image data target identification based on the generalized quantum evidence theory can be improved.

The invention discloses a scene imagination retrieval method, device and system, a storage medium and a program product, and the method comprises the following steps: S1, collecting an electroencephalogram signal of a human body when the human body imagines a specific scene; s2, the electroencephalogram signals are preprocessed, and continuous electroencephalogram signal fragments in a short time window are obtained; s3, encoding and fusing the electroencephalogram signal segments to obtain high-dimensional feature vectors, and identifying and encoding retrieval targets in a retrieval target library to obtain a plurality of target feature vectors; s4, performing cross-modal projection on the high-dimensional feature vector and the multiple target feature vectors, and mapping the high-dimensional feature vector and the multiple target feature vectors to a unified semantic space; s5, calculating the similarity between the high-dimensional feature vector and the target feature vector; and S6, performing retrieval target classification based on the similarity, and outputting a retrieval result in the retrieval category with the highest similarity according to the matching confidence. The problems that in retrieval in the prior art, retrieval operation is inconvenient, and implicit retrieval is lacked are solved.

The invention relates to the technical field of unmanned forcible entry robots, in particular to an unmanned forcible entry robot target recognition method and system based on space calculation, and the method comprises the steps: collecting the three-dimensional space data of a forcible entry scene through a multi-mode sensor; constructing a scene digital twinborn model based on space calculation, and performing accurate mapping of a physical space and a digital space; extracting spatial geometric and topological features of the forcible entry target by adopting a spatial feature enhancement algorithm; target classification and pose estimation are completed in combination with a deep learning model of a space attention mechanism; and a real-time space error compensation mechanism is introduced, and a target identification result is dynamically corrected. Compared with the technical problems that in the prior art, target recognition of an unmanned forcible entry robot is likely to be shielded and interfered, the space positioning precision is low, and the unmanned forcible entry robot cannot adapt to complex forcible entry scenes, the method achieves high-precision, anti-interference and dynamic recognition of the forcible entry target by designing a space calculation closed loop, and improves the operation safety and efficiency of the unmanned forcible entry robot.

The invention provides a multi-source domain invariant acoustic feature extraction method and system for an equipment operation state, and belongs to the technical field of equipment maintenance, and the method comprises the steps: constructing a multi-source domain invariant acoustic feature extraction network based on a DANN model, and the network comprises a feature extractor, a classifier, a domain discriminator and a multi-domain acoustic feature class boundary constraint module; the feature extractor extracts high-dimensional features of sound signals, the classifier carries out fault mode recognition, and the domain discriminator realizes domain prediction. The multi-domain constraint module generates an embedding space, and calculates the maximum mean value difference, the local maximum mean value difference and the Euclidean distance among different source domain features. The network constructs a loss function by taking minimization of inter-domain difference and classification loss and maximization of inter-domain distance and domain discrimination loss as targets, and carries out adversarial training through multi-source tagged acoustic data. According to the method, domain invariant features are extracted by using adversarial learning and hidden space constraint alignment of multi-source domain acoustic features, so that the influence of feature offset under a cross-working-condition condition is effectively reduced, and the fault mode recognition accuracy is improved.

The invention relates to the technical field of cabinet monitoring, and discloses a cabinet aging monitoring system based on a temperature sensor. The system comprises a historical data acquisition module for acquiring historical temperature data of a cabinet in a preset period and generating a historical health data set; extracting temperature characteristic parameters through a characteristic extraction module, and establishing a temperature trend change characteristic matrix; a state space module constructs a multi-dimensional state space according to the matrix, calculates a historical aging event temperature state aggregation degree, and determines a temperature characteristic early warning index set; the real-time risk module extracts real-time temperature characteristic parameters and establishes state vectors, and real-time aging risk correlation factors are calculated and determined through spatial position correlation; and finally, the prediction module combines the data to generate an aging risk probability prediction model, predicts the aging probability of the cabinet and generates a maintenance scheduling suggestion, thereby realizing accurate monitoring and prediction of the aging of the cabinet.

A device may capture real-time images of a product. Capturing may include using an outward-facing sensor on a device. A device may identify the product by using an identification machine learning model. A device may obtain user interaction data corresponding to previous images displayed on the device. A device may identify available offers. A device may identify a set of offers from the available offers using an offer selection machine learning model trained to automatically select offers presentable to users through devices. The offer selection machine learning model may be trained using a dataset of historical interaction data and corresponding offers. A device may present the set of offers through the device. A device may monitor in real-time user interaction with the set of offers. A device may update the offer selection machine learning model according to the real-time user interaction with the set of offers.

The invention discloses a BIM-based multi-dimensional collaborative engineering drawing automatic review method and system, and the method comprises the steps: obtaining BIM model data, and obtaining corresponding review standard provisions; on the basis of the review standard provisions, constructing review rules, and storing the review rules in a rule base; a rule importance level is preset for each review rule, and a parameter threshold value is preset for the review rule related to numerical value verification; analyzing the BIM model data, and constructing a model structure comprising components and association relationships among the components; loading a model structure through a rule engine, calling a digital review rule in a rule base, and carrying out logic judgment and space calculation on components in the model structure, so as to identify a model problem violating the rule; for each identified model problem, carrying out risk level evaluation on the model problem; and generating a structured review report based on the model problem and the corresponding risk level. According to the invention, regularized automatic review of the BIM model is realized.

The invention relates to the technical field of power system equipment monitoring, in particular to a substation equipment state monitoring embedded edge analysis system, which comprises a monitoring front-end module for acquiring and transmitting substation equipment operation state data; the edge processing module comprises a multi-scale wavelet transform unit, a topology continuity analysis unit and a manifold learning unit, wherein the multi-scale wavelet transform unit decomposes data and separates signals and noise through a self-adaptive threshold mechanism; the topological persistence analysis unit maps the de-noised signal to a high-dimensional feature space, calculates a persistent coherence group, and extracts a topological feature vector; and the manifold learning unit constructs a nonlinear manifold structure, calculates a geodesic distance, and executes discharge type identification and anomaly evaluation, and the FPGA and ARM heterogeneous calculation architecture is adopted, and through the synergistic effect of multi-scale wavelet transform, topology persistence analysis and manifold learning, high-precision extraction of weak discharge signals and accurate identification of fault modes are realized.

The invention discloses a spatial visual information system and a sensing method, and belongs to the field of spatial computing. In order to overcome the defects of high power consumption, high delay, poor robustness and the like when target detection is carried out by depending on a traditional image sensor in the prior art, the spatial vision information system comprises a light source, a light source, an image sensor and a control module, and the event-based sensor is used for sensing the light intensity change in the three-dimensional space. The method has the advantages of low power consumption, low delay, high precision and low cost, and is suitable for AR, VR, HR and other scenes.

The invention provides a virtual power plant flexible load aggregation and scheduling control method and system, and relates to the technical field of power management, and the method comprises the steps: obtaining flexible load resource information, calculating a matching degree based on a multi-dimensional matching space, dynamically building a temporary aggregation unit, constructing an expected response reference and individual difference envelope, and generating a main scheduling instruction and an individual compensation instruction. And the matching degree weight and envelope are updated according to the actual response data. According to the invention, the response precision of the virtual power plant to the power grid scheduling task can be improved, and efficient aggregation and accurate scheduling control of flexible load resources are realized.

According to the IO speed limiting method and device under multiple threads, the electronic equipment and the storage medium provided by the embodiment of the invention, the technology realizes speed limiting of the IO request through a quota isolation and critical point synchronization mechanism, and effectively avoids frequent scrambling of a lock at the same time. The core process of the method comprises the following steps: when a client issues an IO request, reading a current value of a speed limit counter, and calculating an available space in combination with a preset speed limit quota and an instantaneous issuing space; when the request quantity does not exceed the available space, directly releasing the request to disk equipment and updating a statistical value; and if the request quantity exceeds the available space, safely accessing the quota management pool through the thread lock, obtaining a target speed limit quota from the global IO request speed limit quota, and temporarily improving the instantaneous issuing space to process the excess request. According to the design, the threads can operate autonomously within the quota through quota independent distribution, lock competition is not needed, meanwhile, synchronous operation is strictly limited in a critical scene of quota application, the lock scrambling frequency is greatly reduced, and therefore IO performance is remarkably improved.

The invention relates to the field of engineering management, and particularly discloses a quality management system and method for engineering construction, and the method comprises the steps: firstly carrying out the preprocessing of a BIM model, and constructing a reference frame integrating visual features and spatial geometric information; when a problem image shot by a mobile terminal at a construction site is received, a computer vision and space calculation technology is introduced, a two-dimensional field image is analyzed into an accurate pose of a shooting camera in a three-dimensional BIM space, and sight line tracing is automatically performed in a BIM digital model based on the accurate pose. And intelligently inferring and retrieving candidate components which are highly matched with the perspective of the problem. And finally, on-site unstructured problem data and the unique identifier of the BIM component are firmly bound through lightweight interaction confirmation with the user, and a standardized structured problem record is obtained. Therefore, the problems of low manual positioning efficiency and unstable association can be solved, and the whole-process intelligent closed loop of quality problem data from acquisition to structured storage is realized.

The invention relates to the technical field of geographic information systems, in particular to a dynamic intelligent site selection method and system based on Gis geographic space calculation, and the system comprises a data input module, a data processing module, a geographic space calculation module, a screening module and a result output module which cooperatively work through a data interface and a control flow. The invention provides an efficient, accurate and scientific plot screening method for the fields of high-standard farmland construction, urban building planning and the like by realizing dynamic intelligent site selection based on Gis geographic space calculation; by improving the accuracy of plot screening, optimizing resource allocation, improving the working efficiency, enhancing the scientificity and rationality of decision making and promoting the development and innovation of related fields, the method has important practical application value and wide development prospects.

The invention discloses a cloud rendering method and system for space computing and terminal equipment, and belongs to the technical field of cloud computing and virtual / augmented reality. The method aims at solving the technical problems that an existing space computing device cannot run severe applications due to limitation of local computing power, power consumption and heat dissipation, and application ecology is separated from a traditional two-dimensional desktop. The method comprises the following steps: operating an operating system environment capable of bearing two-dimensional and three-dimensional applications on a cloud server, performing real-time synthesis and rendering on the output of each application in a three-dimensional virtual space, and updating a scene according to user interaction data received from terminal equipment, and the generated three-dimensional scene is transmitted to terminal equipment in a streaming manner by adopting an optimized coding technology. The method has the beneficial effects that a core computing task is arranged at the cloud end, so that a user can obtain top-level workstation performance through light-weight terminal equipment, various professional applications can be seamlessly operated, persistence and cross-equipment roaming of a working space are realized, and the productivity value of space computing is greatly improved.

The present application relates to the technical field of smart water affairs and urban public safety, and particularly relates to a kind of artificial intelligence driven urban pipe network flood resilience evaluation method and system, comprising: constructing Riemann metric tensor by using metric matrix containing potential barrier function, and establishing the Riemann manifold embedding space of pipe network physical state;Then, based on fluid energy, a Hamilton function is constructed, and a dynamics prediction model with physical conservation is obtained by using symplectic neural network and symplectic discrete integral format training;Subsequently, a second-order Hamilton-Jacobi-Aleksandrov partial differential equation describing stochastic differential game is constructed, and a physical perception neural network is used to solve and extract the resilience safety boundary;Finally, real-time data is mapped to the manifold space, the Riemann gradient is calculated, and a quadratic programming problem is solved to generate control instructions. The problem of lack of physical constraints and safety bottom line in pipe network control under extreme random working conditions is solved, and real-time closed-loop control with physical consistency is realized.

Systems, computer program products, and methods are described herein for generating an interactive 3D environment using spatial computing to generate historical digital components. The present invention is configured to identify a user account(s), wherein the user account(s) is associated with a resource account(s); identify a resource transmission(s) associated with the resource account(s), wherein the resource transmission(s) is associated with a geolocation coordinate(s) or an entity identifier(s); generate a virtual computing environment based on the at least one resource transmission and geolocation coordinate(s) or the entity identifier(s); generate a virtual computing environment avatar based on the user account, the resource transmission(s) and the geolocation coordinate(s) or the entity identifier(s); and generate a resource transmission movie in the virtual computing environment, wherein the resource transmission movie comprises at least one virtual computing environment component based on the resource transmission(s).