244 results about "Model graph" patented technology

The invention relates to the technical field of intelligent operation and maintenance, in particular to an execution method of a large model graph retrieval enhancement system oriented to software and hardware monitoring operation and maintenance, which comprises the following steps: S1, inputting fault information to the graph retrieval enhancement system; s2, a graph construction and updating module receives and processes the fault information, generates a triple, and writes the triple into an operation and maintenance / fault knowledge graph; s3, the fault information is input into a graph retrieval enhancement module for two-stage filtering retrieval, and sub-graph information is screened out; s4, the prompt word construction module converts the fault information and the screened sub-graph information into structured natural language prompt segments; and S5, a reasoning generation module performs natural language question and answer to generate a fault analysis result. Based on the above scheme, the execution method enhances the adaptive capacity of knowledge reasoning and fault positioning, gives play to the generalization reasoning capacity of a large language model while ensuring the accuracy, and enhances the practical value.

The invention belongs to the technical field of power distribution network fault recovery, and provides a power distribution network fault recovery method based on graph reinforcement learning and a related device, and the method comprises the steps: constructing a power distribution network fault recovery problem graph model, and carrying out the embedding of a power distribution network model graph based on a graph attention neural network; based on the power distribution network fault recovery problem graph model, an agent set of multi-agent reinforcement learning is constructed, and the power distribution network fault recovery problem is modeled as a Markov decision process; and solving the Markov decision process, carrying out multi-agent training, and generating a fault recovery strategy by the trained agents according to the current state of the power distribution network. According to the method, the technologies of graph theory, deep learning and reinforcement learning are deeply fused, and efficient and accurate power distribution network fault recovery strategy generation is realized.

The invention discloses an MCP-based multi-agent collaboration method and device and a medium, and relates to the technical field of artificial intelligence, the method comprises the following steps: obtaining a model registry form through a standardized model registration interface, analyzing model metadata in the registry form, and extracting a core field of a current registration model; creating a model node in the model map, and initializing the model node based on the core field; receiving a task request, triggering a scheduling engine, determining a plurality of candidate model nodes in the model atlas according to task content, respectively calculating task execution scores of the candidate model nodes, and generating a model execution chain based on the task execution scores; and based on the model execution chain, scheduling a candidate model corresponding to the candidate model node, and executing the corresponding task content. Dynamic access of multiple types of models is supported through a standardized model registration interface, system expansibility and integration efficiency are improved, and matching precision of tasks and models and multi-model cooperation continuity are enhanced.

The invention provides a model sensitive data detection method which comprises the following steps: loading a model file of a to-be-detected model, determining a frame type of the model file, obtaining model graph structure data corresponding to the model file, and obtaining a model parameter set corresponding to the model file from the model graph structure data; performing sensitive data detection on the model parameters in the model parameter set to obtain a first detection result; when the first detection result represents that the model parameter set does not contain sensitive data, abnormal hidden data detection is carried out on a weight parameter and an offset parameter corresponding to the to-be-detected model in the model parameter set, and a second detection result is obtained; and when the second detection result represents that the model parameter set does not contain abnormal hidden data, performing safe operation detection on the to-be-detected model in the isolation environment to obtain an operation detection result, so as to realize multi-level sensitive data detection, ensure the comprehensiveness and depth of detection, and improve the detection efficiency and detection precision of sensitive data detection.

The invention discloses a large-scale heterogeneous computing power cluster training and pushing acceleration method, which comprises the following steps: S1, collecting operation characteristics of each node of a heterogeneous cluster, and constructing an equipment state parameter set; s2, loading a training and reasoning model, constructing an intermediate representation graph structure, and generating graph structure information; s3, inputting the graph structure information and the equipment state parameter set into a scheduling strategy model constructed based on a neural network ordinary differential equation, and generating an optimization decision result; s4, reconstructing a model graph according to an optimization decision result, and dividing the model graph into a training sub-graph and a reasoning sub-graph; s5, mapping the sub-graphs to heterogeneous nodes, performing resource matching and task distribution according to the equipment state parameter set, and generating a scheduling result; s6, collecting performance feedback information; and S7, inputting feedback information into the scheduling model to update parameters, and adjusting evolution function strategy parameters. According to the method, the scheduling acceleration of the training and pushing task of the deep model in the heterogeneous cluster is realized.

The invention relates to a virtual try-on method based on a diffusion model, computer equipment and a program product, and the virtual try-on method comprises the steps: obtaining a clothes graph and a model graph, respectively obtaining a posture graph, a depth graph, a mask graph, model potential features and clothes potential features, and inputting the posture graph, the depth graph, the mask graph, the model potential features and the clothes potential features into a first control network and a second control network; performing convolution on the posture graph and the clothing graph to obtain a posture feature graph, combining the random noise, the model latent features and the posture feature graph, inputting the combination into a first control network, and outputting a posture control vector by the first control network; performing convolution on the depth map and the clothing map to obtain a depth feature map, combining the random noise, the model latent features and the depth feature map, inputting the combination into a second control network, and outputting a depth control vector by the second control network; injecting a posture control vector and a depth control vector into an intermediate layer and a decoder of the first diffusion model to output a fitting image; and comparing the difference loss of the fitting image and the model chart, and training the first control network and the second control network.

The invention discloses an oil product pipeline leakage monitoring method, device and equipment and a medium, and relates to the technical field of pipeline monitoring, the method comprises the steps that a graph model of a pipeline monitoring network is constructed, and each node pipeline in the graph model is provided with a measuring point; collecting pipeline data of each measuring point in real time, wherein the pipeline data comprises temperature, pressure and flow data; performing feature extraction on the pipeline data to obtain various feature data; determining a pipeline working condition for the various characteristic data corresponding to each measuring point, and adjusting a fusion weight for fusing the various characteristic data in real time by adopting a reinforcement learning algorithm based on the pipeline working condition; according to each fusion weight, performing feature fusion on the multiple feature data to obtain a multi-source fusion feature; inputting the multi-source fusion feature of each measuring point into a sensor fault recognition model, and outputting a sensor fault mark; and inputting the multi-source fusion feature of each node carrying the sensor fault mark into a leakage identification and positioning model, and outputting the leakage probability of each node. The prediction accuracy can be improved.

The embodiment of the invention discloses a three-dimensional object texture enhancement method based on coordinate mapping and super-resolution. A specific embodiment of the method comprises the steps of obtaining a scene image data sequence corresponding to a target scene; constructing a three-dimensional scene grid model; generating a scene texture expansion view and image data of each model; the following training steps are executed: obtaining a high-resolution texture expansion graph; generating image data of each rendering model; generating a pixel loss value and a perception loss value; generating an adversarial loss value; generating an image loss value; in response to determining that the image loss value does not meet the preset loss condition, adjusting the parameters of the initial neural network, and executing the training step again; in response to determining that the image loss value meets the loss condition, determining a generative network in the initial neural network as a generative model; and generating a target three-dimensional scene grid model. According to the embodiment, enough training data can be provided for training of the generative network, and the precision and accuracy of the generated three-dimensional grid model can be improved.

The invention discloses a knowledge distillation-based lightweight diffusion model drawing generation method and system, and relates to the technical field of drawing generation, and the method comprises the steps: collecting electric power engineering drawing data, preprocessing the drawing data, constructing a basic model, training the model, obtaining the trained basic model, and designing a lightweight model. And defining a knowledge distillation loss function, combining with the output of the basic model, training a lightweight model, outputting an intermediate feature map and a prediction result by using the trained lightweight model, evaluating the quality and diversity of an electric power engineering drawing sample generated by the lightweight model by using indexes, and adjusting the model and data and optimizing model parameters according to an evaluation result. According to the lightweight diffusion model provided by the invention, the parameter quantity and the calculation complexity of the model are remarkably reduced while relatively high quality of the generated image is maintained, the operation efficiency and the mobility of the model are improved, and the lightweight diffusion model can be operated on equipment with limited resources to meet the requirement of real-time application.

Systems, methods, and computer program products that use unsupervised learning to learn relationships between operations of a machine learning model based on a model graph representation to group the operations into clusters and, given a set of clusters and labels for the clusters, use a reinforcement learning algorithm to generate a final device placement result for the machine learning model.

The invention discloses an unmanned aerial vehicle performance pattern generation method and device, computer equipment and a storage medium, and the method comprises the steps: collecting historical unmanned aerial vehicle performance patterns, and carrying out the text marking of the historical unmanned aerial vehicle performance patterns, so as to construct a training data set; training a text graph model and a corresponding control model by using the training data set so as to construct a pattern generation model; and generating a corresponding unmanned aerial vehicle performance pattern by using the pattern generation model based on a set pattern generation requirement. According to the method, historical unmanned aerial vehicle performance patterns are collected and text marking is carried out to construct a training data set, the data set is utilized to train a text graph model and a control model thereof, a pattern generation model is constructed, and finally patterns are generated through the model pattern generation model according to set pattern generation requirements. In this way, the process of manual direct design or repeated adjustment can be reduced, the generation period of the unmanned aerial vehicle performance pattern is remarkably shortened through automatic model generation, and the generation efficiency is improved.

The invention discloses a multi-level network threat dynamic identification method based on a graph neural network, and the method comprises the following steps: collecting multi-source heterogeneous network security data, and carrying out the preprocessing; constructing a multi-level network threat graph; inputting the multi-level network threat graph into an improved GraphSAGE network to carry out graph embedding modeling; identifying an attack propagation path, and extracting a risk sub-graph region serving as a candidate attack chain; performing threat level evaluation on the risk sub-graph region, and calculating an overall threat score of the risk sub-graph region; and comparing the overall threat score with a preset threshold value, if the overall threat score exceeds the threshold value, determining that the threat is a high-risk threat, and outputting an early warning result. The multi-level threat graph is modeled through the graph neural network, attack chain recognition and threat evaluation are achieved, and the method has the advantages of being high in expressive power, accurate in recognition and fast in response.

The invention relates to a modeling method, in particular to an unmanned aerial vehicle spectral image BRDF rapid acquisition and adaptive generalization modeling method. The method comprises the following steps: 1, determining a research area, obtaining multi-angle BRDF data of the research area, and obtaining illumination change data at the same time; 2, preprocessing the acquired multi-angle BRDF data in combination with illumination change data to obtain preprocessed multi-angle images, splicing the multi-angle images to generate a panorama of the research area, and acquiring a digital surface model graph at the same time; 3, carrying out pixel-by-pixel classification on the research area based on the panorama to obtain a ground feature category map; calculating the gradient and the slope direction of the research area pixel by pixel based on the digital surface model graph; 4, correcting a preset BRDF model by using the acquired illumination change data, gradient and slope direction; and 5, self-adaptive generalization modeling is carried out. According to the method, high-efficiency BRDF acquisition can be realized, and the influence of regional change, space environment and topographic factors on BRDF modeling precision can be eliminated.

The invention discloses a robot path planning method for warehouse logistics cluster operation, and belongs to the technical field of path planning. The method comprises the following steps: constructing a two-dimensional model diagram by using a grid method; the ant colony algorithm is improved; an improved ant colony algorithm is adopted to plan an operation path for each logistics robot; a local obstacle avoidance strategy is carried out through a dynamic window algorithm, and whether obstacles exist around is detected; and the collision type is judged, and a corresponding collision avoidance strategy is adopted until all the robots safely and correctly arrive at the preset target point. According to the method, the pheromone concentration is initialized by introducing the Sigmoid function, blind search in the early stage is avoided, the self-adaptive slope parameter is introduced, and the steep degree of the Sigmoid function is dynamically adjusted according to environmental characteristics; meanwhile, the ant colony algorithm and the dynamic window algorithm are fused, parameters are dynamically adjusted according to the number of iterations, the obstacle rejection weight is introduced, the algorithm is prevented from falling into local optimum, and global path planning and local dynamic obstacle avoidance are achieved.

The invention discloses a civil engineering construction task automatic scheduling method and system. The method comprises the steps that a heterogeneous graph model representing construction task elements and the incidence relation of the construction task elements is constructed; processing the heterogeneous graph model by using a graph neural network to mine a dependency relationship between processes and extract risk association features related to uncertainty to form a construction state graph; constructing a Bayesian network based on the construction state atlas; probabilistic reasoning is carried out through a Bayesian network, the influence of uncertain factors is quantified, and key information representing risk conduction is fed back to the graph neural network so as to dynamically correct recognition of the graph neural network on a process dependency relationship; the dependency constraint output by the graph neural network and the risk quantification result output by the Bayesian network are fused, and a construction task scheduling scheme is generated; and synchronously updating the heterogeneous graph model, the graph neural network and the Bayesian network according to field construction feedback data to realize closed-loop iterative optimization of a scheduling scheme.

Disclosed in the embodiments of the present application are a model rendering method and a related apparatus. The method comprises: for an initial three-dimensional model to be processed, simplifying the model structure of the initial three-dimensional model on the basis of a topological structure feature of the initial three-dimensional model, so as to obtain a simplified three-dimensional model, wherein the number of meshes comprised in the simplified three-dimensional model is less than the number of meshes comprised in the initial three-dimensional model, and the difference between the simplified three-dimensional model and the initial three-dimensional model meets a preset similarity requirement; by means of lighting simulation processing, determining a lighting intensity corresponding to a vertex in the simplified three-dimensional model when the simplified three-dimensional model is in a virtual environment; and on the basis of the simplified three-dimensional model and the lighting intensity corresponding to the vertex in the simplified three-dimensional model, rendering the simplified three-dimensional model, so as to obtain a model image for representing the simplified three-dimensional model. The method can automatically reconstruct and render a three-dimensional model, thereby improving the reconstruction efficiency of the three-dimensional model and reducing labor costs.

The present invention provides a lithology classification model construction method and a lithology classification method, and relates to the technical field of lithology classification. The lithology classification model construction method comprises: extracting the lithology characteristics of each lithology in a lithology data set, and constructing a lithology adjacency matrix and a lithology adjacency submatrix according to the co-occurrence relationship of all lithologies; obtaining output lithology characteristics and output lithology sub-features according to the lithology adjacency matrix, the lithology adjacency submatrix and the lithology characteristics respectively; obtaining a graph representation and a node representation according to all output lithology characteristics, and obtaining a subgraph representation and a subnode representation according to all output lithology subfeatures; obtaining a model graph representation and a model subnode representation according to the graph representation and the subnode representation, and obtaining a model subgraph representation and a model node representation according to the subgraph representation and the node representation; and constructing a lithology classification model according to the model graph representation, the model node representation, the model subgraph representation and the model subnode representation. The present invention can effectively improve the efficiency of lithology classification of geological maps.

The invention provides a laser interference processing optimization method and system for improving the performance of a micro-nano structure, and relates to the technical field of laser micro-nano machining.The method comprises the steps that firstly, micro-nano structure sample processing parameters are extracted, a sensitive tracking model is constructed to analyze parameter sensitivity, and a lifting-retaining parameter set is obtained; according to the simulation modeling, processing and lifting a dynamic model diagram, analyzing the period consistency of the dynamic model diagram and a reference design diagram through foreground and background maximum flow cutting, and determining a structure period; if the local photoetching model diagram is of a periodic structure, projecting the actual local photoetching model diagram to a local photoetching model diagram of one type in a sine manner, analyzing the curve slope, and optimizing a periodic interference angle and a light beam wavelength; and if the structure is a non-periodic structure, interpolating a gradient processing chromaticity layout for the second-class local photoetching model diagram according to a chromaticity tradeoff criterion, and analyzing and optimizing a dynamic phase in real time. According to the method, high-precision optimization of the processing parameters of the micro-nano structure with consistency in different periods is realized, and the overall performance and stability of the micro-nano structure are effectively improved.

A method for grinding the internal thread of a ball screw nut is implemented according to the following steps: S1, drawing a model diagram of the internal nut of a ball screw in a three-dimensional drawing software, and importing the initial grinding position and the distance of the non-roller surface on the x-axis into a processing device after measuring the distance of the non-roller surface on the x-axis; S2, the processing device grinds the grinding wheel to its initial grinding position and the rolling surface of the internal thread of the ball screw nut; S3, when the grinding wheel reaches the initial position of the non-roller surface, the grinding wheel withdraws along the x-axis and moves according to the distance on the x-axis in step S1; S4, after moving the distance on the x-axis in step S1, the grinding wheel contacts the rolling surface on the x-axis to continue processing. The beneficial effect of the present invention is that by avoiding the non-roller surface, the ineffective working time of the grinding wheel in the non-target area is reduced, thereby extending the service life of the grinding wheel.

The invention belongs to the technical field of model-driven system engineering and intelligent system modeling, and particularly relates to a test requirement formalized design method based on primitive intelligent extension. The method comprises the following steps: obtaining a semantic map, and defining semantic nodes in the semantic map as type modules or intelligent modules; instantiating the type module to obtain a type model instance node, and instantiating the intelligent module to obtain an intelligent model instance node; organizing the type model instance nodes and the intelligent model instance nodes into a model graph; constructing an extended state primitive, constructing a plurality of interactive combination states based on the extended state primitive, defining an intelligent migration mechanism and constructing an extended state machine diagram; respectively testing the model diagram and the expansion state machine diagram, and if the model diagram and the expansion state machine diagram are tested to be qualified, exporting the model diagram and the expansion state machine diagram; the method can solve the problems of dynamic behavior description fragmentation, multi-agent interaction mechanism stiffness and insufficient model reusability of a traditional system modeling language in intelligent system modeling.

A meta-model topology comprises a plurality of functions and conforms to a global label schema. A new function not included in the plurality of functions is integrated into the meta-model topology. A particular label of interest that is associated with the new function is identified and the new function is configured such that an output from the new function conforms to an output form corresponding to the particular label of interest from the global label schema. The new function is then integrated into the meta-model topology and the meta-model topology that includes the new function is used to generate a model graph. The model graph is then deployed to a remote application that is configured to receive data prompts comprising input data processed by nodes of the model graph.

The embodiment of the invention relates to a generation method of a lamp strip modeling graph, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target picture which comprises a target image region occupied by a target object, determining an equivalent outer contour corresponding to the target object based on the target picture, the equivalent outer contour comprising a plurality of key feature points, in response to a smoothing parameter about the equivalent outer contour input by a user, removing key feature points which do not meet a preset concave condition from the equivalent outer contour to obtain a plurality of candidate feature points, generating a target contour based on the plurality of candidate feature points, generating lamp strip arrangement information based on a preset spacing distance, and displaying the lamp strip arrangement information. The lamp strip arrangement information is used for representing the positions of the lamp strip sections with different colors on the target contour, and rendering the target contour based on the lamp strip arrangement information to obtain a lamp strip modeling graph. According to the embodiment of the invention, a clear, visible and personalized lamp strip modeling graph is provided for a user, the user can shape an accurate and attractive model according to the lamp strip modeling graph, and the interestingness and the use experience are improved.

The invention discloses a human behavior prediction method based on a double-flow space-time diagram convolutional network, and belongs to the technical field of computer vision and deep learning, and the method comprises the following steps: S1, obtaining a human skeleton data set; s2, preprocessing skeleton point data; s3, processing the preprocessed skeleton point data through a double-flow space-time diagram convolutional network; s4, constructing a multi-scale joint point spatial dependency relationship; s5, processing the output features of the first stream through frequency weighting and a channel feature importance attention mechanism, dynamically adjusting the feature weights of high-frequency and low-frequency channels, and generating enhanced spatial-temporal features; and S6, fusing the output features of the double-flow network, generating a final behavior prediction result, and realizing human body behavior prediction. According to the method, through a multi-space category modeling graph convolution module and a frequency weighting and channel feature importance attention mechanism, a multi-space category modeling double-flow space-time graph convolution network is further provided, and the accuracy of behavior prediction is remarkably improved.

In one aspect, a method for modeling graphs on distributed storage, comprising: receiving graph data including vertices, edges, and properties; mapping each vertex to a vertex record in a distributed storage system; mapping each edge to an edge record in the distributed storage system; mapping each property to a property record in the distributed storage system; determining, for each vertex, whether a number of incident edges exceeds a maximum record size threshold; storing pointers to incident edge records directly within vertex records when the number of incident edges does not exceed the maximum record size threshold; utilizing an adjacency index to lookup incident edge records when the number of incident edges exceeds the maximum record size threshold; and executing graph traversal operations that navigate from vertex to vertex by accessing the appropriate edge records through either the stored pointers or the adjacency index.

The invention provides a secondary equipment debugging intelligent auxiliary method and system based on a secondary logic model, and relates to the technical field of debugging assistance, and the method comprises the steps: collecting multi-source structured data related to secondary equipment; constructing a secondary logic model diagram for debugging assistance by taking the equipment nodes as objects and the communication relationship and the logic control relationship as connecting edges based on the multi-source structured data; obtaining a debugging task; mapping the debugging task to a corresponding node in the secondary logic model diagram through a semantic and configuration fusion matching mechanism; based on the secondary logic model diagram and the debugging task mapping result, generating a structured debugging operation template in a mode of combining template retrieval, state injection and logic verification; based on the structured debugging operation template, comparing and checking the running state data of the current debugging object equipment; and on the basis of the comparison check result and the structured debugging operation template, executing online monitoring of the link state, and assisting in realizing intelligent analysis of the debugging state.

The embodiment of the invention discloses a self-adaptive merging method and system based on multiple single BIM models, and the method comprises the steps: carrying out the projection of the single BIM models from three dimensions to two dimensions, obtaining a two-dimensional model diagram on a two-dimensional plane, and extracting feature intersection points and feature edges from the two-dimensional model diagram; on the basis, combining vertexes and edges in the single BIM models and feature intersection points and feature edges corresponding to the two-dimensional model graph to form a model feature vector matrix, calculating model feature values, and obtaining a model feature value set of the multiple single BIM models; and carrying out clustering analysis on the model characteristic value set to obtain a fitted and combined target model, and carrying out combination to realize light weight of the model. And moreover, the single BIM models are automatically processed in the whole process, manual operation of designers is not needed, and the model merging efficiency is improved.

Provided are an explainable artificial intelligence (XAI) apparatus and a method for analyzing a model thereof. The XAI apparatus according to the present invention may use bytecode of a model to generate a model graph even for models including dynamic control flow, which are otherwise unable to generate a graph, in order to provide visualization of the decision-making process of an XAI algorithm.

The invention discloses a path optimization method and device for a sweeping robot and electronic equipment. The method comprises the steps that an environment modeling graph of a to-be-cleaned area is acquired, and a cleaning path set is determined according to the environment modeling graph; the cleaning path set is optimized through an improved genetic algorithm, optimization is stopped until a preset number of iterations is reached, a target cleaning path set is obtained, and the improved genetic algorithm gradually optimizes an initial cleaning path in the cleaning path set at least through a fitness function, crossover operation and mutation operation; and determining the cleaning path with the highest fitness value in the target cleaning path set as an optimal path. According to the method and the device, the technical problems that the sweeping path is not clear, the path smoothness consideration is lacked and the dynamic obstacle avoidance capability is insufficient during path planning of the sweeping robot in the prior art are solved.

The invention discloses a spherical panoramic image feature matching method and system, a terminal and a storage medium, and the method comprises the steps: obtaining a spherical panoramic image, and carrying out the preprocessing of the spherical panoramic image; screening the preprocessed spherical panoramic image based on a spatial constraint model, and constructing a scene graph based on the screened spherical panoramic image; segmenting the scene graph into a plurality of sub-scene graphs, and performing priority ranking on the sub-scene graphs based on a graph sequence scheduling algorithm; and performing geometric correction and feature extraction on all the screened spherical panoramic images, and executing a feature matching task of the spherical panoramic images in the sub-scene images according to the priority ranking of the sub-scene images. Through a spatial constraint model, a graph order scheduling algorithm, geometric correction and a cascade Hash matching algorithm, the problem that feature matching efficiency and precision are difficult to consider when a spherical image feature matching technology processes large-scale high-resolution spherical images is solved.

The invention provides an education large model tuning method and device based on dynamic optimization, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring multi-modal data; the multi-modal data comprises physiological data, learning behavior data and emotion feedback data; inputting the multi-modal data into a heterogeneous model in the education large model, processing the multi-modal data by using the heterogeneous model to obtain multi-modal feature vectors, and fusing the multi-modal feature vectors to obtain a fused feature vector; the heterogeneous model comprises a GLM-4 model, a graph neural network and a convolutional neural network; and inputting the fusion feature vector into a reinforcement learning model in an education large model, determining a reward through a reward function, determining a Q value according to the reward, and determining a recommendation strategy based on the Q value. According to the method, the individuation capability and the real-time response efficiency of the education large model can be comprehensively improved.