998 results about "Graph model" patented technology

For resonance image data of an imaged subject, a method that first detects and estimates the dominant motions of k-space data (i.e., the motion vectors) and then constructs a graphical model for each estimated motion vector. The segments of the k-space that are determined to be corrupted by motion are restored by minimizing the energy associated with the corresponding graphical model. Consequently, the MR image of the imaged subject becomes free of motion artifacts.

The invention relates to a criminal suspect mining association method and a system based on social network analysis and is characterized in that the method comprises the following steps: pre-processing the user input data, extracting the key information from the input data; establishing the social network graph model; setting the parameter; executing the community discovery algorithm; outputting the discovery result and listing the criminal suspects; compared with the prior art, the method and the system have the beneficial effects as follows: the potential associated criminal suspect can be found from the social circle of the given criminal suspect, the method is good in performance and fast in system operation, by considering the requirement of the real scenes, good expansibility can be achieved for analyzing in the range appointed by the user.

The invention discloses a traffic congestion prediction method and system based on a traffic congestion propagation model. The method comprises: a historical track of a vehicle is obtained and a passing speed of the vehicle when passing through a first road section is calculated; according to the passing speed, a vehicle driving threshold is calculated; if an instantaneous driving speed of the current vehicle is lower than the vehicle driving threshold, traffic congestion is determined; and a road section with the monthly traffic congestion occurrence frequency larger than a predetermined frequency is determined to be a frequent traffic congestion section, a congestion sub graph is generated based on the frequent traffic congestion section, and the congestion sub graph is calibrated based on the probability of concurrence of traffic congestion of all connected sections and then a traffic congestion probability graph model is generated to predict a traffic congestion situation. Therefore, the accurate road traffic state can be extracted by using multi-source track big data, thereby completing the urban traffic congestion propagation analysis and discovering a traffic congestion source. Therefore, traffic congestion occurrence is reduced and the trip cost of the vehicle owner is saved.

The invention belongs to the technical field of network security, and particularly relates to a network attack target identification method and a network attack target identification system based on an attack graph, wherein the method comprises the following steps: modeling for a state migration process of an attacker in a network, acquiring a network attack graph model and all possible attack paths, and generating a network attack graph; mapping the network attack graph to a Markov chain, and constructing a state transition probability matrix which absorbs the Markov chain; and in combinationwith the state transition probability matrix, acquiring an expectancy for success probability matrix of attack intention of the attacker; through the expectancy for success probability matrix, finding out a state node corresponding to the maximum probability value, and completing attack target identification. With the method and the system provided by the invention, an average probability value of realizing different intentions of the attacker can be evaluated more objectively and accurately, a problem that the conventional method is limited by ideal cumulative probability when evaluating probability of occurrence of attacks is solved, computation complexity is low, operations are simple and convention to execute, and more reliable guidance is provided for assisting a security administrator to make a decision and improving network security performance.

The invention discloses a CT image liver segmentation method and system based on characteristic learning, being able to effectively improve the segmentation precision of the liver in a CT image. The method comprises the steps: S101: reading a training image set and an image to be segmented, wherein the training images in the training image set and the image to be segmented are the CT images of a belly; S102: extracting the Haar characteristic of the training images and the image to be segmented, the local binary pattern characteristic, the directional gradient histogram and the co-occurrence matrix characteristic; S103: utilizing a principal component analysis method to perform characteristic fusion on all the extracted characteristics so as to acquire more effective characteristics; S104: utilizing a classifier to classify the characteristics of each pixel of the image to be segmented to obtain a liver probability graph; and S105: combining the liver probability graph with the image to be segmented, modifying the graph model weight of a random walk segmentation algorithm to realize segmentation of the liver.

The invention discloses a method for predicting dynamic social network user behaviors based on a computer probability graph model, which comprises the following steps of: 1, performing objective statistical analysis on the dynamic social network user behaviors in terms of social influence, time dependence and network correlation; 2, performing formal definition on the dynamic social network user behaviors by adopting computer technical means such as a graph theory, a set, a matrix theory and the like; 3, establishing a dynamic anti-noise factor graph model according to the definition in the step 2; 4, learning the dynamic anti-noise factor graph model, and estimating a value Theta of a series parameter from given historic records; and 5, predicting the user behaviors according to the Theta to obtain prediction results. By the method, modeling and accurate prediction are performed on the dynamic social network user behaviors from a micro level.

The present invention discloses a human body behavior prediction method based on human body skeleton movement information, comprising the following steps: calculating a normalized relative orientative feature of each articulation point of each limb by using human body skeleton information extracted from an RGB D image; carrying out dynamic segmentation on a feature sequence by using a segmentation method based on feature sequence potential difference so as to acquire a posture feature sub-sequence and an action feature sub-sequence; extracting a key posture and an atomic action from the posture feature sub-sequence and the action feature sub-sequence, and constructing a multi-layer graph model based on the key posture and the atomic action; extracting a human body sub-behavior pattern contained in the multi-layer graph model, and constructing a context probability statistical model of the human body sub-behavior pattern; and carrying out identification and prediction of the human body sub-behavior pattern. The human body behavior prediction method based on the human body skeleton movement information has strong robustness for body differences, spatial position differences and the like between different individuals, has strong generalization capability for action differences between different individuals in the same category of behaviors, and has strong identification capability for the action similarity between different categories of behaviors.

An automated method and system for the implementation of a hierarchical event relationship network for correlation analysis in a distributed computing environment in which events are defined based on a connected graph model. Event handling information for each event type to be monitored is used to customize a plurality of rule templates for each type within an event source, where the event source is a hardware component, an application software component or an operating system platform. A plurality of event relationship network rules are verified to ensure they do not violate an event protocol. A hierarchical class definition and naming structure is generated from the plurality of event relationship network rules for each event source. Event management rules are then generated automatically for each event type from the event relationship network rules and the rule templates. The event management rules are loaded into a rule-based event manager. The performance of the rule-based event manager is then monitored.

Various aspects of the present invention include a database interaction system and method comprising: a display, a set of user input devices, and a database comprising a data set including a plurality of fields and associated field values; a graph model configured to define a plurality of nodes and states, each node representing a field from the plurality of fields; a graph-to-data mapper configured to map the field values to states contained in the nodes of the graph model; and a graphical interface module configured to generate for display one or more nodes from the plurality of nodes, wherein a display of a node includes a graphical representation of field values associated with a specific field represented by the displayed node and states contained therein.

The invention discloses a virtual network function rapid mapping algorithm based on a satellite network. The algorithm comprises the following steps of: designing a satellite network-based software defined network and a network function virtualization collaborative deployment framework; And designing a virtual network function dynamic mapping method. According to the software defined network and network function virtualization collaborative deployment framework designed by the invention, network functions can be decoupled from hardware equipment, so that the flexibility and the destroy resistance of the network are improved. The virtualized network function dynamic mapping method comprises two steps that a feasible mapping path set in one operation period of a satellite network is calculated in a static step, and the feasible mapping paths are weighted and sorted according to the extended length of the mapping time; In the dynamic step, a graph model matching algorithm is adopted to match an optimal mapping path from feasible mapping paths with different weights in a time slice, and meanwhile, an arrangement strategy is formulated. Time delay can be greatly reduced, and the requirement for high-dynamic change of a satellite network topological structure is met.

The invention discloses an image sequence category labeling method based on a mixed graph model. The method comprises a step of performing superpixel segmentation of an image sequence and characteristic description of superpixels; a step of performing nearest neighbor matching of inter-frame superpixels of a two-continuous-frame image; a step of using the mixed graph model to carry out global optimization modeling of the image sequence category labeling based on the spatial domain adjacency relation among superpixels of a single frame image and the time domain matching relation among superpiexels of a multi-frame image; and a step of using a linear method to solve a global optimization problem to obtain category labels of superpixles of a continuous multi-frame image. Compared with previous graph models, the mixed graph model created by the invention can describe the first-order and symmetric relation among superpixels in a single frame image and also the high-order and non-symmetric relation among superpixels in a two-continuous-frame image; the linear method is used for solution; and a category label which is better in consistency of time domain and higher in accuracy is effectively provided for each superpixel of an image sequence.

The invention discloses a CT image liver segmentation method and system based on multi-scale weighting similarity measure and capable of accurately segmenting a liver area. The method comprises steps of: S101, reading a training image set and a to-be-segmented image; S102, preprocessing the read image data; S103, extracting superpixels from an area around an initial bound and a liver bound in the to-be-segmented image; S103, by using the central point of each superpixel in the to-be-segmented image as a center, selecting all pixels within a certain neighborhood as test blocks and selecting multi-scale image blocks with the same positions and sizes from training images as training blocks to obtain a training block set; S105, computing the similarity measure between the test blocks and the training block set to obtain the prior probability that each superpixel around the liver bound in the to-be-segmented image belongs to the liver; and S106, modifying a randomly moving graph model weight value in combination with a prior model and the to-be-segmented image so as to segment the liver in the to-be-segmented image.

The invention discloses a semantic high-precision map construction method based on dot-line feature fusion laser, which comprises the following steps: 1) performing semantic segmentation and feature extraction on a visual image acquired by a camera to obtain a visual image containing semantic categories and dot-line features, and then obtaining a foreground and a background of a moving target; 2)projecting the laser three-dimensional point cloud acquired by the laser radar onto a visual image plane, fitting to obtain a depth map, and endowing the laser three-dimensional point cloud with semantic categories and dot line features; 3) performing super-pixel segmentation on the moving target, calculating the distance between super-pixel blocks, constructing a graph model, performing image segmentation, and accurately extracting the boundary of the moving target; and 4) removing the visual feature points and the laser three-dimensional points belonging to the moving target to construct a static high-precision semantic three-dimensional map. The invention further discloses athe positioning method of the semantic high-precision map constructed by adopting the method, and the mapping is more accurate and reliable by accurately removing the moving target.

The invention discloses a semantic data query system with optimized storage, comprising a semantic data importing module, a semantic data storage management module, a stored data persistence module and a semantic data query module. The system supports import of various regularly described resource description framework data, and can map a storage model to a magnetic disc, thereby implementing quick reproduction of an internal memory storage model. In the system, a query graph model operable to a bottom-layer storage model is formed by transforming and processing the semantic data query; a cost model for querying connection operations is established by counting bottom-layer stored data, and an optimization module for the semantic data query is implemented through a greedy algorithm; and sequence of query is regulated, so that query performance is improved.

The invention discloses a session recommendation method based on a space-time sequence diagram convolutional network. The method comprises the following steps: S1, modeling all session sequences intoa directed session graph; S2, constructing a global graph by taking common commodities in the session as links; S3, embedding an ARMA filter into a gated graph neural network, extracting a topologicalgraph signal which changes over time from the graph model, and obtaining a feature vector of each node involved in the session graph; S4, obtaining global preference information from historical sessions of the user by adopting an attention mechanism; S5, obtaining local preference information of the user from the last session clicked by the user, and obtaining final preference information of theuser in combination with the global preference information; S6, predicting the probability of possible occurrence of the next clicked commodity in each session, and giving a Top-K recommended commodity. According to the method, rich context relationships of clicked commodities can be captured from the global graph, global and local preferences of the user are accurately learned, the time attenuation effect of historical preferences of the user on current preferences is effectively evaluated, and accurate commodity prediction is provided.

A path computation method includes defining photonic constraints associated with a network, wherein the photonic constraints include wavelength capability constraints at each node in the network, wavelength availability constraints at each node in the network, and nodal connectivity constraints of each node in the network, and performing a constrained path computation in the network using Dijkstra's algorithm on a graph model of the network with the photonic constraints considered therein. An optical network includes a plurality of interconnected nodes each including wavelength capability constraints, wavelength availability constraints, and nodal connectivity constraints, and a path computation element associated with the plurality of interconnected photonic nodes, wherein the path computation element is configured to perform a constrained path computation through the plurality of interconnected nodes using Dijkstra's algorithm on a graph model with the photonic constraints considered therein.

The invention discloses a method drawing up a multi-goal reservoir optimization scheduling graph capable of being self-adaptive to climate change. The method for drawing up the multi-goal reservoir optimization scheduling graph comprises the steps of: step 1. establishing a coupling model of a global climate model (GCM) and a variable infiltration capacity (VIC) hydrological model so as to forecast a run-off process under a future climate change scene; step two. establishing a multi-goal reservoir optimization scheduling graph model; and step 3. taking the forecast run-off process data under the future climate change scene as the input of the optimization scheduling graph model, and drawing up the multi-goal optimization scheduling graph model by adapting a self-adaptive genetic algorithm. The method for drawing up the multi-goal reservoir optimization scheduling graph has the advantages of balancing the social economy goal and ecological goal of reservoir scheduling, improving the comprehensive benefits of reservoir scheduling to the maximum degree on the condition of ensuring the flood control safety of a reservoir and being capable of being self-adaptive to future climate change and being widely applied to the production practice of multi-goal reservoir optimization scheduling.

The invention discloses a multiple-unmanned-aerial-vehicle multiple-ant-colony collaborative target searching method. The multiple-unmanned-aerial-vehicle multiple-ant-colony collaborative target searching method comprises the following steps that S1, a grid method is adopted to divide and mark a searching sea area, and a target probability graph model is established; S2, a target function is established, and the unmanned aerial vehicle steering price, the unmanned aerial vehicle collision threat price and the searching probability are subjected to weighted summation; and S3, a multiple-ant-colony algorithm is adopted to conduct collaborative path optimizing design on multiple unmanned aerial vehicles, and by setting the maximum number N<max> of iteration times, the S32 and S33 are executed until the maximum number of iteration times is met and the optimal searching path is output. According to the multiple-unmanned-aerial-vehicle multiple-ant-colony collaborative target searching method, the probability graph characteristics of a target in the sea area are fully utilized to design the new ant colony pheromone comprising local initialization, global initialization and updating rules, thus through the ant algorithm, trajectory planning of the unmanned aerial vehicles can be quickly completed, the problem of repeated searching is avoided, the searching paths of the unmanned aerial vehicle cross, and the searching efficiency is improved.

The present invention discloses an entity linkage algorithm based on a graph model. The entity linkage algorithm based on a graph model is characterized by comprising: forming a candidate entity by using the Wikipedia knowledge base; constructing a semantic feature between the entities by using LDA; constructing relationships between entities based on linkage structures of Wikipedia to form a graph model; and integrating related semantic features into the graph model; and ranking the entities by using the PageRank algorithm to obtain an entity linkage result, which specifically comprises steps of calculation and integration of a naming dictionary, a candidate entity set, related features, construction of the graph model, and ranking of candidate entities. Compared with the prior art, the entity linkage algorithm based on a graph model has the advantages of being good in entity feature integration and high in reliability of the entity linkage result; data is downloaded by using Wikipedia, so that no additional costs are needed, and especially data sets do not need to be noted manually; and the method is simple, convenient in usage, and saves time and efforts.

The invention provides a random walking image automatic annotation method and device based on a label graph model. The method comprises the following steps: providing an annotated image set and an image to be annotated; acquiring an adjacent image set related to the image to be annotated; acquiring a candidate label set; constructing a co-occurrence matrix; acquiring a typical vector; constructing a tendency matrix for the candidate label set according to the typical vector; fusing the co-occurrence matrix and the tendency matrix, so as to obtain a relation matrix; constructing a label graph model; and carrying out random walking on the label graph model, so as to obtain a weight vector of a node; and determining the label of the image to be annotated according to the corresponding weightvalue of each node in the weight vector. The method can be used for effectively annotating the images according to the co-occurrence relation and tendency relation between the labels; and the method has the advantage of accuracy in annotation; the image automatic annotation device has the advantages of being simple in structure and being easy to realize.

The invention discloses a short text classification method based on semantic graphs, which is characterized by including the steps: A, constructing a semantic graph model for each piece of text information, and combining all semantic graph models; B, comparing similarity level among different texts according to the semantic graph models and by means of a similarity computing method; and C, according to the text similarity level, classifying the texts by the aid of a text semantic graph classifier. The short text classification method based on the semantic graphs has the advantages that semantic connotations of documents can be highlighted to a maximum degree by using the graph models to represent the texts, latent semantic information and theme features in the texts can be accurately described to a great extent by the aid of the TSG (text semantic graph) models constructed by the method, and the TSG classification method can be more reliable and efficient in use as compared with other classification methods by means of the feature, so that human cost is greatly reduced, artificial arrangement of the text information is avoided to a great extent, and the text information is automatically organized by a computer.

The invention provides a customized recommendation method based on graphs and can effectively reduce influence of sparsity on the recommendation effect. According to the method, a first step, a hidden meaning model is utilized to calculate historical scoring records of users to acquire hidden relationships among users and among objects; a second step, similarity among the users is calculated by utilizing the hidden relationships acquired in the first step, similarity among the objects is calculated, and a user graph and an object graph are constructed for the similar users and the similar objects; a third step, a user-object graph model is constructed by utilizing a user graph model and an object graph model acquired in the second step and a bipartite graph of the users and the objects acquired through utilizing the historical scoring records of the users; and a fourth step, the access probability of objects without scoring record of each user is ordered in a descending mode by utilizing a random walk personalrank algorithm, and front N objects are acquired to form a recommendation list for recommendation to the users.

The present invention discloses a Chinese integrated entity linking method based on a graph model. An ambiguous entity in a text can be mapped into a specific entity in a real world, in order to provide aid for knowledge base expansion, information extraction and search engines. The method mainly comprises three parts of generating a candidate entity, constructing an entity indicator diagram, and disambiguating an integrated entity. For a given text, an entity referent item therein is recognized to obtain the candidate entity. The entity referent item and the candidate entity thereof are regarded as graph nodes to construct an entity referent graph. An in-degree and out-degree algorithm is applied to the entity indicator diagram for implementing disambiguation of multiple ambiguous entities in the text. The present invention does not depend on the knowledge base completely in the establishment of the entity indicator diagram, and also can implement incremental evidence mining to find evidence on an encyclopedia webpage. Dependence path analysis is employed to find the possibly related entity referent item. When the dependence path sizes of two entity referent items are within a set range, the two entity referent items are regarded as the possibly related entity referent items. Further, whether their candidate entities have relations in the real world is determined, so that the efficiency of disambiguation is greatly improved.

The invention discloses a shape collaborative segmentation method based on graph convolution network. The method of the invention comprises the following steps: a given group of shapes are overly segmented into sub-slices, and a graph model among the sub-slices is constructed. some of the sub-slices are labelled; A graph convolution network is constructed to propagate the labeled sub-chip label information to other non-labeled sub-chips. The invention applies graph convolution network to the field of shape collaborative segmentation, and the invention can obtain higher accuracy result comparedwith other methods at present.

The invention provides a multi-scale multi-level image segmentation method based on a minimum spanning tree. Multi-scale multi-level image segmentation is expressed and realized by a graph model. The segmentation method is suitable for initial segmentation results obtained by various images and various rules to effectively combine over-segmented regions in high level segmentation, so an over-segmentation phenomenon is avoided; moreover, multi-scale segmentation results on different levels provides characteristic description information on different levels for analysis of target structural components; and the method is very important for target recognition.

The invention discloses a method for disambiguating entity names in a medical disease diagnosis record. Based on a heterogeneous concomitant disease network and a graph model, the entity names in the medical disease diagnosis record are disambiguated. The similarity between to-be-disambiguated entity names and candidate entity names is used as local information, and the contribution of other to-be-disambiguated entities in the same record to current to-be-disambiguated entities serves as global information, so that the accuracy of medical entity name disambiguation can be improved; the heterogeneous concomitant disease network is established according to the disease diagnosis record and annotation data, so that the relationships between the diseases and between the disease and the operation can be reflected more intuitively and credibly; and the entity names are subjected to standard name mapping accurately and efficiently, so that the problem of ambiguity of medical disease entity names in diagnosis information is solved, and the practical application demands are met.

The disclosure provides an object detection method and apparatus based on a Dynamic Vision Sensor (DVS). The method includes the following operations of: acquiring a plurality of image frames by a DVS; and, detecting the image frames by a recurrent coherent network to acquire a candidate box for objects to be detected, wherein the recurrent coherent network comprising a frame detection network model and a candidate graph model. By using a new recurrent coherent detection network, a bounding box for an object to be detected is fast detected from the data acquired by a DVS. The detection speed is improved greatly while ensuring the detection accuracy.

The invention belongs to the technical field of ocean remote sensing, and discloses an improved island shoreline segmentation system and segmentation method facing remote sensing data. remote sensing image data waveband combination selection based on an optimal index is carried out, and selected waveband combination data is taken as input data of island shoreline segmentation. Island shore line coarse segmentation based on a Deeplab neural network structure is carried out, and island shoreline optimization based on a full connection condition random field is carried out. The method and system are oriented to the remote sensing waveband data, and an optimal exponent formula is used for selecting a waveband combination training neural network most suitable for island shoreline segmentation; coarse segmentation and fine segmentation are carried out on the island shore line by combining a deep learning model and a probability graph model; and a 97.8% of MIoU value is obtained in the segmentation result is .

The invention discloses a photovoltaic hot spot effect detection method for an electricity-graph model and belongs to the field of photovoltaic power generation. The photovoltaic hot spot effect detection method for the electricity-graph model includes that firstly, regarding a photovoltaic cell panel as a whole body to build the electricity-graph model, wherein the electricity-graph model is built according to output voltage signals, load current signals and the like electric signals of the photovoltaic cell panel and infrared thermograms gathered by a thermal infrared imager; secondly, using the model to detect the running state of the photovoltaic cell panel and timely forecast and discover the hot spot effect of the battery panel. The potential safety hazard of a photovoltaic system due to delayed maintenance is avoided, and the reliability and stability of a photovoltaic power generation system are further improved.