35 results about "Probabilistic graph" patented technology

A location system for locating and determining the motion and velocity of a wireless device. The methods include direct inferences about whether a device is in motion versus static based on a statistical analysis of the variation of radio signal strengths over time. The system is trained according to a sparse set of identified locations from which signal strengths are measured. The system uses the signal properties of the identified locations to interpolate for a new location of the wireless device. The system uses a probabilistic graph where the identified locations of the floor plan, expected walking speeds of pedestrians, and independent inference of whether or not the device is in motion are used to determine the new location of the device.

Multi-source multi-modal activity recognition for conducting aerial video surveillance comprising detecting and tracking multiple dynamic targets from a moving platform, representing FMV target tracks and chat-messages as graphs of attributes, associating FMV tracks and chat-messages using a probabilistic graph based mapping approach; and detecting spatial-temporal activity boundaries.

The present invention relates to a method and apparatus for detecting and tracking vehicles. One embodiment of a system for detecting and tracking an object (e.g., vehicle) in a field of view includes a moving object indication stage for detecting a candidate object in a series of input video frames depicting the field of view and a track association stage that uses a joint probabilistic graph matching framework to associate an existing track with the candidate object.

A method for predictive analytics in a semi-structured process including receiving traces of the semi-structured process, at least one of the traces including a document content value, determining a process model from the traces, the process model comprising tasks at nodes of the semi-structured process and embodies all possible execution sequences in the process, determining a probabilistic graph including a probability at each of the tasks of the semi-structured process advancing from one task to another task, and combining the process model and probabilistic graph to determine a probabilistic process model including probabilities and strengths of transitions between tasks.

A plurality of landmarks are automatically located on a 3-dimensional polygonal mesh of connected vertices. A probabilistic graph is generated for the plurality of landmarks pre-identified on each of a first set of 3-dimensional models. The graph represents local surface characteristics for each landmark and relational positions between neighboring pairs of landmarks. Local surface characteristics are determined for each vertex of the mesh. For each landmark, a set of the vertices is identified that satisfies a criteria based on a surface difference between the vertex local surface characteristics and the landmark local surface characteristics. A relational position for each pair of vertices from the sets of vertices corresponding to the neighboring pairs is determined based on the graph. One of the vertices is determined for each of the plurality of landmarks to minimize the surface difference and the relational difference for the landmark.

Propagating data in a technical network by considering runtime requirements. A component tree data structure is generated for a probabilistic graph representing the technical network and its technical constraints. On the component tree a propagation algorithm is applied, which iteratively determines an optimal edge in the generated component tree, which maximizes an expected information flow to a query node to and/or from each network node by considering the technical network constraints and by executing a Monte-Carlo sampling for estimation of the expected information flow for the cyclic components and by computing the expected information flow of the non-cyclic components analytically and which updates the component tree iteratively with each determined optimal edge and re-estimates the expected information flow in the updated component tree for providing a result with nodes in the technical network for data propagation, so that information flow is maximized by considering technical network constraints.

The invention provides an expert system updating method and device, and a business processing method and device. The expert system updating method comprises the steps: acquiring a probability graph network corresponding to at least one reference expert system, wherein the reference expert system and the target expert system are used for outputting a business decision result corresponding to the target business based on the business feature data of the same target business; acquiring the sample business feature data and optimization target data of the target business; and based on the data, combining the probabilistic graph networks of the reference expert system and the target expert system to carry out graph structure learning, and outputting graph structure updating information of the probabilistic graph network of the target expert system. According to the embodiment of the invention, the expert system has the capability of learning the graph structure, and the decision result of the expert system is more accurate.

The invention discloses a method for classifying problems on the basis of PGM (probabilistic graph models). The method includes a modeling phase and an inferring phase. The first phase includes manually classifying training datasets; substituting the classified labeled datasets into the probabilistic graph models; constructing network structures of directed acrylic nets; computing prior probability and conditional probability of various observation nodes to obtain conditional probability distribution of models. The second phase includes carrying out Bayesian inference on the basis of Gibbs algorithms according to existing network structures and the CPD (conditional probability distribution) to obtain categories of the problems. Compared with existing algorithms for classifying problems, the method has the advantages that the probabilistic graph models are built, the models are trained by the aid of training data, the problems are classified by the aid of trained models, and accordingly the method not only has the characteristic of high interpretability of processes for classifying problems on the basis of rules, but also has merits of independence from expert knowledge and automatic learning of processes for classifying problems on the basis of machine learning.

The invention discloses an electric power monitoring system network security alarm evaluation method based on a probabilistic graph model, which belongs to the technical field of electric power monitoring system network security, and comprises the steps of merging and screening original alarm data, forming an electric power monitoring system feature alarm sequence, extracting a feature vector, making a probability model; and judging a power monitoring system network security alarm threat. According to the method, alarms with high threats can be quickly identified from massive network security alarms of the power monitoring system, and the method has very important significance for next emergency response and quick recovery of a service system.

The invention provides anerror evaluation method for multiple approximation technologies based on probabilistic graph model in special accelerator, wherein the approximation technology combination of any part is rapidly assessed and selected through the probability graph model, and on the premise that the output quality is guaranteed, the power consumption is reduced to the maximum extent. The method at least comprises the steps: converting a data flow diagram of a specified application into a Bayesian network of a probabilistic graph model according to a predefined mapping rule, the network comprising approximate configuration nodes in two states and input nodes in three states; then establishing an efficient and accurate dependency subgraph based on structure learning, and determining a conditional probability table of each node based on node parameter learning according to configuration of different approximation technologies; and according to a variable elimination inference algorithm, based on a Bayesian network and a conditional probability table, accurately solving a required marginal probability, and outputting an error distribution condition.

The invention provides an enterprise credit evaluation method and device and electronic equipment. The method comprises the steps of obtaining feature information of a to-be-evaluated enterprise, wherein the feature information comprises dimension indexes and enterprise data corresponding to each dimension index, and the dimension indexes comprise at least one of a total order completion rate, a cost profit rate, a product quality qualification rate, an on-time delivery rate, an order management cost, an inventory cost and a communication cost; inputting the feature information into a pre-trained probabilistic graph model, so that the probabilistic graph model outputs a credit value of the to-be-evaluated enterprise according to the feature information, wherein the probabilistic graph model is obtained based on enterprise relationship training in the supply chain; therefore, the relation between other enterprises and the to-be-evaluated enterprise is effectively utilized from the angle of the supply chain of the enterprise in the enterprise credit value evaluation process by utilizing the probability graph model, the evaluation method is enriched, and the credit value precision of the to-be-evaluated enterprise is improved.

The invention provides a network table column type detection method based on a probabilistic graph model, and belongs to the field of table interpretation in a semantic network. The method comprises the following steps: splicing tables belonging to the same mode from the same website into a table; performing single-column classification on the spliced table: firstly, dividing columns in the spliced table into numeric type columns and character type columns, and then classifying the numeric type columns and the character type columns respectively; and on the basis of a single-column classification result, a probabilistic graph model is constructed to mine a semantic relationship implied between columns, so that the column type sequence of the whole table is detected. According to the method, the semantic type of the column in the network table can be detected, a good effect is achieved, and compared with other column type detection methods, the accuracy is improved by 10% or above.