Abstract: Systems and method described herein present techniques for identifying a gesture using gesture data compressed by principal joint variable analysis. A classifier of a gesture recognition system may receive a frame comprising a set of gesture data points identifying locations of body parts of a subject. The classifier may determining that a subset of the set of gesture data points is sufficient to recognize a first gesture. The subset may be stored into a database in reference to the first gesture. A recognizer may receive a new frame of new gesture data points identifying locations of body parts of a new subject. The recognizer may recognize that the gesture of the new subject corresponds to the first gesture responsive to comparing at least one new gesture data point from the new frame to at least one gesture data point of the subset.
Abstract: A machine learning classifier based procurement system determines a price risk score, a supplier risk score, and an item risk score for bids based on classifications performed by a machine learning classifier. The scores are compared to respective thresholds to determine if any of the bids are associated with a high-risk procurement.
Type:
Grant
Filed:
February 22, 2017
Date of Patent:
June 13, 2017
Assignee:
ACCENTURE GLOBAL SOLUTIONS LIMITED
Inventors:
James Hoover, Jeffrey Scott Miller, Lisa Wester, Randall C. Gowat
Abstract: A method, apparatus and computer program product are provided for generating and utilizing a user pattern profile. In this regard, the user pattern profile can include information regarding service selections made on a user node and movements of a user. The generated user pattern profile can compared to a threshold profile, and based on the results of the comparison, an action can be undertaken.
Abstract: A system, method and a computer program product may be provided for automatically creating and parameterizing a semantically-enriched diagnosis model for an entity. The system receives a list of data points, from sensors or a database, to be used to create a diagnosis model. The system automatically creates the diagnosis model based on the received list of data points and data stored in a database and parameterizes the diagnosis model. The parameterized diagnosis model reflects rules that determine one or more potential causes of one or more abnormalities of one or more physical conditions in the entity.
Type:
Grant
Filed:
December 30, 2013
Date of Patent:
June 13, 2017
Assignee:
International Business Machines Corporation
Abstract: A medical general intelligence computer system and computer-implemented methods analyze morpho-physiological numbers for determining a risk of an emergent disease state, determining an emergent disease state, predicting a pre-emergent disease state, determining a pre-emergent disease state, and/or predicting a risk of a pre-emergent disease state.
Abstract: An improved content search mechanism uses a graph that includes intelligent nodes avoids the overhead of post processing and improves the overall performance of a content processing application. An intelligent node is similar to a node in a DFA graph but includes a command. The command in the intelligent node allows additional state for the node to be generated and checked. This additional state allows the content search mechanism to traverse the same node with two different interpretations. By generating state for the node, the graph of nodes does not become exponential. It also allows a user function to be called upon reaching a node, which can perform any desired user tasks, including modifying the input data or position.
Type:
Grant
Filed:
April 21, 2016
Date of Patent:
May 16, 2017
Assignee:
Cavium, Inc.
Inventors:
Muhammad R. Hussain, David A. Carlson, Gregg A. Bouchard, Trent Parker
Abstract: The present invention is a biometric security system and method operable to authenticate one or more individuals using physiological signals. The method and system may comprise one of the following modes: instantaneous identity recognition (MR); or continuous identity recognition (CIR). The present invention may include a methodology and framework for biometric recognition using physiological signals and may utilize a machine learning utility. The machine learning utility may be presented and adapted to the needs of different application environments which constitute different application frameworks. The present invention may further incorporate a method and system for continuous authentication using physiological signals and a means of estimating relevant parameters.
Type:
Grant
Filed:
May 10, 2012
Date of Patent:
May 9, 2017
Assignee:
Nymi Inc.
Inventors:
Foteini Agrafioti, Francis Minhthang Bui, Dimitrios Hatzinakos
Abstract: Embodiments are generated directed to method, medium, and system including processing circuitry to generate records including randomly selected events for each of one or more subjects having one or more of the same category parameters as a subject of a particular event. The processing circuitry may also present, on a display device, a computer-generated model based on the records, the model having a decision tree data structure having decision tree nodes corresponding with historical events from the records, each of the decision tree nodes having an indication of a likelihood of occurrence for the particular event based on whether a corresponding history event of the decision tree node occurred or did not occur within a specific time period. Embodiments of the real-time distributed nature of the systems and processing discussed herein can solve big data analytics processing problems and facilitate data anomaly detection.
Type:
Grant
Filed:
September 23, 2016
Date of Patent:
May 9, 2017
Assignee:
SAS Institute Inc.
Inventors:
Steven William Enck, Emily Chapman-McQuiston, Daniel Kelly
Abstract: A method and system for providing an answer to a subscription-based query service. The method includes acquiring context information and evidence information from one or more electronic devices based on a query. One or more belief values are assigned based on the evidence information and the context information. The belief values are aggregated for determining a score for competing hypotheses using a probabilistic model. Sufficiency of hypotheses is determined based on statistical significance for potential answer information to the query.
Abstract: An interface device and method of use, comprising audio and image inputs; a processor for determining topics of interest, and receiving information of interest to the user from a remote resource; an audiovisual output for presenting an anthropomorphic object conveying the received information, having a selectively defined and adaptively alterable mood; an external communication device adapted to remotely communicate at least a voice conversation with a human user of the personal interface device. Also provided is a system and method adapted to receive logic for, synthesize, and engage in conversation dependent on received conversational logic and a personality.
Abstract: Systems, methods, and devices use search terms, current state information, historical data, and expected location hints to predict where a user may be when a search may be relevant. In an embodiment, search terms entered on a first user computing device may be combined with location information resident on a second user computing device to determine where a user is likely to be and what results are likely to be relevant to a user in the future. In a further embodiment, relevant search terms indicative of time, such as “tomorrow” or “tonight,” and/or user-related information may also be used to return predictive search results. In a further embodiment, user-related information from other users may also be used to return predictive search results.
Type:
Grant
Filed:
January 30, 2015
Date of Patent:
April 25, 2017
Assignee:
QUALCOMM Incorporated
Inventors:
Yashwanth Prakash, Charles Wurster, Eric Bilange
Abstract: The present disclosure relates generally to the field of automatically learning and automatically adapting to perform classification of protected data. In various examples, learning and adapting to perform classification of protected data may be implemented in the form of systems, methods and/or algorithms.
Type:
Grant
Filed:
March 7, 2014
Date of Patent:
April 18, 2017
Assignee:
International Business Machines Corporation
Abstract: Learning to rank modeling in the context of an on-line social network is described. A learning to rank model can learn from pairwise preference (e.g., job posting A is more relevant than job posting B for a particular member profile) thus directly optimizing for the rank order of job postings for each member profile. With ranking position taken into consideration during training, top-ranked job postings may be treated by a recommendation system as being of more importance than lower-ranked job postings. In addition, a learning to rank approach may also result in an equal optimization across all member profiles and help minimize bias towards those member profiles that have been paired with a larger number of job postings.
Type:
Grant
Filed:
June 30, 2015
Date of Patent:
April 18, 2017
Assignee:
LinkedIn Corporation
Inventors:
Lijun Tang, Eric Huang, Xu Miao, Yitong Zhou, David Hardtke, Joel Daniel Young
Abstract: An intelligent control system based on an explicit model of cognitive development (Table 1) performs high-level functions. It comprises up to O hierarchically stacked neural networks, Nm, . . . , Nm+(O?1), where m denotes the stage/order tasks performed in the first neural network, Nm, and O denotes the highest stage/order tasks performed in the highest-level neural network. The type of processing actions performed in a network, Nm, corresponds to the complexity for stage/order m. Thus N1 performs tasks at the level corresponding to stage/order 1. N5 processes information at the level corresponding to stage/order 5. Stacked neural networks begin and end at any stage/order, but information must be processed by each stage in ascending order sequence. Stages/orders cannot be skipped. Each neural network in a stack may use different architectures, interconnections, algorithms, and training methods, depending on the stage/order of the neural network and the type of intelligent control system implemented.
Type:
Grant
Filed:
September 3, 2015
Date of Patent:
April 11, 2017
Inventors:
Michael Lamport Commons, Mitzi Sturgeon White
Abstract: A method is provided for estimating past data by identifying a high frequency data set for a defined time period. A pattern is calculated for the high frequency data set and then the pattern is applied to a low frequency data set in a past time period to estimate a high frequency query point.
Type:
Grant
Filed:
August 4, 2015
Date of Patent:
April 11, 2017
Assignee:
Amazon Technologies, Inc.
Inventors:
Muhammad Ali Siddiqui, Charles Graham Haver Crissman, Sanjeev Kewal Verma, Mark Christopher Veronda
Abstract: A system, method and computer program product for interfacing a decision engine and a marketing engine in order to provide vendor-related data in response to decision-related data is disclosed. In at least one embodiment, the system and method may include providing a decision engine on a user-accessible network; interfacing a marketing engine with the decision engine on the network; receiving a plurality of user inputs with the decision engine; processing decision-related data with the decision engine in accordance with the plurality of user inputs; sharing the decision-related data with the marketing engine; processing the decision-related data with the marketing engine; and transmitting vendor-related data via the network.
Abstract: A computer-program causing a computing device to perform an association measurement between a target variable and each non-target variable of a data set; select non-target variables for inclusion in a visualization based on the degree of association; perform correspondence analysis between target values of the target variable and non-target values of each selected non-target variable; order target value markers within a target row based on the degrees of closeness; order non-target value markers within each non-target row based on the degrees of closeness; determine a width of each target value marker based on a frequency of occurrence of its target value in the data set; determine a width of each non-target value marker based on a frequency of occurrence of its non-target value in the data set; and cause generation of the visualization with connection markers emanating from the target value markers and extending among the non-target value markers.
Abstract: Electronic devices and methods for processing an input content are disclosed. The method includes: obtaining a first input content through a first operation; displaying the first input content on the display unit, the first input content comprising at least two elements; determining a first element from the at least two elements in accordance with a predetermined rule; obtaining a second element through a second operation, the second element not belonging to the at least two elements; updating the first element with the second element at the position where the first element has been displayed on the display unit; and displaying the second element on the display unit.
Abstract: An apparatus and method are disclosed for providing feedback and guidance to touch screen device users to improve text entry user experience and performance by generating input history data including character probabilities, word probabilities, and touch models. According to one embodiment, a method comprises receiving first input data, automatically learning user tendencies based on the first input data to generate input history data, receiving second input data, and generating auto-corrections or suggestion candidates for one or more words of the second input data based on the input history data. The user can then select one of the suggestion candidates to replace a selected word with the selected suggestion candidate.
Type:
Grant
Filed:
June 27, 2014
Date of Patent:
April 4, 2017
Assignee:
Microsoft Technology Licensing, LLC
Inventors:
Eric Norman Badger, Drew Elliott Linerud, Itai Almog, Timothy S. Paek, Parthasarathy Sundararajan, Dmytro Rudchenko, Asela J. Gunawardana
Abstract: A tag recommendation for an item to be tagged is generated by: selecting a set of candidate neighboring items in an electronic social network based on context of items in the electronic social network respective to an owner of the item to be tagged; selecting a set of nearest neighboring items from the set of candidate neighboring items based on distances of the candidate neighboring items from the item to be tagged as measured by an item comparison metric; and selecting at least one tag recommendation based on tags of the items of the set of nearest neighboring items. The item comparison metric may comprise a Mahalanobis distance metric trained on the set of candidate neighboring items to correlate the trained Mahalanobis distance between pairs of items of the set of candidate neighboring items with an overlap metric indicative of overlap of the tag sets of the two items.
Type:
Grant
Filed:
February 28, 2011
Date of Patent:
March 21, 2017
Assignee:
XEROX CORPORATION
Inventors:
Mohamed Aymen Benzarti, Boris Chidlovskii, Nishant Vijayakumar