Abstract: A digital sound identification system for storing a Markov model is disclosed. A processor is coupled to a sound data input, working memory, and a stored program memory for executing processor control code to input sound data for a sound to be identified. The sample sound data defines a sample frequency domain data energy in a range of frequency. Mean and variance values for a Markov model of the sample sound are generated. The Markov model is stored in the non-volatile memory. Interference sound data defining interference frequency domain data is inputted. The mean and variance values of the Markov model using the interference frequency domain data are adjusted. Sound data defining other sound frequency domain data are inputted. A probability of the other sound frequency domain data fitting the Markov model is determined. Finally, sound identification data dependent on the probability is outputted.
Abstract: In one implementation, a computer-implemented method includes accessing, by a computer system, information that describes use of one or more computer-based services by a particular user from one or more computing devices that are associated with the particular user; identifying one or more native applications that are associated with the one or more services, wherein the one or more native applications are configured to be installed and executed by one or more types of mobile computing devices; determining whether to recommend the one or more native applications based on the information and one or more threshold levels of use of the one or more computer-based services; and providing, based on the determining, a recommendation that is associated with the particular user and that identifies at least one of the one or more native applications.
Abstract: A computer-implemented artificial lift detection system, method, and software are provided for failure detection for artificial lift systems, such as sucker rod pump systems. The method includes providing artificial lift system data from an artificial lift system. Attributes are extracted from the artificial lift system data. Data mining techniques are applied to the attributes to determine whether the artificial lift system is detected to fail within a given time period. An alert is output indicative of impending artificial lift system failures.
Abstract: A technique of structuring a navigation database is provided, wherein the navigation database includes at least route link data for a predetermined geographic area. A method implementation of the technique includes organizing route link data associated with the predetermined geographic area into at least one routing cluster; providing the at least one routing cluster with a cluster identifier; and storing the at least one routing cluster together with the cluster identifier in the navigation database.
Abstract: Embodiments of the present invention provide for a method of identifying customer service and duplicate questions submitted by a user to a consultation system by creating a model from features extracted from questions previously identified as customer service questions, extracting features from a newly submitted question by performing phrasal analysis of the question, comparing the extracted features of the newly submitted question to the extracted features of the model, and determining whether the newly submitted question is a customer service question.
Abstract: A knowledge-based system under uncertainties and/or incompleteness, referred to as augmented knowledge base (AKB) is provided, including constructing, reasoning, analyzing and applying AKBs by creating objects in the form E?A, where A is a rule in a knowledgebase and E is a set of evidences that supports the rule A. A reasoning scheme under uncertainties and/or incompleteness is provided as augmented reasoning (AR).
Type:
Grant
Filed:
March 15, 2013
Date of Patent:
March 1, 2016
Inventors:
Eugene S. Santos, Eunice E. Santos, Evelyn W. Santos, Eugene Santos, Jr.
Abstract: A computer system iteratively executes a decision tree-based prediction model using a set of input variables. The iterations create corresponding rankings of the input variables. The computer system generates overall variables contribution data using the rankings of the input variables and identifies key input variables based on the overall variables contribution data.
Type:
Grant
Filed:
April 3, 2013
Date of Patent:
March 1, 2016
Assignee:
Applied Materials, Inc.
Inventors:
Deepak Sharma, Helen R. Armer, James Moyne
Abstract: Embodiments of the invention provide a neural core circuit comprising a synaptic interconnect network including plural electronic synapses for interconnecting one or more source electronic neurons with one or more target electronic neurons. The interconnect network further includes multiple axon paths and multiple dendrite paths. Each synapse is at a cross-point junction of the interconnect network between a dendrite path and an axon path. The core circuit further comprises a routing module maintaining routing information. The routing module routes output from a source electronic neuron to one or more selected axon paths. Each synapse provides a configurable level of signal conduction from an axon path of a source electronic neuron to a dendrite path of a target electronic neuron.
Type:
Grant
Filed:
August 28, 2012
Date of Patent:
March 1, 2016
Assignee:
International Business Machines Corporation
Abstract: Generally discussed herein are systems and methods for probabilistic name matching. In one or more embodiments a method can include determining a first set of possible intended names as a function of a first name, determining a second set of possible intended names for each name in a set of names in a name variant database, and probabilistically matching a name from the first set of possible intended names to a name from the second set of possible intended names. Probabilistically matching can include determining a weight associated with typing the first name but intending to type another name in the first set of possible intended names and determining the probability of typing a name in the set of names in the name variant database but intending to type a name from the second set of possible intended names.
Abstract: A computer-implemented method, an apparatus and a recording medium are provided for predicting a score associated with a first user and with a first item are provided. The method comprises: storing one or more first scores in a first database, each first score being associated with a user and with an item; calculating, based on the first scores, one or more latent user features associated with one or more users including the first user and one or more latent item features associated with one or more items including the first item; calculating, based on the latent user features and the latent item features, a second score associated with the first user and with the first item; and providing the second score as a predicted score associated with the first item and with the first user. The recording medium comprises instructions to configure the apparatus to perform the method.
Abstract: A system, method, and computer program product are disclosed for surveillance of artificial lift systems. An Artificial Lift Surveillance Tool (ALST) is provided to identify artificial lift wells with production declines due to artificial lift well failures. Production well information is provided for a plurality of the production wells each being associated with an artificial lift system. Artificial lift system failure alerts for the plurality of production wells are received and processed on a computer. A signal indicative of the production well information for each of the plurality of production wells is received and processed on a computer. The plurality of production wells are displayed in a hierarchical ordering, such as a treemap, responsive to the signal.
Abstract: A method and corresponding system for providing a skip group rule feature is disclosed. When a search for a key matches a skip group rule in a group of prioritized rules, the search skips over rules having priorities lower than the skip group rule and the search continues to a next group. A convenient example of a compiler rewrites the lower priority rules by subtracting the skip group rule from them. The subtraction includes subtracting range, exact-match, mask, and prefix fields. The rewritten rules appear to a search processor as typical rules. Beneficially, the search processor requires no additional logic to process a skip group rule, skip over lower priority rules, and go on to search a next group of rules. Advantageously, this approach enables any number of skip group rules to be defined allowing for better classification of network data.
Abstract: Techniques are shown for generating image frames from a media presentation, selecting candidate thumbnails from the generated image frames using a selection process, and testing each selected candidate thumbnail for a success ranking relative to a target metric. The probability of choosing a selected candidate thumbnail with a success ranking higher than all other selected thumbnails as an optimum thumbnail for presentation to a user is based, at least in part, on the ratio of the success ranking of the selected candidate thumbnail with the highest success ranking to the sum of the success rankings of all of the selected candidate thumbnails. This Abstract is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.
Type:
Grant
Filed:
September 13, 2012
Date of Patent:
March 1, 2016
Assignee:
Google Inc.
Inventors:
Justin Lewis, Henry Benjamin, Stanley Charles Ross Wolf
Abstract: Embodiments of the invention relate to a neuromorphic network for producing spike-timing dependent plasticity. The neuromorphic network includes a plurality of electronic neurons and an interconnect circuit coupled for interconnecting the plurality of electronic neurons. The interconnect circuit includes plural synaptic devices for interconnecting the electronic neurons via axon paths, dendrite paths and membrane paths. Each synaptic device includes a variable state resistor and a transistor device with a gate terminal, a source terminal and a drain terminal, wherein the drain terminal is connected in series with a first terminal of the variable state resistor.
Type:
Grant
Filed:
September 30, 2010
Date of Patent:
February 23, 2016
Assignee:
International Business Machines Corporation
Inventors:
Daniel J. Friedman, Seongwon Kim, Chung H. Lam, Dharmendra S. Modha, Bipin Rajendran, Jose A. Tierno
Abstract: An AHaH (Anti-Hebbian and Hebbian) apparatus for use in electronic circuits. Such an AHaH apparatus can include one or more meta-stable switches, and one or more differential pairs of output electrodes, wherein each electrode among each differential pair of output electrodes can include one or more input lines coupled thereto via one or more of the meta-stable switch.
Abstract: A system and method for distributing shared content based on a probability is provided. The system includes a shared content request unit to receive a shared content request; a bid retrieval unit to retrieve a plurality of shared content items based on the share content request, and to retrieve a plurality of bids corresponding to the plurality of shared content items, respectively; a probability retrieval unit to retrieve a plurality of likelihood values for each of the plurality of bids, respectively; a bid adjustment unit to adjust the plurality of bids based on the corresponding plurality of likelihood values; and a shared content selection unit to select shared content based on the adjusted plurality of bids.
Abstract: Techniques for application quality testing time predictions are described that provide customized processing time predictions for application testing. Testing times for various stages of testing are collected during application testing. The collected testing data may be stored in association with various attribute values ascertained for the applications. The collected timing data is used to predict processing times for applications that match defined profiles. The profiles may be defined to include selected attributes and values used to identify applications having corresponding attributes and values. The collected timing data may be processed to derive predictions for processing times on a profile-by-profile basis. When a new application is submitted, the application is matched to a particular profile based on attribute values possessed by the application.
Abstract: Systems and techniques are disclosed for generating weighted machine learned models using multi-shard combiners. A learner in a machine learning system may receive labeled positive and negative examples and workers within the learner may be configured to receive either positive or negative examples. A positive and negative statistic may be calculated for a given feature and may either be applied separately in a model or may be combined to generate an overall statistic.
Type:
Grant
Filed:
December 11, 2013
Date of Patent:
February 23, 2016
Assignee:
Google, Inc.
Inventors:
Tushar Deepak Chandra, Tal Shaked, Tze Way Eugene Ie, Yoram Singer, Joshua Redstone
Abstract: Embodiments of the invention provide a method comprising creating a structural description for at least one neurosynaptic core circuit. Each core circuit comprises an interconnect network including plural electronic synapses for interconnecting one or more electronic neurons with one or more electronic axons. The structural description defines a desired neuronal activity for the core circuits. The desired neuronal activity is simulated by programming the core circuits with the structural description. The structural description controls routing of neuronal firing events for the core circuits.
Type:
Grant
Filed:
March 8, 2013
Date of Patent:
February 16, 2016
Assignee:
International Business Machines Corporation
Abstract: The present disclosure relates generally to a computer application software program for mobile phones, and more specifically to an application program related to social networking websites wherein an individual's influence on social networking websites can be quantified based on his/her quantitative and qualitative activity postings. A social networker may register any one or more social networking websites for which he/she is a participant and the system and method discussed herein will measure all activity postings, responses, replies, discussions, third party use of the original activity postings and the like, to generate weighted scores that are aggregated for an impact score that is reflective of the social networkers respective influence.