Patents Examined by Ilya Traktovenko
-
Patent number: 9754288Abstract: Content items, such as e-books, audio files, video files, etc., may be recommended to a user based on the user's presence at a geolocation or venue. Geolocation is the geospatial location of the user, while a venue is a designated area for an activity, such as a concert hall, aircraft, waiting room, etc. The recommendations may be of content items relating to the geolocation or venue, or they may be content items being accessed by others who are, or have been, in approximately the same geolocation or venue.Type: GrantFiled: November 10, 2014Date of Patent: September 5, 2017Assignee: Amazon Technologies, Inc.Inventors: Francis J. Kane, Jr., Peter Thomas Killalea, Llewellyn J. Mason
-
Patent number: 9710451Abstract: A method and associated systems for using methods of DNA computing to implement an operation of a natural-language processing (NLP) system. A processor translates components of a slot grammar of the NLP system and an input filler vocabulary into listings of sequences of nucleotides. These sequences are encoded into a set of nucleotide chains, which are then allowed to chemically interact with each other such that the chains automatically bond in ways that are analogous to the way that a traditional computerized NLP system would use inferences and contextual information to fill slots of the slot grammar with tokens of the filler vocabulary. The resulting DNA molecules are extracted and information encoded into sequences of nucleotides comprised by the extracted molecules is decoded to yield a set of all possible strings that may generated by filling slots of the slot grammar with tokens of the vocabulary.Type: GrantFiled: June 30, 2014Date of Patent: July 18, 2017Assignee: International Business Machines CorporationInventors: Aaron K. Baughman, Peter K. Malkin, Brian M. O'Connell, Craig M. Trim
-
Patent number: 9697300Abstract: A graph syntax validation system, method, or computer-readable medium that receives: (i) an input graph, (ii) transformation rules, and (iii) a minimal valid graph. The system/method/computer-readable medium transforms the input graph into the minimal valid graph using the transformation rules that are comprised of source patterns and target patterns. The system/method/computer-readable medium recurrently transforms the input graph until either the input graph has been reduced to the minimal valid graph indicating that the input graph uses a valid syntax, or until it is determined that one or more transformation rules do not match the input graph indicating that the input graph uses an invalid syntax.Type: GrantFiled: April 3, 2014Date of Patent: July 4, 2017Assignee: Software AGInventors: Thomas Kummer, Markus Brueck
-
Patent number: 9696699Abstract: A Self-Organizing Process Control Architecture is introduced with a Sensing Layer, Control Layer, Actuation Layer, Process Layer, as well as Self-Organizing Sensors (SOS) and Self-Organizing Actuators (SOA). A Self-Organizing Sensor for a process variable with one or multiple input variables is disclosed. An artificial neural network (ANN) based dynamic modeling mechanism as part of the Self-Organizing Sensor is described. As a case example, a Self-Organizing Soft-Sensor for CFB Boiler Bed Height is presented. Also provided is a method to develop a Self-Organizing Sensor.Type: GrantFiled: November 15, 2013Date of Patent: July 4, 2017Assignee: CYBOMEDICAL, INC.Inventor: George Shu-Xing Cheng
-
Patent number: 9684868Abstract: A method, system and computer program product are disclosed for predicting influence in a social network. In one embodiment, the method comprises identifying a set of users of the social network, and identifying a subset of the users as influential users based on defined criteria. A multitude of measures are identified as predictors of which ones of the set of users are the influential users. These measures are aggregated, and a composite predictor model is formed based on this aggregation. This composite predictor model is used to predict which ones of the set of users will have a specified influence in the social network in the future. In one embodiment, the specified influence is based on messages sent from the users, and for example, may be based on the number of the messages sent from each user that are re-sent by other users.Type: GrantFiled: May 7, 2015Date of Patent: June 20, 2017Assignee: International Business Machines CorporationInventors: Richard D. Lawrence, Estepan Meliksetian, Prem Melville, Claudia Perlich, Karthik Subbian
-
Patent number: 9679259Abstract: A matching or pairing system and method for matching first and second entities having a greater likelihood of forming a successful pairing includes a trained machine learning system to provide heuristic values useful in determining a compatibility score for the pairing. During training of the machine learning system, a training example selection device can provide attribute values logically associated with entities engaged in historically successful pairings and a number of hypothetically successful pairings. The hypothetically successful pairings may be based at least in part on historically successful pairings where at least one attribute value logically associated with at least one entity in the pairing is varied, adjusted, or subjected to a loosened constraint. During run-time operation a screening device can screen unsuccessful pairings and forward potentially successful pairings that meet a threshold value to the neural network. The system can then determine a compatibility score for the pairing.Type: GrantFiled: January 24, 2014Date of Patent: June 13, 2017Assignee: PLENTYOFFISH MEDIA ULCInventors: Markus Frind, Sa Li, Steve Oldridge
-
Patent number: 9659257Abstract: A method and system that provide for decision support and/or training support in crisis decision-making situations are provided. In one implementation, a method identifies patterns from known cases based on information from a crisis event. Each of the known cases includes attributes and at least one outcome. The method also identifies a first subset of the known cases that relate to the identified patterns from the known cases. The method also analyzes the identified patterns to determine a cue that, if answered, will provide a second subset of the known cases including a more converged range of decision outcomes than the first subset.Type: GrantFiled: February 25, 2013Date of Patent: May 23, 2017Assignee: AlphaTRAC, Inc.Inventor: Charles Reed Hodgin
-
Patent number: 9652477Abstract: An object potentially belongs to a number of topics. Each topic is characterized by a probability distribution profile of a number of representative items that belong to the topic. Sample items are selected from the object, less than a total number of items of the object. A probability that the object belongs to each topic is determined using the probability distribution profile characterizing each topic and the sample items selected from the object.Type: GrantFiled: October 31, 2009Date of Patent: May 16, 2017Assignee: Hewlett Packard Enterprise Development LPInventors: Helen Balinsky, Steven J. Simske
-
Patent number: 9607217Abstract: Briefly, embodiments of methods and/or systems of generating preference indices for contiguous portions of digital images are disclosed. For one embodiment, as an example, parameters of a neural network may be developed to generate object labels for digital images. The developed parameters may be transferred to a neural network utilized to generate signal sample value levels corresponding to preference indices for contiguous portions of digital images.Type: GrantFiled: December 22, 2014Date of Patent: March 28, 2017Assignee: Yahoo! Inc.Inventors: Suleyman Cetintas, Kuang-chih Lee, Jia Li
-
Patent number: 9600768Abstract: An apparatus and method are disclosed for determining whether a driving environment has changed relative to a detailed map stored by an autonomous vehicle. An autonomous driving computer system of the autonomous vehicle may determine whether the driving environment has probably changed based on the location of one or more objects detected in the driving environment. The autonomous driving computer system may include various object models, each object model being associated with an object type, and where each object model defines one or more probability values that a given object type is expected (or not expected) to be found at a given location. By aggregating the various probability values resulting from the detection of objects in the driving environment, and then comparing the aggregated probability values with one or more probability threshold values, the autonomous driving computer system may predict or determine whether the driving environment has probably changed.Type: GrantFiled: April 16, 2013Date of Patent: March 21, 2017Assignee: Google Inc.Inventor: David I. Ferguson
-
Patent number: 9600767Abstract: The present invention relates to a system, method, and computer program product for generating a single software code based on a description of a distributed architecture. The present invention introduces a BICA-SMART development framework that implements a distributed architecture in a flexible, parallel and scalable implementation that is embodied by a single software code. Thus, using the present invention, a user can input a description of the architecture into the system, with the system automatically generating the software code to implement the architectural description.Type: GrantFiled: December 30, 2008Date of Patent: March 21, 2017Assignee: HRL Laboratories, LLCInventors: Aleksey Nogin, Deepak Khosla, Yang Chen
-
Patent number: 9558445Abstract: Described are techniques for processing inputs. A plurality of rules engines is provided. Each of the rules engines is written in a different programming language. Input validation processing is performed of a first set of one or more inputs by a first of the plurality of rules engines using a first portion of a set of validation rules. Input validation processing is performed for the first set of one or more inputs by a second of the plurality of rules engines using the first portion of validation rules.Type: GrantFiled: September 25, 2012Date of Patent: January 31, 2017Assignee: EMC IP Holding Company LLCInventors: Bruce R. Rabe, Scott E. Joyce, Norman M. Miles, Peter Chen
-
Patent number: 9552461Abstract: A system and method for preparing food, involving a nutritional information module for aggregating nutritional and portion information of an entire menu to adjust serving weight by preferred caloric value. The system involves a scheduler module which compiles task information for any individual recipe. The scheduler module has a passive task time and/or an active task time and stamps the preparation time for a recipe. The system compiles and stores a cook's information for analyzing an individual cooking: style time. Moreover, the system involves a feedback module for predicting preparation time of any particular menu choice. Additionally, the system involves recipe data, an organizer, a shopping assistant, and a recommendation module to facilitate menu pairings as well as sourcing and purchasing, required ingredients, required cookware, and utensils for a recipe.Type: GrantFiled: May 24, 2011Date of Patent: January 24, 2017Inventor: Chet Harrison
-
Patent number: 9552379Abstract: Systems and methods for foreign key identification are described. The method includes computing a threshold value for each of a primary key-foreign key (PK-FK) pair of a super-set of PK-FK, and generating a sub-set of PK-FK pairs based on comparison of the threshold value and a predefined threshold value. The predefined threshold value is indicative of an acceptance criterion. Further, the method includes determining a conformance score for each of the PK-FK pair of the subset of PK-FK pairs. The conformance score is based on deviations between Cumulative Probability Distribution (CPD) values of PK and CPD of FK for each PK-FK pair. Further, the method includes comparing the conformance score of the each PK-FK pair of the sub-set of PK-FK pairs with a predetermined acceptability index. The predetermined acceptability index is indicative of an acceptance of at least one positive FK from the set of PK-FK pairs.Type: GrantFiled: March 15, 2013Date of Patent: January 24, 2017Assignee: Tata Consultancy Services LimitedInventors: Karandas Pejathaya, Gopinath Talluri, Anand Shankar Bhide
-
Patent number: 9547827Abstract: A terminal device includes an acquisition unit, an accumulation unit, a communication unit and a prediction unit. The acquisition unit acquires local information of a present location at a present time. The accumulation unit accumulates the acquired local information for a period of time. The communication unit transmits, to an information processing device, the accumulated local information. The communication unit also receives, from the information processing device, parameters of a statistical model which are learned using local information acquired from a plurality of other terminal devices. The prediction unit predicts local information in relation to an arbitrary time and location using the received parameters of the statistical model.Type: GrantFiled: February 26, 2013Date of Patent: January 17, 2017Assignee: Sony CorporationInventors: Naoki Ide, Takashi Usui, Shinichiro Tsuda
-
Patent number: 9547820Abstract: A method of classifying an input pattern and a pattern classification apparatus are provided. The method includes enabling an artificial neural network to learn based on learning input data received by an input layer of the artificial neural network, determining classification of an input pattern received by the input layer of the enabled artificial neural network according to an output value obtained from an output layer of the artificial neural network, the obtained output value being based on the input pattern, updating connection intensities of a plurality of connection lines of the enabled artificial neural network to output a result value indicating the determined classification from the output layer when the input pattern, and determining updated classification of the input pattern according to an updated output value obtained from an output layer of the updated artificial neural network, the obtained updated output value being based on the input pattern.Type: GrantFiled: September 25, 2012Date of Patent: January 17, 2017Assignees: Samsung Electronics Co., Ltd., INDUSTRY-ACADEMIC COOPERATION FOUNDATION, YONSEI UNIVERSITYInventors: Youn-ho Kim, Chang-mok Choi, Kun-soo Shin, Myoung-ho Lee, Jin-kwon Kim
-
Patent number: 9535978Abstract: Determining an impact of an event identified in a first topic map meta-model will have on at least one asset identified in a second topic map meta-model representative of weight. A third topic map meta-model is created which maps at least one asset from the second topic map meta-model to an event from the first topic map meta-model and is comprised of: a topic map representation of assets of the second topic map meta-model and events of the first topic map meta-model, a topic map based index with instance ontology of the first and second topic map meta-models, identification of at least one association between an event identified in the first topic map meta-model and at least one asset identified in the second topic map meta-model; and weight assigned to the at least one association.Type: GrantFiled: June 2, 2014Date of Patent: January 3, 2017Assignee: International Business Machines CorporationInventors: Peter A. Coldicott, Thomas T. Hanis, Eoin Lane
-
Patent number: 9530098Abstract: The present disclosure includes a method for providing a response to a statement of a user. The method includes receiving user input that comprises a portion of a user statement. The method also includes selecting, before receiving a whole user statement, an answerable statement response between an answerable statement, multiple answerable statements and a response to an answerable statement. The selecting is responsive to user input and to structured representations of answerable statements answerable by an answering entity. Further, the method includes sending to the user information representative of response to the user statement.Type: GrantFiled: December 19, 2014Date of Patent: December 27, 2016Assignee: KNAPP INVESTMENT COMPANY LIMITEDInventors: Amit Antebi, Hanoch Rahimi
-
Patent number: 9524463Abstract: Methods and systems for automating carbon footprinting are disclosed. In some embodiments, the methods include a plurality of steps. In some embodiments, related to predetermined resources associated with an item from predetermined data sources is obtained. Then, estimated emission factors are calculated for each of the resourced. Next, a contributory uncertainty of the data and of the emission factors is determined. Then, a user is guided based on a comparison of the respective contributory uncertainty of data related to the resources or emission factors Next, both data related to the resources and the estimated emission factors of the resources are utilized to determine a carbon footprint of the item.Type: GrantFiled: February 16, 2011Date of Patent: December 20, 2016Assignee: The Trustees of Columbia University in the City of New YorkInventors: Christoph Johannes Meinrenken, Klaus S. Lackner, David Joseph Walker, Robert Christian ter Kuile
-
Patent number: 9514236Abstract: A recommendation network is described. In some embodiments, the recommendation network includes recommenders that explicitly or implicitly recommend, rate or refer items and recommendation receivers that receive the recommendations. In some embodiments, the recommenders can be recommendation receivers, and vice versa. In some embodiments, recommendation receivers assign rust ratings to recommenders. The recommendation receiver can assign separate trust ratings to individual topics for which the recommendation receiver trusts the recommender. The separate trust ratings represent the recommendation receiver's amount of trust in the recommender to makes valuable recommendations for the specific topic. The recommendation network can use the separate trust ratings, along with ratings provided by the recommender, to rank recommendations per the separate topics. The recommendation receiver can assign the recommender to different bundles, topics, channels, etc. to which other recommendation receivers can subscribe.Type: GrantFiled: November 15, 2011Date of Patent: December 6, 2016Assignee: RESOURCE CONSORTIUM LIMITEDInventors: Matthew R. Evans, Daniel L. Salgado