International Business Machines Corporation

Conduent Business Services, LLC

Raghuram Krishnapuram

Sachindra Joshi

Prasad Manikarao Deshpande

Sumit Negi

Deepak S Padmanabhan

Debapriyo Majumdar

Vijil Enara Chenthamarakshan

Krishna Kummamuru

Rema Ananthanarayanan

Tanveer Afzal Faruquie

Shajeer K Mohammed

Vinatha Chaturvedi

Ravi Kothari

Shourya Roy

L Venkata Subramaniam

Dinesh Garg

Jayanta Basak

Vishal Singh Batra

Vivek Tyagi

Krishna Prasad Chitrapura

Nandita J Mahajan

L Venkat Subramaniam

Manoj N Kumar

Sameep Mehta

Amit Anil Nanavati

Rahul Gupta

Karthik Visweswariah

Kenney Ng

Pradeep Kumar Dubey

Gyana Ranjan Parija

Danish Contractor

Sreyash Kenkre

Himanshu Sharad Bhatt

Thomas A Hampp-Bahnmueller

Scott Holmes

Neeraj Agrawal

Kiran Mehta

Ganesh Ramakrishnan

Deepali Semwal

Noel J Almeida

Nimit Kumar

Ramakrishna Varadarajan

Methods and arrangements for monitoring and flagging distinct flows in an evolving network. There is identified a locality comprising at least two nodes in a graph of nodes and edges, wherein the edges represent interactions between nodes. At least one target source-destination node pair is identified in the locality for monitoring, and at least one monitoring rule is generated. An interaction is flagged upon a detected violation of at least one monitoring rule, and there is updated, in response to the detected rule violation, at least one of: the identified locality; the at least one target source-destination pair; and the at least one monitoring rule.

Monitoring flows in an evolving transaction network using dynamic rules

The disclosed embodiments illustrate method and system of processing data by a computing device for training a target domain classifier. The method includes extracting one or more first features and one or more second features from a first target instance, associated with a target domain. The method further includes predicting a first label for the received first target instance based on the one or more first features by utilizing a trained first classifier associated with a set of labeled source instances, wherein the predicted first label is assigned to the first target instance when a first score of the predicted first label exceeds a first pre-specified threshold. Further, the method includes updating a set of labeled target instances associated with the target domain based on the labeled first target instance, wherein the updated set of labeled target instances is utilized to train the target domain classifier.

Method and system of processing data for training a target domain classifier

Methods, systems, and computer program products for generating probabilistic annotations for entities and relations using reasoning and corpus-level evidence are provided herein. A method includes determining candidate entities and candidate relationships between entities from text contained within textual documents associated with a given domain; generating questions to support or refute legitimacy of a given one of the candidate entities and/or a given one of the candidate relationships; automatically determining an answer to each of the questions based on analysis of one or more additional items of knowledge pertaining to the given domain; computing a confidence score for each answer; and assigning a confidence value in support of the legitimacy of the given one of the candidate entities and/or the given one of the candidate relationships, wherein said confidence value is based on an aggregation of the confidence scores for the answers to the one or more questions.

Generating probabilistic annotations for entities and relations using reasoning and corpus-level evidence

A method and a system for response evaluation of users from electronic documents are disclosed. In an embodiment, one or more questions and a first response pertaining to each of the one or more questions are extracted from one or more first electronic documents. Further, a second response pertaining to each of the one or more extracted questions and metadata are extracted from one or more second electronic documents. For the second response pertaining to each of the one or more extracted questions, a score is determined based on one or more similarity measures that correspond to a category of each of the one or more extracted questions. Thereafter, the response evaluation is rendered on a user interface displayed on a display screen. The response evaluation comprises at least the determined score for the second response pertaining to each of the one or more extracted questions.

Method and system for response evaluation of users from electronic documents

Provided are techniques for creating an inverted index for features of a set of data elements, wherein each of the data elements is represented by a vector of features, wherein the inverted index, when queried with a feature, outputs one or more data elements containing the feature. The features of the set of data elements are ranked. For each feature in the ranked list, the inverted index is queried for data elements having the feature and not having any previously selected feature and a cluster of the data elements is created based on results returned in response to the query.

Clustering a collection using an inverted index of features

Methods and arrangements for automatically finding the dependency of a software product on other software products or components. From an install image or directory, a signature is found by deriving the same from a directory structure of the software. Further, a directory tree structure is built and an approximate sub-tree matching algorithm is applied to find commonalities across software products.

Mining dependencies from disk images

Methods and arrangements for automatically finding the dependency of a software product on other software products or components. From an install image or directory, a signature is found by deriving the same from a directory structure of the software. Further, a directory tree structure is built and an approximate sub-tree matching algorithm is applied to find commonalties across software products.

Techniques for segregating one or more logs of at least one multitasking user to derive at least one behavioral pattern of the at least one multitasking user are provided. The techniques include obtaining at least one of at least one action log, configuration information, domain knowledge, at least one task history and open task repository information, correlating the at least one of at least one action log, configuration information, domain knowledge, at least one task history and open task repository information to determine a task associated with each of one or more actions and segregate the one or more logs based on the one or more actions, and using the one or more logs that have been segregated to derive at least one behavioral pattern of the at least one multitasking user. Techniques are also provided for deriving intelligence from at least one activity log of at least one multitasking user to provide information to the at least one user.

System and computer program product for deriving intelligence from activity logs

Method for deriving intelligence from activity logs

Techniques, systems, and articles of manufacture for determining related data points from multi-modal inputs. A method includes collecting multiple items of multi-modal data comprising at least one dimension from multiple data sources, wherein said at least one dimension comprises a geographic dimension, a temporal dimension and/or an event-related dimension, determining a window of relevance for each of the multiple items of multi-modal data with respect to the at least one dimension, and identifying two or more of the multiple items of multi-modal data as related, by determining an overlap of the window of relevance corresponding to each of the two or more items of multi-modal data with respect to the at least one dimension.

Determining related data points from multi-modal inputs

Techniques for retrieval of one or more relevant multi-attribute structured objects with respect to a query are provided. The techniques include receiving a query, grouping one or more attributes of one or more objects in a database into one or more groups according to how each bears a relation to the query, and using the one or more attribute groups to produce an output of one or more relevant multi-attribute structured objects in response to the query.

Retrieval of relevant objects in a similarity

Embodiments of the invention provide retailers with the ability to employ concept-based marketing using only a few representative examples. Embodiments of the invention take seed examples, utilize the seed examples to provide an expanded list (that can be edited as desired) representative of the concept, and map the expanded list to a final set of customers to be included in a targeted marketing operation.

System and method for example based targeted marketing

A method, a system and a computer program product for analyzing customer service quality is disclosed. A plurality of customer call service quality parameters is identified using historical data. The plurality of customer call service quality parameters is quantified and correlated. The customer service quality is analyzed using the plurality of customer call service quality parameters. A repository is generated using the historical data of a plurality of customer calls and a set of pre-defined customer call flow templates. A subset of service quality queries is identified using contextual information of the customer call from the repository of service quality queries. The subset of service quality queries is then interspersed in the customer call. The customer service quality is analyzed using responses to the subset of service quality queries.

Customer service analysis

Product data pertaining to a plurality of products is gathered from a plurality of sources. Dependency information for the plurality of products is extracted from the product data. The dependency information is analyzed to determine dependencies for each product of the plurality of products. The dependencies for each product of the plurality of products are displayed to a user.

Discovery, analysis, and visualization of dependencies

A method () is disclosed of extracting factoids from text repositories, with the factoids being associated with a given factoid category. The method () starts by training a classifier () to recognize factoids relevant to that given factoid category. Documents or document summaries relevant to the given factoid category is next collected () from the text repositories. Sentences having a predetermined association to the given factoid category is extracted () from the documents or said document summaries. Those sentences are classified (), in a noisy environment, using the classifier () to extract snippets containing phrases relevant to the given factoid category. It is the extracted snippets that are the factoid associated with the given factoid category.

System and method for extraction of factoids from textual repositories

Growing community of inventors

New Delhi, India

Raghuram Krishnapuram