International Business Machines Corporation

Jeffrey K Huebert

John Edward Petri

Adam Clark

Aspen L Payton

Corville O Allen

Richard Joseph Stevens

Joel C Dubbels

Kathryn Lamont Whaley

Scott Robert Carrier

Jennifer Lynn La Rocca

Robert E Goff

Provided are techniques for a personalized, social navigation coach. While a commuter is commuting on a commute path, periodically, current conditions for the commute path are determined. One or more risk factors of having an accident based on the current conditions and a commute model are identified, where the one or more risk factors are associated with one or more icons, and where the commute model uses sensor data comprising historic data at different points in time. A graphic range is generated with an indicator that indicates an amount of risk of having an accident along the graphic range. The one or more icons and the graphic range are displayed.

Personalized social navigation coach

Provided are techniques for detecting and highlighting insightful comments in a thread of content. A context is determined for a thread of content including comments. Each of the comments in the thread of content is analyzed to determine which comments are insightful and which comments are not insightful. At least one of highlighting the comments that are insightful and hiding the comments that are not insightful are performed. Semantic relationships are used to provide supporting evidence and cross references to additional information for the comments that are related to the context.

Detecting and highlighting insightful comments in a thread of content

A method, computer system, and computer program product for determining qualities of user favorable photographs are provided. The embodiment may include receiving a plurality of photographs from an electronic device. The embodiment may also include parsing each photograph. The embodiment may further include calculating a favorability value of each photograph. The embodiment may also include determining whether the favorability value of each photograph exceeds a favorability threshold value. The embodiment may further include organizing the received photographs into one or more clusters based on features of each photograph. The embodiment may also include generating a classification model for each cluster.

Cognitively identifying favorable photograph qualities

A method, computer system, and computer program product for cognitively coaching a user to take favorable photographs are provided. The embodiment may include determining characteristics of favorable photographs from a favorable photo database using image analysis techniques. The embodiment may also include identifying subjects in a current camera frame. The embodiment may further include identifying characteristics of a photograph from a current camera frame. The embodiment may also include determining similarities or differences between the favorable photographs and the current camera frame. The embodiment may further include generating directions that map a current state of similar characteristics to the favorable photographs.

Cognitively coaching a subject of a photograph

A system, a method, and a computer program product for managing answer feasibility in a Question and Answering (QA) system. A set of candidate situations is established. The set of candidate situations corresponds to a first set of answers. A QA system establishes the set of candidate situations by analyzing a corpus. The first set of answers will answer a question. The QA system identifies a subset of the set of candidate situations. The subset of candidate situations corresponds to a portion of contextual data. The portion of contextual data is from a set of contextual data. The set of contextual data relates to the question. The question-answering system determines a set of answer feasibility factors. The set of answer feasibility factors is determined using the subset of candidate situations. The set of answer feasibility factors indicates the feasibility of the answers in the first set of answers.

Managing answer feasibility

A processor uses natural language processing to ingest product reviews for a plurality of products. Each of the products embodies a specific form for each of the plurality of product features. The processor analyzes the ingested product reviews for sentiments associated with the specific forms. The processor generates a sentiment score for each product feature based on the analysis. The processor ranks the plurality of product features based on the sentiment scores.

Analyzing sentiment in product reviews

A computer-implemented method for cognitive matching of narrative data may include collecting a set of data for a party and determining, by analyzing the set of data, an identifiable event for the party. In addition, the method may include identifying, using the identifiable event, a relevant feature of a corpus and providing an output corresponding to the relevant feature.

Cognitive matching of narrative data

A cognitive matching of narrative data mechanism may include a collecting module configured to collect a set of data for a party and a determining module configured to determine, by analyzing the set of data, an identifiable event for the party. The mechanism may include an identifying module configured to identify, using the identifiable event, a relevant feature of a corpus, and a providing module configured to provide an output corresponding to the relevant feature.

Techniques disclose validating user-provided text feedback for topical relevance relative to a question asked. A form with at least a first field is received. The first field includes unstructured text content provided as feedback in response to a question. The unstructured text content of the first field is evaluated to identify an answer type. A measure of relevance of the unstructured text content relative to the question is determined based on the evaluation.

Validating topical relevancy of data in unstructured text, relative to questions posed

A system and computer implemented method for managing perspective data is disclosed. The method may include collecting a first lot of perspective data for an item. The method may include introducing a variant feature to the item to constitute a modified item. The method may include collecting a second lot of perspective data for the modified item. The method may also include evaluating the first and second lots of perspective data to ascertain a sentiment fluctuation based on information relevant to the variant feature.

Perspective data analysis and management

System, method, and computer program product to determine that a question received by a deep question answering system is speculative, generate, by one or more predictive algorithms, a set of candidate answers, compute a score for each candidate answer in the set of candidate answers, and return a first candidate answer, of the set of candidate answers, as responsive to the speculative question received by the deep question answering system.

Candidate answers for speculative questions in a deep question answering system

Mechanisms are provided to implement an echolocation functionality within a virtual environment. The mechanisms receive graphical information for a virtual environment, and analyzes the graphical information to detect a virtual object present in the virtual environment. One or more characteristics of the detected virtual object are identified, which may include a relative location of the virtual object to a virtual representation of a user in the virtual environment. Echo data is generated that defines characteristics of an audio output that represents the virtual object in a manner emulating an echo of a sound emitted from the virtual representation of the user in the virtual environment. Output of the audio output by the one or more audio output devices is controlled based on the generated echo data.

Accessibility of virtual environments via echolocation

While a virtual reality environment is being presented to a user, at least a first sound in a real world environment in which the user physically is located can be detected. a nature of the first sound can be determined. Based on the nature of the first sound, a second sound that matches a theme of the virtual reality environment can be selected. The first sound can be masked by presenting the second sound to the user in the virtual reality environment.

Growing community of inventors

Rochester, MN, United States of America

Jeffrey K Huebert