International Business Machines Corporation

Hernan Badenes

Rosanna Mannan

Siddharth A Patwardhan

Marco Patricio Crasso

Julian Ariel Cerruti

Patricio M Reyna Almandos

Hongxia Jin

Bin Xu

Jalal U Mahmud

Vibha Singhal Sinha

John C Tang

Barton Allen Smith

Liang Gou

Eric M Wilcox

Jeffrey Scott Pierce

Pritam S Gundecha

Diego A Masini

Jerald Thomas Schoudt

Stephen Dill

Rama K Akkiraju

Mateo Nicolas Bengualid

Tara L Matthews

Julia Grace

Mateo N Bengualid

Richard P Gabriel

Eduardo M Coria

Nicolas Lanaro

Agustin A Casamayor

A computer-implemented method includes detecting a first set and a second set of citations to a legal case in a plurality of legal documents and a first legal document distinct from the plurality of legal documents, respectively. The computer-implemented method further includes determining tones corresponding to each citation in the first and second sets of citations. The computer-implemented method further includes determining a score for each tone in the first and second sets of tones. The computer-implemented method further includes aggregating a first and subset and a second of the first and second sets of citations, respectively. The computer-implemented method further includes generating an average score for the first and second subsets. The computer-implemented method further includes determining a degree of similarity between the first and second subsets based, in part, on a comparison of average scores. A corresponding computer program product and computer system are also disclosed.

Tone analysis of legal documents

An approach is provided that provides a tone optimization recommendation. The approach obtains a current tone inferred from digital content and a desired tone inference for a target audience. A tone optimization recommendation to reduce a difference between the current tone and the desired tone is determined using a processor. A memory is modified to save the tone optimization recommendation. The tone optimization recommendation is provided.

Tone optimization for digital content

An approach is provided for determining a time of an alarm. Natural language processing determines a meaning of user input which specifies the alarm, an event, an action, and an amount of time. The alarm notifies the user about the action the user is to take prior to the event, which will occur at an indefinite time. The alarm is triggered at a time that precedes an estimated time of the event by the amount of time. Information is retrieved that describes movements and usage of a mobile device of the user, profile information, historical user behavior, calendar appointments, messages sent and received by the user of the user, and social network contacts and user-generated content. The estimated time of the event is generated. The time of the alarm is determined as a time that precedes the estimated time of the event by the amount of time.

Cognitively determining a time of an alarm

A method and system for improving an automated mobile device charging detection system is provided. The method includes automatically detecting a connection between a mobile device and a charging apparatus. A voltage signal between the charging apparatus and circuitry of the mobile hardware device is detected via a hardware sensor that includes a motion sensor for charging attempt detection. A specified time period is determined to have elapsed since detecting the voltage signal and a subsequent loss of the voltage signal between the charging apparatus and the circuitry of the mobile hardware device is detected. In response, a notification indicating the loss of the voltage signal is presented to a user.

Automated mobile device charging detection

A computer-implemented method includes detecting a first and second set of citations to a plurality of legal cases cited in a plurality of legal documents and a first legal document distinct from the plurality of legal documents, respectively. The computer-implemented method further includes determining a first and second set of tones corresponding to each citation in the first and second sets of citations, respectively. The computer-implemented method further includes determining a score for each tone in the first and second sets of tones, respectively. The computer-implemented method further includes detecting a first set of annotations corresponding to the first set of citations. The computer-implemented method further includes building a training model, based, at least in part, from at least a subset of the first set of annotations. The computer-implemented method further includes determining a second set of annotations corresponding to the second set of citations.

Annotation of legal documents with case citations

A method for detecting and presenting burnout symptoms associated with users is provided. The method may include receiving a plurality of predictor rules for monitoring and detecting a plurality of burnout indicators. The method may further include monitoring and receiving the plurality of burnout indicators. Additionally, the method may include storing the monitored and received plurality of burnout indicators. The method may also include detecting a plurality of burnout events associated with the stored monitored and received plurality of burnout indicators. The method may further include determining the plurality of burnout symptoms based on the detected plurality of burnout events. The method may also include determining at least one aggregate score based on the determined plurality of burnout symptoms. The method may further include presenting at least one alert and at least one recommendation based on the determined plurality of burnout symptoms and the determined at least one aggregate score.

Burnout symptoms detection and prediction

Ranking and recommendation of online content including social media, blog and forum posts is provided. A method of and computer program product for content analysis are provided. A subset of content items is selected from a set of content items. Each content item in the set has at least one attribute. For each content item in the subset, a user is queried to obtain a subjective value. A formula is derived that relates the at least one attribute of each content item of the subset to the subjective value of each content item of the subset. The formula is applied to each content item of the set to determine a calculated value of each content item of the set. A ranking of the set of content items is determined based on the calculated value of each content item. Recommendations are provided to a user based on the ranking.

Ranking and recommendation of online content

According to one embodiment of the present invention, a method for cross-service tagging is provided. The method includes creating connections to multiple applications, each application having multiple entities. Relationships are determined between the entities within a single application and between entities across multiple applications. A tag is associated with a selected one of the entities in a first one of the multiple applications. Entities in other applications besides the first application are identified that are related to the selected entity, based on the determined relationships. The tag is propagated across multiple applications by associating the tag with the identified entities in the other applications. According to a second embodiment of the present invention, a method for inferring tags suggestions is provided. This method includes analyzing email messages to create keywords from text analysis, from bringing content and tags from other email messages or directory applications. Tags suggestions from the various sources are merged and weighed according to an algorithm.

Augmented and cross-service tagging

Embodiments of the invention relate to partial authentication to access incremental information. An aspect of the invention concerns a method of authorizing access to information that comprises providing an initial segment of a password wherein the password includes password segments each associated with an incremental portion of the information. In response to the initial password segment satisfying an expected value, the method may authorize access to the information portion associated with the initial password segment. The method may authorize access to other information portions associated with subsequent segments of the password in response to the subsequent password segments satisfying respectively expected values.

Partial authentication for access to incremental data

Growing community of inventors

Neuquen, Argentina

Hernan Badenes