International Business Machines Corporation

John Handy Bosma

Jeremy R Fox

Leanna Holmquist

Martin G Keen

Jana Helton Jenkins

Victor Povar

Angineh Aghakiant

David Wayne Harrison

Paul P Giangarra

Lalitha Krishnamoorthy

Mayo Takeuchi

Raj Desai

Ryan Kallicharran

Sri Sai Anupama Pasumarthy

Amitabha Das

Raymond Fallon

Juan Leon

William Chamberlin

Robert Vanderheyden

Keith Goode

Carla Quinn

Elizabeth Kelly

Training an ordinal mapping deep neural network (OMDNN) can include receiving multiple samples, each a computer-processable data structure corresponding to a real-world object and including a data element indicating one of n predefined classes to which each sample is linked. Each sample can be mapped by the OMDNN to sample points of a multidimensional space. The OMDNN can predicts the class of each sample based on an ordinal mapping. Parameters of the OMDNN can be iteratively adjusted in response to misclassifying one or more samples. Iteratively adjusting the parameters can be based on an expected loss determined by an ordinal mapping loss function that measures (a) distances between each sample point in the multidimensional space and each other sample point of the same class and (b) overlap between sample points of different classes.

Neural network trained using ordinal loss function

Embodiments for capturing a micro-weather report by a UAS deployment by one or more processors are described. Micro-weather conditions at a selected location and altitude may be determined utilizing one or more sensor devices associated with the UAS. The collected micro-weather conditions data may be stored in a repository. A micro-weather report may be generated for the selected location and altitude according to the collected micro-weather conditions data stored in the repository.

Micro-weather report capture by unmanned aerial system (UAS) deployment

A method for microphone management is provided. The method includes receiving an enable secure audio indicator. In response to receiving the enable secure audio indicator, a set of computing devices are identified, and a communication is initiated to each device in the set of computing devices. The communication includes an instruction to disable a microphone associated with each respective device.

Management of computing device microphones

Embodiments for managing collaborative editing of content are provided. At least one user interface is provided to a first user and a second user. The at least one user interface is configured to selectively provide the first user and the second user with the ability to edit content. Time-limited editing periods associated with the at least one user interface are established for the first user and the second user. During a first of the time-limited editing periods, the first user is provided with the ability to edit the content, and the second user is prevented from editing the content. During a second of the time-limited editing periods, the second user is provided with the ability to edit the content, and the first user is prevented from editing the content. The second of the time-limited editing periods does not overlap with the first of the time-limited editing periods.

Methods and systems for managing collaborative editing of content

An embodiment for detecting and mitigating bias is provided. The embodiment may include receiving real-world data from a database. The embodiment may also include creating an inverted index from the real-world data. The embodiment may further include analyzing words in the inverted index. The analyzation may identify a plurality of categories in the real-world data. The embodiment may also include generating a structure template containing various entities within each category of the plurality of categories. The embodiment may further include receiving a test record of the structure template. The embodiment may also include providing alternative entities in the test record where bias is likely to occur. The embodiment may further include storing the test record. The embodiment may also include in response to determining bias exists, indicating a corrective action.

Detecting and mitigating bias in natural language processing

Preserving privacy of deleted personal data is provided. A registration of a client device is received. The client device stores a plurality of personal data corresponding to a plurality of data subjects. A copy of a set of personal data corresponding to a particular data subject deleted from the client device is received along with metadata describing the set of personal data deleted from the client device and a hash key based on the set of personal data deleted from the client device. Access to the copy of the set of personal data deleted from the client device is granted in response to receiving an access request that includes the hash key corresponding to the set of personal data from the particular data subject within a defined period of time. The copy of the set of personal data is deleted after expiration of the defined period of time.

Privacy preserving data deletion

A computer system analyzes user sentiment to dynamically modify a communication session. One or more user interactions are captured during a communication session, wherein a machine learning model is updated based on the captured user interactions. A likelihood score of a user terminating the communication session before performing one or more desired actions is calculated. In response to determining that the likelihood score is above a threshold value, one or more queries are presented, during the communication session, to the user, wherein the one or more queries are selected using the machine learning model. Received user feedback is analyzed to determine a user sentiment. The communication session is dynamically modified based on to the user feedback and the user sentiment. Embodiments of the present invention further include a method and program product for analyzing user sentiment to dynamically modify a communication session in substantially the same manner described above.

Method, medium, and system for analyzing user sentiment to dynamically modify communication sessions

A method, system and computer program product for providing user control of tracking user behavior. A request from a tracking implementer (e.g., website) for installing content (e.g., tracking cookies) on a user's computing device for tracking user behavior is detected. Alternatively, the installation of content by the tracking implementer on the user's computing device to track user behavior is detected. If the user had previously established a standard terms of service for the tracking implementer to abide in order to track the user's behavior, then a determination is made as to whether the tracking implementer agreed to accept such standard terms of service. If the tracking implementer did not agree to accept such standard terms of service, then the tracking implementer is blocked from tracking the user's online behavior, including blocking the tracking implementer from installing content on the user's computing device to track the user's behavior.

Growing community of inventors

Leander, TX, United States of America

John Handy Bosma