International Business Machines Corporation

Nizar Lethif

Kuntal Dey

Enara C Vijil

Saritha Arunkumar

Prasad P Purandare

Apurva S Patel

Young Min Lee

Emily A Ray

Kush Raj Varshney

Mary Elizabeth Helander

Joana Sofia Branquinho Teresa Maria

Hemank Lamba

Mudhakar Srivatsa

Various embodiments select advertisements for delivery to at least one mass media streaming device at a given location and time slot. Content and corresponding time and physical location information being posted in an online portal from at least one electronic device are obtained. The content is filtered based on time slot and physical location. A set of typical topics for a location and time slot are determined. A subset of advertisements is selected from a set of available advertisements based on the set of typical topics. The subset of advertisements is delivered to the at least one mass media streaming device. The mass media streaming device may be a television. A set of current topics for the location and time slot may be determined and aggregated with the set of typical topics. The subset of advertisements may be selected from the set of available advertisements based on the aggregated set.

System and method for targeting mass media ads on the television to given physical locations using online activity profiles at the locations

The system, method, and computer program product are disclosed that track the evolution of a network over time through the analysis of media corpora associated with nodes of the network at each time slice. The media corpora may be analyzed to generate word clusters for each time slice that are then compared across time slices to determine how the network has evolved. The evolution may be tracked by determining the similarity of each word cluster of a particular time slice to each word cluster of another time slice. The similarity may be measured by a similarity score for each comparison that may be combined to determine an overall similarity of the network between the two time slices.

Tracking the evolution of topic rankings from contextual data

Detecting equipment failure risk in industrial process may include distributing equipment operations data to a cluster of nodes based on a range of time and operation specified in maintenance data associated with the equipment. From a record entry in the maintenance data, an operation, installation and maintenance time may be determined. A plurality of nodes storing equipment operations data associated with the operation during a time range between the installation and the maintenance time are selected. Operation features may be determined by distributed processing operation in the plurality of nodes. The operation features are aggregated and added as an entry in a target table. Equipment failure risk is detected by risk failure analysis performed based on the target table. A signal may be sent to automatically adjust or correct one or more operation features.

Equipment failure risk detection and prediction in industrial process

A method of operating a configurable gaze tracking system includes initializing a plurality of sensors by determining positional information of the sensors, wherein the sensors establish a virtual framework, initializing a plurality of target objects by determining positional information of the target objects within the virtual framework, determining a current user using data output by the sensors, determining a gaze of the current user, matching the gaze to one of the target objects in the virtual framework, wherein a target object matched to the gaze is a current target object, and activating the current target object to receive input.

Configurable sensor array for a multi-target environment

An authentication control method, system, and computer program product, includes performing an initial calibration to login to a registered device by detecting a plurality of biological signals, biometric signals, and idiosyncratic signals of a user and selecting a combination of the plurality of biological signals, biometric signals, and idiosyncratic signals to use in an initial calibration-authentication score, computing a login-authentication score at a time of the login based on a user input of signals corresponding to the signals of the initial calibration-authentication score, and allowing the login to the registered device if the login-authentication score is within a predetermined threshold of the initial calibration-authentication score.

System, method and computer program product for controlling and altering biological, biometric, and idiosyncratic authentications

Methods and systems for determining a time dependent relevancy score of an agent node among an evolving heterogeneous network are described. A processor may expand the heterogeneous network by generating temporal heterogeneous networks representing states of the heterogeneous network at different times. The processor may extract a set of agent nodes from each temporal heterogeneous network and may generate a relationship network based on the extracted agent nodes for each temporal heterogeneous network. The processor may remove the agent node from the temporal heterogeneous network to generate a conditional relationship network excluding the removed agent node. The processor may determine a relevancy score for the agent node based on the corresponding relationship network and the conditional relationship network. Each relevancy score for the agent node may correspond to a temporal heterogeneous network and may indicate an impact of removing the agent node from the corresponding temporal heterogeneous network.

Node relevance determination in an evolving network

A split and merge advertisement method, system, and non-transitory computer readable medium, include splitting a first advertisement to be played on a second device when a moving user of a first group of users moves from a proximity of a first device to a proximity of the second device.

Splitting and merging advertisements to a plurality of devices

A processor-implemented method enables a device based on authentication of a particular user. One or more processors data mine past activities of a particular user. The past activities are detected by physical monitoring devices that monitor the particular user. The processor(s) create an authentication question and answer for the particular user based on the past activities of the particular user that the one or more processors have data mined. The processor(s) receive a request to use an electronic device used by the particular user, and then 1) transmit the authentication question to the electronic device used by the particular user and 2) receive an authentication answer to the authentication question from the electronic device used by the particular user. In response to the authentication answer from the electronic device matching the answer for the authentication question, the processor(s) remotely enable the electronic device for the particular user.

Authentication/security using user activity mining based live question-answering

A computer-implemented information verification method, system, and computer program product, include verifying a user device is within a proximity of a second device to grant access for the user device to a service available at a second location with the second device, where a trusted user operating the second device attests to a user device location of the user device so that the user of the user device accesses the service available only to users in the second device location of the trusted user independently of activities on the second device.

Location verification via a trusted user

A method for enabling at least one user interface display field to perform at least one action is provided. The method may include receiving a first user action associated with the at least one user interface display field. The method may further include activating the at least one user interface display field in response to the received first user action. Additionally, the method may include determining a context associated with the activated at least one user interface display field. The method may also include applying the determined context associated with the activated at least one user interface display. The method may further include receiving a second user action associated with the activated at least one user interface display field based on the applied determined context. The method may also include executing the received second user action.

Context sensitive active fields in user interface

A computer-implemented information verification method, system, and non-transitory computer readable medium, include acquiring a first measurement from a user device specific to a user device location, acquiring a second measurement from a second device specific to a second device location, comparing the first measurement with the second measurement, and verifying the user device is within a proximity of the second device to grant access for the user device to the second device, based on a result of the comparing.

System, method and computer program product for location verification

A method modifies a physical device for use by a particular person. One or more processors receive information from a sensor indicating a detection by the sensor of a sequence of actions performed by an unidentified person. The sequence of actions are physical actions performed in a particular order, and the physical actions are disparate types of physical movements performed by the unidentified person. One or more processors compare the sequence of actions performed by the unidentified person a known sequence of actions for a particular person. In response to the sequence of actions performed by the unidentified person matching the known sequence of actions for the particular person, one or more processors identify the unidentified person as the particular person and then modify a physical device for use by the particular person.

Personal identification using action sequences detected by sensors

A split and merge advertisement method, system, and non-transitory computer readable medium, include an advertisement splitting circuit configured to split the first advertisement to be played on a second device when a moving user of the first group of users moves from a proximity of the first device to a proximity of the second device as detected by the user identifying unit of each of the first device and the second device, an optimization circuit configured to optimize a second advertisement to be played on the first device for the first group of users having a new group composition and a third advertisement to be played on the second device for the moving user, and an advertisement merging circuit configured to merge the third advertisement with the second advertisement when the moving user moves from the second device to the first device.

Growing community of inventors

Croton-on-Hudson, NY, United States of America

Nizar Lethif