International Business Machines Corporation

Deepti M Naphade

Yuk Lung Chan

Heidi L Lagares-Greenblatt

Jairo A Pava

Christopher Cramer

Robert G King

Tin Hang To

Lawrence Alfred Clevenger

Alain F Loiseau

Jenny S Li

Xinlin Wang

Marie R Laser

Daniel Acevedo

Steven M Jones

Michael P Kreig

Michael L Greenblatt

Methods, systems and computer program products for prompting web-based user interaction are provided. Aspects include determining a plurality of items of interest based on data associated with a user. Aspects also include associating an emotion with each item of the plurality of items of interest. Aspects also include associating an emotion with each digital media clip of a plurality of digital media clips. Responsive to detecting an internet browsing action performed by the user, aspects include displaying a selected digital media clip of the plurality of digital media clips and a selected item of interest of the plurality of items of interest. The selected digital media clip and the selected item of interest are associated with a same emotion.

Prompting web-based user interaction

Methods, systems and computer program products for providing a customized display of social media content are provided. Aspects include receiving a plurality of social media posts that have been published for display by a social media service. Aspects also include receiving a profile associated with a user of the social media service including social media post filtering preferences. The social media post filtering preferences are created based at least in part upon an analysis of social media posts that were previously disliked by the user. Aspects further include identifying a set of acceptable social media posts and a set of unacceptable social media posts. Aspects also include causing the set of acceptable social media posts to be displayed in a news feed window of the social media service in association with an account of the user of the social media service.

Customized display of filtered social media content using a private dislike button

A method is provided for identifying a strength of an input picture password formed by performing a sequence of gestures relative to a picture. The method includes storing, in a memory device, a crowdsource history of picture passwords each of which include a picture and a sequence of gestures on the picture. The method further includes generating, by a processor-based demography-based pattern usage assessment generator, a demography-based pattern usage assessment by analyzing the crowd source history. The method also includes providing, by a user-perceptible indication device, an indication of the strength of the input picture password in accordance with the demography-based pattern usage assessment.

Picture/gesture password protection

Methods, systems and computer program products for identifying customer groupings in a smart store are provided. Aspects include detecting a plurality of customers in the smart store and retrieving stored associations for at least one of the plurality of customers from a customer database based on data captured for each of the plurality of customers. Aspects also include tracking a movement of each of the plurality of customers through the smart store and updating the stored associations in the customer database between two or more of the plurality of customers that are determined to be shopping together based on their movement through the smart store. Aspects further include charging a single customer of the plurality of customers for items removed from the smart store by another customer based on the stored associations.

Customer tracking and inventory management in a smart store

Provided are embodiments including a method, system, and computer program product for identifying how to deliver advertisements to a user based on the user sentiment and learned behavior. The embodiments provide for collecting information on the sentiment of a user, monitoring user interactions based at least in part on the collected emotional information on the sentiment of the user, and determining a pattern of user interactions with one or more applications of a user device based on the sentiment information. The embodiments also provide for determining a pattern of user responses to an advertisement based on the sentiment information, and generating a profile based at least in part on the pattern of user interactions and the pattern of user responses.

Delivering advertisements based on user sentiment and learned behavior

A computer-implemented method includes providing a first mapping between a set of two or more IP addresses and a set of two more servers. The first mapping is embodied in a virtual network layer modifiable by a workload advisor based on a weight recommendation. A plurality of transactions are received from a load balancer. The weight recommendation for the servers is received, where the weight recommendation defines a goal for weighting transactions among the servers. A second mapping, from the two or more IP addresses to the servers, is determined dynamically by the workload advisor, based on the weight recommendation and absent communication between the load balancer and the workload advisor. A second plurality of transactions are received and are routed to the servers through the virtual network layer according to the second mapping.

Transaction distribution with an independent workload advisor

In an approach to a passively managed loyalty program using customer images and customer behaviors, one or more processors may receive one or more customer characteristics and one or more customer behaviors. One or more processors may also query for a first user based on the one or more customer characteristics and the one or more customer behaviors. One or more processors may further receive a user profile ID based on the query. One or more processors may additionally store at least one customer characteristic from the one or more customer characteristics and at least one customer behavior from the one or more customer behaviors under the user profile ID.

Passively managed loyalty program using customer images and behaviors

In an approach to determining quality score of images for user identification, one or more processors receive a set of input images for a first user. One or more processors may determine a quality score for each image in the set of input images with respect to an ability of each respective image to identify the first user, wherein the quality score pertains to both: (i) a quality the image, and (ii) a quality of a subject of the image. One or more processors may additionally determine a first set of output images based on the quality score for each image in the set of input images. One or more processors may further identify the first user based on the first set of output images.

Determining quality of images for user identification

In an approach to establishing personal identity using user identity patterns, one or more processors receive a set of input images corresponding to a period of time, where each input image in the set of input images corresponds to a specific time within the period of time. One or more processors may also identify a first user in the set of input images and determining, a user identity pattern based on the set of input images, where the user identity pattern includes multiple instances of at least one physical characteristic of the first user over the period of time. One or more processors may further determine a user behavior based on the user identity pattern. One or more processors may additionally associate the set of input images and the user identity pattern with a first user profile for the first user.

Establishing personal identity and user behavior based on identity patterns

In an approach to identifying users by real time contextual data, one or more processors may receive a registration information for a first user and a first biometric data for the first user. One or more processors may determine a first user behavior based on the first biometric data and the registration information for the first user. Additionally, one or more processors may store the registration information, the first biometric data, and the first user behavior in a first user profile for identification of the first user.

Establishing personal identity using real time contextual data

A method for augmenting a review. The method includes accessing a review database and a particular review of an object. Providing a reviewer profile including a plurality of reviewer attributes and analyzing the reviewer attributes to determine a rationale for the review.

Augmented reviews with cognitive reasoning

Techniques are provided for performing automated operations to analyze incoming user messages. An indication of a message sent to a recipient user is received. Based at least in part on natural-language processing of the contents of the received message, the received message is analyzed. Such analysis includes determining an action date associated with the received message that is distinct from a date on which the received message was sent to the recipient user, and determining one or more action items corresponding to that action date. An indication of the action date and the one or more corresponding action items may be provided to each of one or more relevant third parties prior to the action date in order to facilitate the display of an additional message to the recipient user regarding the corresponding action items.

Automated relevance analysis and prioritization of user messages for third-party action

Embodiments include methods, systems, and computer program products for remediating a color vision deficiency. Aspects include receiving a user profile. Aspects also include receiving a real time location image including a plurality of objects. Aspects also include determining an image context. Aspects also include generating a situational notification based at least in part upon the user profile, the real time location image, and the image context.

Cognitive situation-aware vision deficiency remediation

A computer identifies one or more privacy settings. The computer receives a query for information. The computer determines whether a response to the query satisfies the one or more privacy settings. If the computer determines that the response to the query does not satisfy the one or more privacy settings, the computer alters the response to satisfy the one or more privacy settings.

Data security system

A method of generating a targeted advertisement by identifying a target criteria from an entry of a search history associated with a user, identifying an intended recipient based on social information associated with the user and the target criteria, and associating at least one item with the intended recipient by analyzing the social information and the target criteria. Further, the method includes outputting as advertisement information the at least one item and at least one of a plurality of advertisement recipients. The advertisement information enables the generation of the targeted advertisement and the at least one item is utilized in the targeted advertisement.

Growing community of inventors

Fishkill, NY, United States of America

Deepti M Naphade