International Business Machines Corporation

Munish Goyal

Sarbajit Kumar Rakshit

Kimberly Greene Starks

Wing L Leung

Raphael Ezry

Qin Shirley Held

Steven M O'Brien, Jr

Parul Arora

Craig M Trim

Uri Klein

Jason Boada

Sanjay Kumar Prasad

Nilanjana Chandra

Rachel Cohen

Anthony Gridley

Balasubramanian E A

Nithya Ramkumar

Brett A Squires

Jonathan A DeBusk

Chirdeep Gupta

LanXiang Ye

Jingzi Tan

Barbara S O'Loughlin

James Edward Bostick

Shikhar Kwatra

Zachary A Silverstein

Krishnasuri Narayanam

Ramasuri Narayanam

Mary E Rudden

Gyana Ranjan Parija

Nandakishore Kambhatla

Debapriyo Majumdar

Soujanya Soni

Rohit Manohar Lotlikar

Sambuddha Roy

Pavithra Krishnan

Shivaram Kulkarni

Simon Thomas

Dangaia Sims

Milind V Vaidya

Anita Karlsson-Dion

Sameer Singhdeo

Gabriel Asaftei

Shobhit Varshney

Michael Wendel

Avinash Arya

Jeremy Chase

Methods and systems for mobile automation control of disease spread are disclosed. A computer-implemented method includes: determining, by a computing device, a health status of a person; determining, by the computing device, that the person is sick based on the health status; determining, by the computing device, facial and body movements of the person determined to be sick; determining, by the computing device, that the person determined to be sick performed a germ-transmitting activity based on the facial and body movements; and deploying, by the computing device, a cleaning robot to clean based on the determining that the person determined to be sick performed the germ-transmitting activity.

Mobile automation control of disease spread

In an approach for predictive forecasting of food allocation, a first data is received from one or more sensors. The amount and condition of available food is determined from the first data. The number and location of people is determined from the first data. The received data is modified to create a second data. One or more food requirements for the people are predicted based on the number and location of people and the second data. An optimal food allocation for the people is predicted based on the amount and condition of food available and the one or more food requirements. The optimal food allocation is reported.

Predictive forecasting of food allocation

A method includes: detecting, by a computing device, a new entry in one of plural databases; comparing, by the computing device, the new entry to watch entries defined in a watch database; determining, by the computing device, whether the new entry matches a watch entry in the watch database; creating, by the computing device, a new watch in the watch database when the new entry does not match any watch in the watch database; and updating, by the computing device, a watch in the watch database when the new entry matches the watch in the watch database.

Self-healing accounting system

A computer-implemented method includes: receiving, by a computing device, a plurality of journal entries from a plurality of transactional systems; determining, by the computing device, association scores for a plurality of pairs of journal entries selected from the plurality of journal entries; generating, by the computing device, a reconciliation graph including a plurality of nodes representing the plurality of journal entries and a plurality of edges based on the determined association scores; recommending, by the computing device, actions to apply to at least one journal entry of the plurality of journal entries to minimize a number of nodes not connected by the plurality of edges in the reconciliation graph; receiving, by the computing device, feedback regarding the recommended actions to apply to the at least one journal entry; and updating, by the computing device, the reconciliation graph based on the feedback.

Multi-way optimal reconciliation and recommendation

A method, apparatus, system, and computer program product for estimating a mass of a prepared food product. An ultrasonic beam is steered by a computer system at the prepared food product on a platform. An estimate of a mass of the prepared food product on the platform is determined by the computer system using response signals detected in response to scanning the prepared food product on the platform with the ultrasonic beam.

Mass estimation of prepared food products

A method and system for identifying workplace risk factors is provided. The method includes monitoring via execution of multiple geographically distributed sensor devices, workplace injury based events associated with individuals at a multisite distributed workplace environment. Current injury data describing the workplace injury based events is stored and predicted future workplace injury based events associated with future workplace injury based events with respect to a predicted plurality of individuals at the multisite distributed workplace environment are determined. Injury risk mitigating actions associated with prevention of said predicted future workplace injury based events are generated and an associated cost optimized reduction plan for prioritized implementation of the injury risk mitigating actions is generated.

Injury risk factor identification, prediction, and mitigation

An offer specifying a physical product, a physical location, a time limit, and an upper limit of instances of the physical product is configured. An optimal item exhaustion rate corresponding to the offer is determined. An expected conversion rate corresponding to the offer and an expected customer travel time corresponding to the offer are forecasted for a registered customer. The registered customer is computed as a prospective customer. Using the optimal item exhaustion rate and the expected customer travel time, an offer time corresponding to the prospective customer and the offer is selected to allow the prospective customer to arrive at the physical location at a time consistent with the optimal exhaustion rate, the time being before the time limit and before a number of sold instances of the physical product exceeds the upper limit. The offer is transmitted at the offer time.

Point of purchase based physical item offer optimization

An approach is provided in which the approach aggregates a set of pixel values from a bitmap image into a set of row sum values and a set of column sum values. The bitmap image is a pixelated representation of a document. The approach applies a localized Fourier transform to the set of row sum values and the set of column sum values to generate frequency representations of the set of row sum values and the set of frequency sum values. The approach decomposes the bitmap image into a set of image portions based on at least one separation location identified in the set of frequency representations, and sends the set of image portions to a text recognition system.

Scalable structure learning via context-free recursive document decomposition

Bias identification in social network posts. A method performs a semantic comparison of social network posts by a user of a social network to identify a group of social network posts by the user about a specific topical content category. The method determines a respective semantic sense of each social network post of the group. The method also ascertains a semantic sense pattern among social network posts in the group of social network posts about the specific topical content category. The method identifies a bias in at least one social network post of the group of social network posts based on identifying that the respective semantic sense in each of the at least one social network post deviates from the ascertained sematic sense pattern. The method uses the identified bias to predict bias in one or more other social network posts made by the user on the topical content category.

Bias identification in social network posts

A method and system for improving document lifecycle editing and storage technology is provided. The method includes enabling interactions between a user and a hardware controller. Editor profiles associated with editing privileges of the user are generated. The editor profiles include parameters generated based on a performance of past edits. The editing tasks are automated task difficulty attributes associated with a difficulty of executing the editing tasks are generated. The editing tasks may include readability and consolidation tasks. An optimized version of the editing tasks is assigned to software editors and time periods associated with the software editors completing the editing tasks are tracked. The optimized version of the editing tasks is generated based on the editor profiles and new tasks for assignment. User permissions and alerts are monitored and recommendation actions associated with the editing tasks are generated. The editing tasks are modified for future execution.

Automated editing task modification

A method and system for improving linguistic data and storage technology is provided. The method includes receiving data input text from a user and identifying text within the data input text. The data input text is edited and improvements in the data input text are detected via a machine learning process. In response, a modified version of the user interface is generated for allowing additional users to view and modify additional data input text. Change attributes associated with the data input text with respect to the modified version of the user interface are determined and alternative input suggestions are ranked. Editing data and code are generated in response to an editor engine interacting with a hardware controller. The editing data and code is executed thereby updating and modifying functions associated with software engines to increase an efficiency of future recommendations associated with future data input text analysis.

Updating and modifying linguistic based functions in a specialized user interface

For a task that has been partially executed, a residual complexity index is computed, the task being of a complexity that cannot be ascertained prior to executing the task. An evaluation is made whether the residual complexity index exceeds a cost of a resource that should be considered for allocation to the task. When the evaluation is affirmative, a priority of the task is established relative to a second task. The resource is scheduled to perform the task according to a timing, the timing being determined using the cost of the resource. The resource is allocated to the task according to the timing.

Resource allocation for tasks of unknown complexity

Objects are located. Locations of objects in an area are tracked using a sensor system monitoring the area. Whether a user is performing an object search in the area is determined based on a sequence of actions detected by the sensor system for the user in the area. An identity of an object that is a subject of the object search by the user is inferred using the sequence of actions and a history of patterns of actions performed by the user searching for objects in response to a determination that the user is performing the object search. The user is guided to the object using a last tracked location for the object in the locations of objects tracked by the sensor system in response to inferring identify of the object that is the subject of the object search by the user.

Action based object location system

Methods, systems, and computer program products are provided for remediating an instance of a visual notification interfering with an output of an application on a display device of an electronic device. An instance of a visual notification is identified on a display device. The visual notification is determined to be interfering with the output of the application on the display device. User response to the output of the application is monitored. An assessment is made, based on the monitoring, of an effectiveness of the output of the application. It is determined, based on the assessment, that there exists a failure of the effectiveness of the output of the application. A remediation action is performed in response to the determined failure. The remediation action may include removal of the instance of the visual notification, terminating a parent process of the instance of the visual notification, or restarting the electronic device.

Remediating interference of an instance of a visual notification with an output of an application on a display device

Methods, computer program products, and systems are presented. The methods include, for instance: obtaining a product video representing a product and review feeds authored by a user. Product features are extracted from the product video and user specific features are extracted from the review feeds. User specific add-on content is generated based on the user specific features and user data. The user specific add-on contents are overlaid onto the product video when the product feature corresponding to a user specific feature of the user specific add-on content.

Media enhancement with customized add-on content

Growing community of inventors

Yorktown Heights, NY, United States of America

Munish Goyal