International Business Machines Corporation

Shailendra Moyal

Akash U Dhoot

Venkata Vara Prasad Karri

Sarbajit Kumar Rakshit

Nitin S Jadhav

Partho Ghosh

Nitika Sharma

Niteen D Lakhe

Shilpa Bhagwatprasad Mittal

Shikhar Kwatra

Hariharan Krishna

Abdullah Q Chougle

Sagar D Joshi

Madhu Akhilesham

Rojan Jose

Sneha J Heda

Ishan Rastogi

Animesh Gupta

Hemant Kumar Sivaswamy

Bhavuk Srivastava

Pavan Kumar Penugonda

Sowjanya Rao

Naga Srinivasa Reddy Padala

Vamsi Vasireddy

Amit Kumar Senapaty

Madhukar Hari Kishan Gobbi

Sekhar Reddy Dandu Reddy

Vaibhav Telang

Khader Saheb Shaik

Rasika Ashirwad Vyawahare

Kiran Kumar H N

Akanksha

Lakshmojee Rao Vulli

Arpita Girish Gudihal

Rajesh Prabhakar Dhagare

Divyesh Garg

Subir Ghosh

Srikanth Vankara

Manali Tanpure

Murali Pasala

Karan K Navani

Joseph Korting

Brian M Arthur

Computer technology that receives a query and a desired level of precision and/or accuracy (herein, a 'p/a value') associated with the received query, determines whether the p/a value exceeds a predetermined threshold, if the p/a value exceeds the predetermined threshold, then the virtual assistant system applies digital twin simulation to a digital twin data set in determining the query response to improve precision and/or accuracy of the query response, and outputs the query response to the querying party (for example, output as sound data in a voice assistant system). If the p/a value is below the threshold value, then the digital twin simulation is not performed, which makes the response quicker and puts less computational power demands on the virtual assistant system. In some embodiments, the virtual assistant system calculates the p/a value based on context.

Computer technology for controlling digital twin simulation in voice assistant devices

Allocating processing activities among multiple computing devices can include identifying multiple computing activities of a computer-executable process and, for each computing activity identified, estimating in real time the computing resources needed. The identifying can be in response to detecting a computer-executable instruction executed by one multiple communicatively coupled computing devices, and the computer-executable instruction can be associate with the computer-executable process. A current condition and configuration of each of the computing devices can be determined in real time. For each computing device an effect induced by executing one or more of the plurality of activities can be predicted, the predicting based each computing device's current condition and configuration and performed by a machine learning model trained using data collected from prior real-time processing of example process activities. Based on the predicting, computing activities can be allocated in real time among the computing devices.

Multi-device processing activity allocation

According to one embodiment, a method, computer system, and computer program product for precise alignment of one or more augmented reality objects is provided. The present invention may include identifying one or more physical objects in a physical environment that will be overlaid with the one or more AR objects; monitoring positions of the one or more identified physical objects with an AR device and one or more connected computing devices; analyzing data of the one or more identified physical objects; and aligning the one or more AR objects precisely to the one or more identified physical objects based on the analyzed data of the one or more physical objects.

Precise alignment of augmented reality objects with physical objects

According to one embodiment, a method, computer system, and computer program product for volumetric video modification is provided. The embodiment may include generating a volumetric video from a multi-camera feed. The embodiment may also include presenting the generated volumetric video to a user. The embodiment may further include receiving one or more user inputs to the presented volumetric video. The embodiment may also include modifying the volumetric video based on the one or more user inputs. The embodiment may further include presenting the modified volumetric video to the user.

Volumetric video modification using a virtual reality system

An approach for providing movement settings for a smart bed associated with an immobile patient is disclosed. The approach includes retrieving patient data and retrieving environmental data. The approach analyses patient profile and creates a digital twin of patient. In the digital twin environment, the approach models the patient movement and send patient movement setting based on desired outcome. Finally, the approach sends instructions to the smart patient bed.

AI based context aware multidirectional patient movement

Enhancing data-driven decision making can include generating a contextual insight data structure using a first artificial intelligence system operating on information data structures selected based on a context of a programmatically defined action. A perception data structure can be generated using a second artificial intelligence system that performs natural language processing of programmatically defined action communications. The perception data structure and the contextual insight data structure can be compared, and in response to detecting a structural variance, the perception data structure can be populated with one or more data items selected from the information data structures. A delta can be determined between the contextual insight data structure and the perception data structure based on a predetermined metric that measures a quantitative difference between the contextual insight object and the perception object. An electronic recommendation based on the delta can be generated and delivered to a user via a user device.

Data-driven decision enhancement

A computer hardware system associated with a hybrid cloud including a private cloud and a public cloud has a hardware processor configured to perform the following executable operations. A plurality of data sets of unprocessed data is randomly sampled to generate a plurality of random samples respectively associated with each of the plurality of data sets. The plurality of random samples is pre-processed, using a machine learning engine, to identify hidden correlations contained therein. The hidden correlations are evaluated against a confidentiality model to characterize each of the plurality of segments as to confidentiality. The data sets are segmented by assigning the data sets to one of the private cloud or the public cloud based upon the evaluating. Data sets assigned to the private cloud based upon the segmenting are processed using the private cloud.

Segmentation of data in hybrid cloud

Disclosed are techniques to determine navigation paths for mobile points of consumption of edge computing resources where the edge computing resources are at least partially hosted on satellite devices. Datasets corresponding to a set of edge computing satellites are received describing their positions, orbital paths, and edge computing resources. Further datasets are received corresponding to mobile points of consumption of edge computing resources. Using both datasets, predictions are determined corresponding to demand for edge computing resources of the edge computing satellites. When a new mobile point of consumption of edge computing resources queues up a transit route to a destination, that transit route and the accompanying requirement for edge computing resources is compared with the determined predictions of resource availability. Where sufficient edge computing resources are unavailable for a transit route, a new route is generated to transit through regions where sufficient edge computing resources are predicted to be available.

Transit routes with orbital edge computing resource availability for mobile edge computing consumption points

A processor may receive a first command and a second command from one or more users. A processor may analyze the first command and the second command. A processor may determine command information associated with the first command and the second command. A processor may display the command information to at least one of the one or more users on a display screen. A processor may receive a response from the at least one of the one or more users associated with the command information on the display screen. A processor may execute the first command and the second command based, at least in part, on the command information and the response.

Multiuser voice command visualization

A a method for robotic assistance continuity to a pedestrian using gait recognition. The method includes determining a gait pattern of the pedestrian based on analysis of visual data obtained at a first position. The pedestrian is provided assistance based on a query at the first position. The pedestrian is identified at a subsequent position by identifying the gait pattern from analysis of visual data obtained at the subsequent position. The need for additional pedestrian assistance is determined at the subsequent position.

Robotic assistance continuity using pedestrian gait recognition

The present inventive concept provided for a method for identifying a natural solution to solve a problem. The method includes identifying the problem in environmental multimedia of an environment; identifying the natural solution to the identified problem and required capabilities thereof based on a mapping; and generating a machine-based solution based on the natural solution.

Identifying natural solutions to problems

A method for managing self-configuration of sensors based on geofencing and context awareness includes determining a position for each object from a plurality of objects within a location. The method also includes segmenting the plurality of objects based on a plurality of parameters, where each parameter provides context to each object and at least one sensor on each object with respect to the location. In response to determining a plurality of geofence areas for the segmentation of the plurality of objects, the method also includes determining a plurality of sensor configurations for the plurality of objects, wherein each sensor configuration is for the at least one sensor on each object. In response to determining an action is performable based on a first sensor configuration from the plurality of sensor configurations, the method also includes performing the first sensor configuration on a first object from the plurality of objects.

Geofencing and context based sensor self-configuration

An approach for a computer program to retrieve historical incident data associated with a contaminated site to predict a future incident at the contaminated site. In the approach, the computer program evaluates the historical incident data to determine a deployment of a plurality of unmanned vehicles to form a virtual fence around the contaminated site. Furthermore, in the approach, the computer program determines instructions for the deployment of each of the plurality of unmanned vehicles to form the virtual fence around the contaminated site. In the approach, the computer program sends the instructions to form the virtual fence to each of the plurality of unmanned vehicles.

Virtual fencing of a contaminated area

In an approach for improving robotic automation systems, a processor receives a request for a set of materials for an activity to be performed. A processor identifies one or more materials of the set of materials. A processor determines a sequence of operations to move the one or more materials. A processor prompts a first robot to pick a first material at the place of origination using a clamping system and to deposit the first material in a first micro trolley. Responsive to determining an arm of the first robot is in a first orientation, a processor moves the first material along a first track on an arm of a multi-robotic system from the place of origination to the place of destination. A processor prompts a second robot to pick the first material from the first micro trolley at the place of destination using the clamping system.

Material movement track to assist robotic arm

In an approach to security for displayed confidential holographic objects, one or more computer processors receive a request from a user to display a holographic object in association with a device. One or more computer processors identify content to be moved to the holographic object. One or more computer processors determine the content includes confidential information. One or more computer processors request authentication from the user. One or more computer processors receive the authentication from the user. One or more computer processors create a holographic boundary, where the holographic boundary blocks a view of the holographic object from one or more unauthorized users. One or more computer processors display the holographic boundary. One or more computer processors display the holographic object in association with the device.

Growing community of inventors

Pune, India

Shailendra Moyal