International Business Machines Corporation

Samarth Bharadwaj

Saneem Ahmed Chemmengath

Karthik Sankaranarayanan

Shivkumar Kalyanaraman

Ashish Mittal

Shreya Khare

Pankaj Satyanarayan Dayama

Pratyush Kumar

Jaydeep Sen

Suranjana Samanta

Vishwajeet Kumar

Mustafa Canim

Vinayaka D Pandit

Karthik Visweswariah

Ramachandra Kota

Ioannis Katsis

Talha Ahmad Siddiqui

A method, system, and computer program product for automated artificial intelligence (AI) factsheet generation for modeling and model customization in speech to text (STT) services. The method receives audio data for a user. The audio data contains human speech. Text data is generated, using a first speech to text model, to represent the human speech of the audio data. A set of transcription errors of the first speech to text model are identified. A set of AI factsheets are generated to describe model metadata for the first speech to text model. Based on the set of transcription errors and the set of AI factsheets, the method generates a second speech to text model customized to the user.

Artificial intelligence factsheet generation for speech recognition

An automatic speech recognition (ASR) computing system and methodology are provided to predict a textual representation of received input speech data. A context acoustic biasing (CAB) engine of the ASR computing system receives historical textual content and an ontology data structure. The CAB engine matches key terms identified in the historical textual content with concepts present in the ontology data structure to generate a contextual term list data structure comprising the concept terms related to concepts matching the key terms. The CAB engine generates acoustic representations of the concept terms in the contextual term list data structure and inputs them to an ASR computer model of the ASR computing system which processes an input speech signal to generate a predicted textual representation of the input speech signal. The predicted textual representation is biased towards the acoustic representations of the concept terms in the contextual term list data structure.

Ontology driven contextual automated speech recognition

A question answering bot that digests non-relational data tables is provided. A processor receives a question regarding a non-relational data table. A processor extracts at least one feature of the question using a natural language processing (NLP) model. A processor extracts at least one similar feature of the non-relational data table to the extracted at least one feature of the question. A processor determines at least one relevant cell in the non-relational data table based on the at least one feature of the question and the at least one similar feature of the non-relational data table. A processor provides an answer to the question, where the answer is based on the at least one relevant cell.

Natural language question answering using non-relational tables

Methods, systems, and computer program products for automated domain-specific constrained decoding from speech inputs to structured resources are provided herein. A computer-implemented method includes converting at least a portion of at least one user-provided speech utterance into text by processing the at least one user-provided speech utterance using an artificial intelligence-based automatic speech recognition model; automatically training an artificial intelligence-based decoding engine, wherein automatically training the artificial intelligence-based decoding engine comprising constraining the artificial intelligence-based decoding engine based at least in part on a domain-specific model and the artificial intelligence-based automatic speech recognition model; and generating at least one of one or more domain-specific text outputs related to one or more structured resources associated with the domain and one or more domain-specific action outputs related to the one or more structured resources associated with the domain by processing at least a portion of the text using the artificial intelligence-based decoding engine.

Automated domain-specific constrained decoding from speech inputs to structured resources

Methods, systems, and computer program products for providing a contextual dialogue framework over dynamic tables are provided herein. A computer-implemented method includes maintaining a context space for a natural language conversation of a user, wherein the context space comprises a dynamic set of one or more tables used for processing at least one query of the natural language conversation; obtaining an additional table associated with an additional query of the natural language conversation; discovering one or more implicit links between the additional table and the dynamic set of tables; updating the context space with the one or more implicit links; and answering the additional query based at least in part on the updated context space.

Contextual dialogue framework over dynamic tables

Methods, systems, and computer program products for generating concept images of human poses using machine learning models are provided herein. A computer-implemented method includes identifying events from input data by applying a machine learning recognition model to at least a portion of the input data, wherein the identifying comprises (i) detecting multiple entities from the input data and (ii) determining behavioral relationships among at least a portion of the multiple entities; generating, using a machine learning interpretability model and at least a portion of the identified events, images illustrating human poses related to at least a portion of the identified events; outputting at least a portion of the generated images to a user; and updating the machine learning recognition model based at least in part on (i) at least a portion of the generated images and (ii) input from the user.

Generating concept images of human poses using machine learning models

Methods, systems, and computer program products for operating re-configurable solar energy generators for increasing yield during non-ideal weather conditions are provided herein. A computer-implemented method includes determining, for each of multiple portions of the sky, by using one or more machine learning algorithms, a respective level of diffuse irradiance corresponding to image data from that portion; identifying one or more portions of the image data corresponding to the multiple portions of sky image data that include a higher level of diffuse irradiance, as compared to other portions of the image data; and configuring one or more solar photovoltaic modules based at least in part on the one or more identified portions of image data that include a higher level of diffuse irradiance.

Operating re-configurable solar energy generators for increasing yield during non-ideal weather conditions

Methods, systems, and computer program products for generating concept images of human poses using machine learning models are provided herein. A computer-implemented method includes identifying one or more events from input data by applying a machine learning recognition model to the input data, wherein the identifying comprises (i) detecting multiple entities from the input data and (ii) determining one or more behavioral relationships among the multiple entities in the input data; generating, using a machine learning interpretability model and the identified events, one or more images illustrating one or more human poses related to the identified events; outputting the one or more generated images to at least one user; and updating the machine learning recognition model based at least in part on (i) the one or more generated images and (ii) input from the at least one user.

Methods, systems, and computer program products for determining sensor placement and a reward sharing mechanism based on shared energy forecasting information are provided herein. A computer-implemented method includes processing multiple data streams derived from multiple respective energy-related sensors within a network, wherein each of the multiple energy-related sensors is linked to a respective one of multiple spatially distributed prosumers of the network; computing an expected utility, with respect to forecast accuracy of energy production within the network, of information captured by each of the multiple energy-related sensors based on said processing; determining a reward structure for each of the prosumers of the network based on the expected utility of the information captured by the energy-related sensors linked to each of the prosumers; and outputting a reward to each of the prosumers of the network in accordance with the determined reward structure.

Determining sensor placement and a reward sharing mechanism based on shared energy forecasting information

Methods, systems, and computer program products for cloud coverage estimation by dynamic scheduling of a distributed set of cameras are provided herein. A computer-implemented method includes transmitting one or more instructions to each of multiple spatially-distributed cameras in a pre-determined geographic area, wherein the one or more instructions cause each of the spatially-distributed cameras to change a context from (i) a pre-determined task to (ii) capturing one or more spatio-temporal measurements of cloud coverage; tracking the one or more spatio-temporal measurements of cloud coverage captured by the multiple spatially-distributed cameras; obtaining one or more meteorological measurements from one or more non-camera sources; and generating a cloud coverage forecast for the pre-determined geographic area based on (i) the one or more spatio-temporal measurements of cloud coverage captured by the multiple spatially-distributed cameras and (ii) the one or more meteorological measurements from the one or more non-camera sources.

Cloud coverage estimation by dynamic scheduling of a distributed set of cameras

One embodiment provides a method of prioritizing mobile finance customer follow up actions based on mobile device location data, the method including: utilizing at least one processor to execute computer code that performs the steps of: associating a mobile finance customer account with a mobile device; receiving a plurality of locations of the mobile device, the plurality of locations including at least one non-transactional location associated with a predetermined geographic location of interest; forming a mobility profile based on the plurality of locations; selecting, using a processor, a follow up action type based at least in part on the mobility profile; and transmitting, using a mobile network, a communication of the follow up action type to the mobile device. Other aspects are described and claimed.

Growing community of inventors

Bengaluru, India

Samarth Bharadwaj