International Business Machines Corporation

Alan Braz

Claudio Santos Pinhanez

Heloisa Caroline De Souza Pereira Candello

Martin J Hirzel

Todd W Mummert

Paulo Rodrigo Cavalin

Marisa Affonso Vasconcelos

Renan Francisco Santos Souza

Silvia C S Bianchi

Marco Aurelio Stelmar Netto

Peter Hans Westerink

Renato Luiz De Freitas Cunha

Lucas Correia Villa Real

Norman Bobroff

Avraham Ever Shinnar

Fabrizio Nascimento Caldas

Rogerio Abreu De Paula

Maira Gatti De Bayser

Luis Gregorio Moyano

Jason Tsay

Paulo Henrique Almeida Cavoto

Argemiro Jose De Lima

Flavio Vinicius Diniz De Figueiredo

A collection of code fragments loaded in an interactive development platform for running on a first processor can be received. A candidate fragment in the collection of code fragments can be determined for migration to a second processor based on characterizing the collection of code fragments. Based on a location of the candidate fragment in the collection of code fragments, a spot can be identified in the collection of code fragments to inject a code for saving program context. The code for saving program context can be injected in the identified spot. Responsive to the code for saving program context having run on the first processor and based on a criterion, the program context can be migrated to the second processor.

Program context migration

A machine-learning model task deduction method, system, and computer program product include extracting data schema of a machine-learning model and analyzing the data schema to determine an intended task of the machine-learning model.

Schema-based machine-learning model task deduction

Techniques facilitating guiding machine learning models and related components are provided. In one example, a computer-implemented method comprises identifying, by a device operatively coupled to a processor, a set of models, wherein the set of models includes respective model components; determining, by the device, one or more model relations among the respective model components, wherein the one or more model relations respectively comprise a vector of component relations between respective pairwise ones of the model components; and suggesting, by the device, a subset of the set of models based on a mapping of the component relations.

Guiding machine learning models and related components

Devices that consume power may be individually and uniquely associated with a blockchain wallet into which funds may be transferred. The device can be provided with a client application that executes within the device to determine an energy provider and the cost rate of energy supply. The client application calculates a value of energy consumption by the device and creates a blockchain transaction to transfer a funds value for the energy consumption from the device's blockchain wallet to a wallet of the energy provider. By providing devices that can self-manage their electricity supply and the accounting thereof, billing of power can be decentralized from a meter that meters all supply to a premises to individual devices. The requirement for a central billing entity, billing address, etc. can also be removed.

Method or system for management of a device for energy consumption by applying blockchain protocol

A conversational agent capability assessment method, system, and computer program product, includes assessing a performance, a personality and a cognitive trait of a conversational agent based on natural written language by a second conversational agent by combining an analysis of a plurality of metrics that each compare a metric from the conversational agent with a metric from the second conversational agent and producing a report detailing the performance, the personality, and the cognitive trait of the conversational agent.

System, method and computer program product for assessing the capabilities of a conversation agent via black box testing

A method for answering a natural-language user query includes receiving a query from a user by a central agent, parsing the query, and determining if an answer is known to the central agent as being within a local database. If the answer is known, the query is answered with a known natural-language answer using the local database. If not, artificial conversational entity (ACE) invocation is performed. The ACE invocation includes determining a topical field for the query, determining an ACE, of a plurality of ACEs, to send the query to, based on the topical field, and sending the query to the ACE. If the ACE is capable of answering, a natural-language answer is received from the ACE and presented to the user. If not, a natural-language answer is created using social knowledge and presented to the user. Social knowledge includes data crawled from subscriber-provided content of social media services.

System and method for managing artificial conversational entities enhanced by social knowledge

Identifying life events within social network feeds. The method may include receiving social media data. The method may include identifying life event data within the social media data. The method may include determining a life event probability score associated with a life event class for the life event data using metadata. The method may include assigning a first life event class to each item of life event data based on the life event probability score. The method may include creating conversations by grouping the life event data. The method may include extracting metadata. The method may include determining a conversation probability score for each conversation based on the metadata and the life event probability score associated with each item of life event data. The method may include assigning a second life event class based on the conversation probability score. The method may include displaying the conversations based on user preferences.

Identification of life events within social media conversations

A conversational agent capability assessment method, system, and computer program product, includes obtaining data to create at least one scenario for testing a conversational agent, performing a set of tests using a scenario of the at least one scenario created to assess a capability of the conversational agent, and comparing a result of the capability from the set of tests with an expected result of the scenario.

Backup and restore of digital data may utilize online social network parameters of a user to determine a number of parts into which to divide digital data and distribute the parts. A list of friends from the social network friends may be selected, e.g., based on a relationship to the user in the social network, to store the parts. The parts may be stored in a friend's device memory, each of the parts stored with a different friend. The digital data may be reconstructed by obtaining a threshold number of parts from the friends.

Growing community of inventors

Campinas, Brazil

Alan Braz