International Business Machines Corporation

Microsoft Technology Licensing, LLC

Renato Luiz De Freitas Cunha

Bruno Silva

Marco Aurelio Stelmar Netto

Ana Paula Appel

Eduardo Rocha Rodrigues

Vagner Figueredo De Santana

Lucas Correia Villa Real

Carlos Henrique Cardonha

Fernando Luiz Koch

Paulo Rodrigo Cavalin

Khalid Ahmed

Renan Francisco Santos Souza

Alecio Pedro Delazari Binotto

Marco A S Netto

Marcos D De Assuncao

Anirudh Badam

Leonardo De Oliveira Nunes

Alan Braz

Marcelo Nery Dos Santos

Nelson Mimura Gonzalez

Ariane Hernandes Amadeu

Vitor Henrique Leal Mesquita

Bernardo Nunes Goncalves

Roberto De Moura Estevão Filho

Henrique Von Atzingen Do Amaral

Marco As Netto

Guilherme Custodio De Souza

A topic for building a new intent on which to train a chatbot can be received. A database of chatbot training data can be searched for a candidate intent having meta-knowledge similar to the received topic. Utterances associated with the candidate intent can be extracted. The received topic and the extracted utterances can be input to a trained machine learning model. The trained machine learning model generates example utterances for the new intent. The new intent with the generated example utterances can be used as training data for training the chatbot.

Training example generation to create new intents for chatbots

Systems and methods for authoring workflows for processing data from a large-scale dataset include defining a metadata schema for the large-scale dataset, and receiving user input defining a workflow as a plurality of operations to be performed on the data. Each of the operations includes input metadata formatted according to the metadata schema. The input metadata describes input data to be processed by the operation and identifying a location for the input data in the data storage system, programmed instructions for performing an atomic operation on the input data to generate output data; and output metadata formatted according to the metadata schema. The output metadata describes the output data and identifying a location for the output data in the data storage system.

Systems and methods for authorizing workflows from a large-scale dataset using a metadata schema

A method of data transformation for acceleration of context migration includes monitoring user actions in a source code development environment using fragment-based source code documents are monitored. A content of each fragment of the source code document is determined. A sequence of execution of the fragments is determined. A status of a project captured by the source code development environment is determined. A fidelity of the data to be transformed to a new execution environment is determined. Upon determining that a new execution environment is warranted based on the determined fidelity, the new execution environment is determined. The one or more fragments are then executed in the new execution environment.

Data transformation for acceleration of context migration in interactive computing notebooks

An approach to identifying architectures of machine learning models meeting a user defined constraint. The approach can receive input associated with evaluating machine learning models from a user. The approach can determine acceptable architectural templates to evaluate the machine learning models based on the input and determine a list of architectures and metrics based on a calculation of maximum neural network sizes of the acceptable architectural templates not exceeding the constraint. The approach can send the list of architectures and metrics to the user for selection.

Automated machine learning model selection

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 method of conducting computing experiments includes executing a set of jobs based on user-selected parameters, learning a user strategy by checking the user-selected parameters during the executing of the set of jobs, and refining the user strategy by refining the set of jobs.

System and method for conducting computing experiments

A system for initiating web containers and isolating network traffic to web containers is described. The system initiates and uses web containers for associated web-based resources, such as domain addresses owned by a single entity. When a web container for a domain address has not been initiated, the system determines an owner of the domain address and any domain addresses associated with the owner and initiates a web container for the domain address and the associated domains. When a user navigates to the domain addresses associated with the determined owner, the system isolates the network activity to the initiated web container.

Internet activity compartmentalization

The present disclosure provides for crop yield estimation by identifying, via image processing, a field in which a crop is grown; identifying a plurality of regions within the field; identifying, by processing growth metrics via a model, a plurality of data collection points in the plurality of regions, wherein a given data collection point of the plurality of data collection points within a given region of the plurality of regions is identified by multivariate analysis as representative of growing conditions in the given region; receiving in-field data linked to the data collection points of the plurality; and predicting a yield for the crop in the field based on the in-field data.

Crop yield estimation

Aspects of the invention include receiving a first instructional video describing a first method of using a function of a first software application; determining each step of the first method described in the first instructional video; determining, by the processor, a second method of using a first function of a second software application, wherein the first function of the first software application is substantially the same as the first function of the second software application; and creating a second instructional video describing each step of the second method.

Automatic creation and annotation of software-related instructional videos

Described are techniques for application migration. The techniques include migrating an application to a target cloud infrastructure and generating a cost-aware code dependency graph during execution of the application on the target cloud infrastructure. The techniques further include modifying the application by removing source code corresponding to unused nodes according to the cost-aware code dependency graph and replacing identified source code of a high-cost subgraph of the cost-aware code dependency graph with calls to a generated microservice configured to provide functionality similar to the identified source code. The techniques further include implementing the modified application on one or more virtual machines of the target cloud infrastructure.

Application migration using cost-aware code dependency graph

A mobile device may generate a plurality of signals based on sensor data received from a plurality of sensors associated with the mobile device. Based on a logic combination of the plurality of signals, the mobile device may detect its status indicating one of different scenarios. Based on the detected mobile device status and a configured policy, the mobile device may determine a type of deletion action for deleting data on the mobile device. The mobile device may perform the determined type of deletion action.

Automatic and customized data deletion actions

In response to identifying one or more applications on a computing device, terms and conditions associated with the one or more applications are identified. A knowledge base based on the identified terms and conditions is generated. The knowledge base includes a determination of sensitive information of a user required by each of the identified one or more applications. Secondary associations of the identified one or more applications are identified from a plurality of external data sources with information related to the identified one or more applications. In response to identifying the secondary associations, it is determined whether sensitive information about the user is found in one or more of the identified secondary associations. In response to determining that sensitive information about the user is found, an advisory is transmitted to the user.

Managing sensitive user information

Chatbot logs can be received. The chatbot logs can be clustered or classified into clusters of potential intents. Trending topics can be detected by analyzing at least social media content. Semantic similarities between the potential intents and the trending topics can be computed. Based on the computed semantic similarities, at least one of the potential intents to at least one of the trending topics can be correlated. Training of the chatbot using the chatbot logs associated with the correlated potential intent can be triggered.

Conversational systems content related to external events

Approaches presented herein enable asset identification for collaborative projects in software development. More specifically, a plurality of assets is identified. Content provided by at least one asset of the plurality of assets is determined. A project that is associated with the content provided by the at least one asset is determined. A repository associated with the project to include the at least one asset is updated.

Asset identification for collaborative projects in software development

Techniques for maintaining a knowledge database system based on user interactions with the database system are described herein. An aspect includes generating a user interface based on a knowledge database comprising a plurality of entities, wherein the user interface comprises a plurality of user interface elements, each user interface element of the plurality of user interface elements corresponding to one or more of the plurality of entities of the knowledge database. Another aspect includes receiving a user interaction corresponding to the user interface. Another aspect includes updating the knowledge database based on the received user interaction, wherein updating the knowledge database based on the received user interaction includes determining a user interface element associated with the received user interaction, mapping the determined user interface element to a first entity of the plurality of entities of the knowledge database, and performing a weight update corresponding to the first entity.

Growing community of inventors

São Paulo, Brazil

Renato Luiz De Freitas Cunha