International Business Machines Corporation

Petrogal Brasil S.a.

Renato Fontoura De Gusmao Cerqueira

Marcio Ferreira Moreno

Emilio Ashton Vital Brazil

Rafael Rossi De Mello Brandao

Rodrigo Da Silva Ferreira

Vagner Figueredo De Santana

Ana Fucs

Viviane Torres Da Silva

Vinicius Costa Villas Boas Segura

Lucas Correia Villa Real

Kiran Mantripragada

Daniel Salles Civitarese

Ulisses Mello

Igor Cerqueira Oliveira

Rafael R De Mello Brandao

Marcelo Nery Dos Santos

Daniel Salles Chevitarese

Marcio F Moreno

Joana De Noronha Ribeiro De Almeida

Juliana Jansen Ferreira

Dario Sergio Cersosimo

Alecio Pedro Delazari Binotto

Bianca Zadrozny

Rogerio Abreu De Paula

Sergio Borger

Bruno Da Costa Flach

Leonardo Guerreiro Azevedo

Matheus Palhares Viana

Ulisses Thibes Mello

Michael Raghib Moreno

Marco Daniel Melo Ferraz

Leonardo Pondian Tizzei

Astrid De Jesus Torres Fernandez

Helon Vicente Hultmann Ayala

Wallas Henrique Sousa Dos Santos

Raquel Zarattini Chebabi

Leonardo Silveira De Albuquerque Martins

Raphael Melo Thiago

Elton Figueiredo De Souza Soares

Bruno Felix Carvalho

Vinícius Costa Villas Boas Segura

Alexandre Pfeifer

A computer-implemented method, a computer system and a computer program product coordinates knowledge from visual elements in a collaboration session. The method includes obtaining collaboration session data. The collaboration session data includes a plurality of visual elements and a plurality of participant interactions. The method also includes identifying a subject and a link in the plurality of visual elements using a text recognition algorithm. In addition, the method includes applying a weight to the link based on the plurality of participant interactions and a distinct characteristic in the plurality of visual elements. Lastly, the method includes generating a knowledge graph. The nodes of the graph comprise the subjects and the edges of the graph comprise weighted links.

Coordinating knowledge from visual collaboration elements

Storing and retrieving subsurface rock physical property models for well drilling by generating estimated subsurface rock physical property models based on a respective set of seismic data, determining a stratigraphic classification for each model based on seismic interpretation data; storing the models associated classification in a database, determining characteristics of the seismic data used to generate the models, selecting from the database a subset of the models based on a similarity of the stratigraphic classification, determining measures of similarity between the characteristics of the seismic data used to generate each of subset of the models and a new set of seismic data and retrieving an estimated subsurface rock physical property model from the subset models based on the similarity measures.

Storage and retrieval of subsurface rock physical property prediction models using seismic interpretation

A plurality of datasets may be received. Multiple instances of a machine learning algorithm may be run to create corresponding multiple machine learning models trained for a specific task in a given domain. Each of the multiple instances may use a different subset of the plurality of datasets in training the corresponding machine learning model. The multiple machine learning models may be run with input data. The multiple machine learning models produce corresponding multiple outcomes. A candidate machine learning model may be determined based on comparing each of the multiple outcomes with ground-truth output. A value associated with the different subset of the plurality of datasets may be determined based on comparing of each of the multiple outcomes with ground-truth output. A smart contract may be created which may include the value and the different subset of the plurality of datasets. The smart contract may be recorded in a blockchain.

Data platform to protect security of data

Machine teaching in an embodiment can include receiving a user annotated concept for a given image in given context. The given image can be broken into parts and classified. Relationships can be determined associated with the parts. The created relationships can be stored along with the user annotated concept in a knowledge base. One or more similar images can be annotated using the parts and relationships. A second image associated the given context can be retrieved, decomposed into parts. The parts can be classified. Relationships can be determined associated with the second image's parts. Classifications and relationships associated with the second image's parts can be compared with classifications and relationships associated with the given image's parts. Based on comparing, the second image can be annotated with the user annotated concept for the given image.

Machine teaching complex concepts assisted by computer vision and knowledge reasoning

A hybrid knowledge representation is searched for a machine learning component corresponding to a search query. The hybrid knowledge representation may be structured as nodes representing machine learning workflow components and edges (e.g., links) connecting the nodes based on relationships between the nodes. Responsive to finding the machine learning component in the hybrid knowledge representation, the machine learning component is returned. Responsive to not finding the machine learning component in the hybrid knowledge representation, the hybrid knowledge representation is searched for machine learning model fragments associated with building the machine learning component, generating a new machine learning component by combining the machine learning model fragments and returning the new machine learning component.

Machine learning engineering through hybrid knowledge representation

Embodiments of the invention are directed to a computer-implemented method of generating a pathway recommendation. The computer-implemented method includes using a processor system to generate an intermediate three-dimensional (3D) virtual reality (VR) environment of a target environment. A machine learning algorithm is used to perform a machine learning task on the intermediate 3D VR environment to generate machine learning task results including predicted features of interest (FOI) and FOI annotations for the intermediate 3D VR environment. The processor system is used to generate, based at least in part on the machine learning task results, the pathway recommendation configured to assist a user with navigating and interpreting a 3D VR environment including the intermediate 3D VR environment having the pathway recommendation.

Route recommendation that assists a user with navigating and interpreting a virtual reality environment

Document retrieval through assertion analysis on entities and document fragments is disclosed. A document is received. Logical structures and entities are extracted from the document by parsing the document. For an entity in the extracted entities, an object representing the entity is created, an assertion made in the document associated with the entity is determined, and the assertion is linked to the object representing the entity. A logical structure from the extracted logical structures and content of the logical structure containing the assertion are identified and linked to the object representing the entity.

Document retrieval through assertion analysis on entities and document fragments

A seismic dataset and a task to be performed with the seismic dataset may be received. A representative seismic line representative of the seismic dataset may be generated. The representative seismic line may include pixel data representative of the seismic dataset. Based on the representative seismic line, the task may be performed. The task may include at least finding an analogous geological region by searching for an analogous seismic dataset existing in a seismic database by comparing the representative seismic line with the analogous seismic dataset's representative seismic line.

Seismic data representation and comparison

A system, method and program product for evaluating a prospect. The method includes: receiving prospect information regarding a prospect for natural resource exploration; extracting a set of characteristics based on the prospect information; identifying a set of similar prospects and a set of prospect exploration results, based on the set of characteristics; receiving a success estimate for the prospect; validating the success estimate based on the set of characteristics, the set of similar prospects, and the set of prospect exploration results to determine inconsistencies in the success estimate; and approving the success estimate or receiving an updated success estimate, based on the inconsistencies in the success estimate.

Assisting prospect evaluation in oil and gas exploration

A document may be received. An ontology associated with a domain may be identified or retrieved. A set of concepts in the document may be extracted, the set represented in the ontology. A set of concepts selected from the ontology may be received. A search may be performed based on the set of selected concepts.

Document analogues through ontology matching

A document editor user interface interacts with a user in receiving content from the user and provides suggestions determined via cognitive computing to the user while the user is authoring a document. A search engine searches for information associated with the content and returns the information. A matching candidate template that matches a style of the document being authored is searched for and may be inferred based on the document being authored. The suggestions may be provided based on definitions of the candidate template. A cognitive component may continuously detect behavior of the user while authoring the document and store information associated with the detected behavior. Additional suggestions may be provided based on the detected behavior.

Automated document authoring assistant through cognitive computing

Systems and methods are described for mapping input devices in real time. The method may include controlling a camera to capture a plurality of images, performing object recognition on the images to identify a plurality of objects, determining properties for each identified object that enable the corresponding object to provide spatial data and interaction data of a preferred input device, ranking the objects according to the determined properties, presenting the identified objects in an order corresponding to the rank that enables a user to select one of the presented objects, tracking the selected object and a human being, generating spatial data and interaction data from a result of the tracking, and providing the generated spatial data and interaction data to a computer to emulate the events of the preferred input device.

Method and system to automatically map physical objects into input devices in real time

Automatically identifying speakers in real-time through media processing with dialog understanding. A plurality of audio streams may be received, an audio stream representing a speech of a participant speaking during an online meeting. A voice characteristic of a voice corresponding to the speech of the participant in the audio stream may be determined. The plurality of audio streams may be converted into text and a natural language processing may be performed to determine content context of the dialog. The natural language processing infers a name to associate with the voice in the audio stream based on the determined content context. A data structure linking the name with the voice may be created and stored in a knowledge base. A user interface associated with the online meeting application is triggered to present the name or identity of the speaker.

Automatically identifying speakers in real-time through media processing with dialog understanding supported by AI techniques

A computer-implemented method includes a step of generating a clipped image by applying a display map to a feedback image of a plurality of display devices that display a set of training frames. The method also includes a step of learning a first set of rules that transform the clipped image to match the set of training frames and a step of generating a rendered surface by applying the display map to an input image. Additionally, the method includes a step of generating a set of render frames by applying the first set of rules to the rendered surface and a step of sending the set of render frames to be displayed by the plurality of display devices.

Automatic real-time configuration of a multi-head display system

Growing community of inventors

Barra da Tijuca, Brazil

Renato Fontoura De Gusmao Cerqueira