公开(公告)号：US20230004555A1

公开(公告)日：2023-01-05

申请号：US17367605

申请日：2021-07-05

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Marcio Ferreira Moreno ,  Isabela Drabik Chaves Chambers Ramos ,  Rafael Rossi de Mello Brandao ,  Guilherme Augusto Ferreira Lima

IPC: G06F16/242 ,  G06F16/248

Abstract: A computer-implemented method of performing an incremental specification of a query includes extracting text from each of a plurality of participants in a dialog. A contextual information is determined of the extracted text of one or more of the plurality of participants. A dialog understanding operation is performed by processing at least the contextual information of the extracted text in a knowledge graph to identify in the dialog at least one or more of a structural gap, an information about entities, relationships, and actions. Query information is provided responsive to the dialog for at least one of filling the identified structural gap, or for providing additional information about one or more of the identified entities, relationships or actions in the dialog.

公开(公告)号：US20250021830A1

公开(公告)日：2025-01-16

申请号：US18352725

申请日：2023-07-14

Applicant: International Business Machines Corporation

Inventor： Achille Belly Fokoue-Nkoutche ,  IBRAHIM ABDELAZIZ ,  Maxwell Crouse ,  Shajith Ikbal Mohamed ,  AKIHIRO KISHIMOTO ,  Guilherme Augusto Ferreira Lima ,  Ndivhuwo Makondo ,  Radu Marinescu

IPC: G06N5/01

Abstract: Systems and techniques that facilitate name-invariant graph neural representations for automated theorem proving are provided. In various embodiments, a system can access a set of first directed acyclic graphs respectively representing a conjecture and a set of axioms. In various aspects, the system can generate, via execution of at least one neural-guided automated theorem prover that independently processes the set of first directed acyclic graphs, a proof for the conjecture. In various instances, the at least one neural-guided automated theorem prover can leverage, for a node representing a non-logical symbol name present in more than one of the set of first directed acyclic graphs, a name-invariant learned embedding based on a second directed acyclic graph that is an aggregation of the set of first directed acyclic graphs.

公开(公告)号：US11875550B2

公开(公告)日：2024-01-16

申请号：US17126765

申请日：2020-12-18

Applicant: International Business Machines Corporation

Inventor： Marcio Ferreira Moreno ,  Rafael Rossi de Mello Brandao ,  Guilherme Augusto Ferreira Lima

IPC: G06F16/732 ,  G06F16/9535 ,  G06F16/901 ,  G06V10/46 ,  G06F16/783 ,  G06V10/764 ,  G06F16/71 ,  G06V10/70 ,  G06F16/483

CPC classification number: G06V10/464 ,  G06F16/483 ,  G06F16/71 ,  G06F16/7328 ,  G06F16/783 ,  G06F16/9027 ,  G06F16/9535 ,  G06V10/70 ,  G06V10/764

Abstract: One or more processor can automatically identify, structure and retrieve spatial and/or temporal sequences of digital media content according to semantic specification. Digital media content can be received and information from digital media content can be extracted. Based on the information, a knowledge graph can be constructed or structured to include at least one of spatial and temporal representation of the digital media content. A search query can be received associated with the digital media content. Based on traversing the knowledge graph structure according to at least one of spatial and temporal criterion mapped from the search query, new digital media content can be composed which meets the search query.

公开(公告)号：US20220198211A1

公开(公告)日：2022-06-23

申请号：US17126765

申请日：2020-12-18

Applicant: International Business Machines Corporation

Inventor： Marcio Ferreira Moreno ,  Rafael Rossi de Mello Brandao ,  Guilherme Augusto Ferreira Lima

IPC: G06K9/46 ,  G06F16/901 ,  G06F16/9535 ,  G06F16/732

Abstract: One or more processor can automatically identify, structure and retrieve spatial and/or temporal sequences of digital media content according to semantic specification. Digital media content can be received and information from digital media content can be extracted. Based on the information, a knowledge graph can be constructed or structured to include at least one of spatial and temporal representation of the digital media content. A search query can be received associated with the digital media content. Based on traversing the knowledge graph structure according to at least one of spatial and temporal criterion mapped from the search query, new digital media content can be composed which meets the search query.

公开(公告)号：US12086145B2

公开(公告)日：2024-09-10

申请号：US17374322

申请日：2021-07-13

Applicant: International Business Machines Corporation

Inventor： Marcio Ferreira Moreno ,  Guilherme Augusto Ferreira Lima ,  Rafael Rossi de Mello Brandao

IPC: G06F16/2457 ,  G06F16/25 ,  G06F16/901 ,  G06N20/00

CPC classification number: G06F16/24575 ,  G06F16/24578 ,  G06F16/258 ,  G06F16/9024 ,  G06N20/00

Abstract: Automatically mapping and combining the application of machine learning models to answer queries according to semantic specification. A query is parsed to extract keywords from the query and to contextualize the query. Based on the keywords, machine learning models are selected that process concepts associated with the keywords. The machine learning models are sorted according to the contextualization of the query. The machine learning models are run on multimodal data according to a sorted order, where data resulting from an output of one of the machine learning models is used as input to another one of the machine learning models. A query result is output based on a result from running the machine learning models.

公开(公告)号：US12045270B2

公开(公告)日：2024-07-23

申请号：US17383789

申请日：2021-07-23

Applicant: International Business Machines Corporation

Inventor： Guilherme Augusto Ferreira Lima ,  Rafael Rossi de Mello Brandao ,  Marcio Ferreira Moreno

IPC: G06F40/30 ,  G06F16/33 ,  G06F40/295 ,  G06F40/40 ,  G06N5/02

CPC classification number: G06F16/3344 ,  G06F40/295 ,  G06F40/30 ,  G06F40/40 ,  G06N5/02

Abstract: Entities and temporal information associated with the entities can be extracted from the documents using natural language processing. A graph structure can be created representing the document's temporal semantics, nodes of the graph structure including the entities and edges of the graph structure representing temporal relationships between the nodes. The graph structure can be linked with the document. Multiple documents can be received and a knowledgebase can be created including multiple graph structures representing the multiple documents according to the multiple documents' temporal semantics. An input document for query can be received and transformed into a graph structure for query, the graph structure for query representing the input document's temporal semantics. The knowledgebase can be searched for a matching document having a graph structure similar to the graph structure for query based on a similarity threshold. The matching document can be output.

公开(公告)号：US12019627B2

公开(公告)日：2024-06-25

申请号：US17367605

申请日：2021-07-05

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Marcio Ferreira Moreno ,  Isabela Drabik Chaves Chambers Ramos ,  Rafael Rossi de Mello Brandao ,  Guilherme Augusto Ferreira Lima

IPC: G06F16/00 ,  G06F16/242 ,  G06F16/248

CPC classification number: G06F16/243 ,  G06F16/248

Abstract: A computer-implemented method of performing an incremental specification of a query includes extracting text from each of a plurality of participants in a dialog. A contextual information is determined of the extracted text of one or more of the plurality of participants. A dialog understanding operation is performed by processing at least the contextual information of the extracted text in a knowledge graph to identify in the dialog at least one or more of a structural gap, an information about entities, relationships, and actions. Query information is provided responsive to the dialog for at least one of filling the identified structural gap, or for providing additional information about one or more of the identified entities, relationships or actions in the dialog.

公开(公告)号：US20230033211A1

公开(公告)日：2023-02-02

申请号：US17383789

申请日：2021-07-23

Applicant: International Business Machines Corporation

Inventor： Guilherme Augusto Ferreira Lima ,  Rafael Rossi de Mello Brandao ,  Marcio Ferreira Moreno

IPC: G06F16/33 ,  G06N5/02 ,  G06F40/295 ,  G06F40/30 ,  G06F40/40

Abstract: Entities and temporal information associated with the entities can be extracted from the documents using natural language processing. A graph structure can be created representing the document's temporal semantics, nodes of the graph structure including the entities and edges of the graph structure representing temporal relationships between the nodes. The graph structure can be linked with the document. Multiple documents can be received and a knowledgebase can be created including multiple graph structures representing the multiple documents according to the multiple documents' temporal semantics. An input document for query can be received and transformed into a graph structure for query, the graph structure for query representing the input document's temporal semantics. The knowledgebase can be searched for a matching document having a graph structure similar to the graph structure for query based on a similarity threshold. The matching document can be output.

公开(公告)号：US20230016157A1

公开(公告)日：2023-01-19

申请号：US17374322

申请日：2021-07-13

Applicant: International Business Machines Corporation

Inventor： Marcio Ferreira Moreno ,  Guilherme Augusto Ferreira Lima ,  Rafael Rossi de Mello Brandao

IPC: G06F16/2457 ,  G06F16/25 ,  G06F16/901

Abstract: Automatically mapping and combining the application of machine learning models to answer queries according to semantic specification. A query is parsed to extract keywords from the query and to contextualize the query. Based on the keywords, machine learning models are selected that process concepts associated with the keywords. The machine learning models are sorted according to the contextualization of the query. The machine learning models are run on multimodal data according to a sorted order, where data resulting from an output of one of the machine learning models is used as input to another one of the machine learning models. A query result is output based on a result from running the machine learning models.

公开(公告)号：US20230004792A1

公开(公告)日：2023-01-05

申请号：US17367598

申请日：2021-07-05

Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

Inventor： Rafael Rossi de Mello Brandao ,  Marcio Ferreira Moreno ,  Guilherme Augusto Ferreira Lima ,  Renato Fontoura de Gusmao Cerqueira

IPC: G06N3/08 ,  G06N3/04 ,  G06N5/02

Abstract: A method and system of creating a knowledge graph includes capturing information of a user interacting with given data, as user interaction data. The user interaction data is structured as a trail of actions over time. An ontology for a domain related to the user interaction data is received. Each action of the trail of actions is matched onto entities of the ontology. The knowledge graph is created based on the ontology having the matched actions.