公开(公告)号：US20240412006A1

公开(公告)日：2024-12-12

申请号：US18522773

申请日：2023-11-29

Applicant: FEEDZAI - CONSULTADORIA E INOVAÇÃO TECNOLÓGICA, S.A.

Inventor： RITA MARQUES COSTA ,  DIOGO RAMALHO DUARTE ,  PEDRO GUSTAVO SANTOS RODRIGUES BIZARRO

IPC: G06F40/40 ,  G06T11/60

Abstract: The present document discloses a computer-implemented method for generating textual descriptions for a data chart, comprising the steps of: composing a text prompt comprising a textual instruction to generate a chart description, a data series description, and data from the data chart converted to text format; sending the composed text prompt to a generative pretrained language model, which in particular implementations comprises a generative pre-trained transformer (GPT) language model; receiving from the language model a generated textual description; wherein the data from the data chart comprises an array or arrays of pairwise keys, and corresponding value datapoints. Also disclosed herein is a respective system and a non-transitory storage media including program instructions for enhancing navigability on a graphical user interface.

公开(公告)号：US20240193489A1

公开(公告)日：2024-06-13

申请号：US18538354

申请日：2023-12-13

Applicant: FEEDZAI - CONSULTADORIA E INOVAÇÃO TECNOLÓGICA, S.A.

Inventor： Diogo MOREIRA DA SILVA EIRA LEITÃO ,  PEDRO DOS SANTOS SALEIRO ,  PEDRO GUSTAVO SANTOS RODRIGUES BIZARRO

IPC: G06N20/20

CPC classification number: G06N20/20

Abstract: A computer-implemented machine-learning training method and system are provided. Training instance(s) can be input to a first machine-learning model and, in response, for each instance, classification prediction output(s) and error prediction output(s) received, which can include an output representing one or more of a false-negative, a false-positive, a true-negative, and a true-positive. The instance(s), classification prediction output(s), and identifier(s) are input to a second machine-learning model and, in response, a predicted error output that includes one or more of a predicting false-negative, a false-positive, a true-negative, and a true-positive. The training instance(s) are assigned to the constraint-unlimited machine-learning classifier or the one or more constraint-limited classifiers, thereby minimizing the composite loss function.

公开(公告)号：US20230394318A1

公开(公告)日：2023-12-07

申请号：US17891981

申请日：2022-08-19

Applicant: Feedzai - Consultadoria e Inovação Tecnológica, S.A

Inventor： Mário João Cabral Cardoso ,  Pedro dos Santos Saleiro ,  Pedro Gustavo Santos Rodrigues Bizarro

IPC: G06N3/0895 ,  G06N3/048 ,  G06N3/045

CPC classification number: G06N3/0895 ,  G06N3/048 ,  G06N3/045

Abstract: In various embodiments, a process for providing a self-supervised framework for graph representation learning includes receiving entity data for a plurality of entities and receiving transaction data for transactions between corresponding entities included in the plurality of entities. The process includes generating a heterogeneous graph representation. Nodes of the heterogeneous graph representation includes a first type of node representing an entity of the plurality of entities and a second type of node representing the transactions. The process includes performing a self-supervised training of a graph neural network including by sampling the heterogeneous graph representation for positive samples and negative samples to learn embedding representations for the nodes of the heterogeneous graph representation, and utilizing the learned embedding representations for the nodes of the heterogeneous graph representation for automatic transaction analysis.

公开(公告)号：US11636487B2

公开(公告)日：2023-04-25

申请号：US17070814

申请日：2020-10-14

Applicant: Feedzai—Consultadoria e Inovação Tecnológica, S.A.

Inventor： Maria Inês Silva ,  David Oliveira Aparício ,  Pedro Gustavo Santos Rodrigues Bizarro ,  João Tiago Barriga Negra Ascensão ,  Rodolfo Cristóvão ,  Miguel Ramos de Araújo ,  Maria Beatriz Malveiro Jorge ,  Mariana Rodrigues Lourenço ,  Sandro Daniel Sabudin Nunes

IPC: G06Q20/40 ,  G06F9/54 ,  G06F16/901

Abstract: In an embodiment, a process for graph decomposition includes initializing nodes and edges of a data graph for analysis using a computer, and performing message passing between at least a portion of the nodes of the data graph to determine a corresponding measure of interest for each node of at least a portion of the data graph. The process further includes receiving an identification of one or more nodes of interest in the data graph, performing message passing between at least a portion of the nodes of the data graph using at least the determined measures of interest to identify a corresponding subgraph of interest for each of the one or more nodes of interest in the data graph, and performing an analysis action using the one or more identified subgraphs of interest.

公开(公告)号：US20220114494A1

公开(公告)日：2022-04-14

申请号：US17500310

申请日：2021-10-13

Applicant: Feedzai - Consultadoria e Inovação Tecnológica, S.A.

Inventor： João Pedro Bento Sousa ,  Pedro dos Santos Saleiro ,  André Miguel Ferreira da Cruz ,  Pedro Gustavo Santos Rodrigues Bizarro

IPC: G06N20/00

Abstract: A series of sequential inputs and a prediction output of a machine learning model, to be analyzed for interpreting the prediction output, are received. An input included in the series of sequential inputs is selected to be analyzed for relevance in producing the prediction output. Background data for the selected input of the series of sequential inputs to be analyzed is determined. The background data is used as a replacement for the selected input of the series of sequential inputs to determine a plurality of perturbed prediction outputs of the machine learning model. A relevance metric is determined for the selected input based at least in part on the plurality of perturbed prediction outputs of the machine learning model.

公开(公告)号：US12001800B2

公开(公告)日：2024-06-04

申请号：US16567761

申请日：2019-09-11

Applicant: Feedzai—Consultadoria e Inovação Tecnológica, S.A.

Inventor： Paulo César Gonçalves Marques ,  Miguel Ramos de Araújo ,  Bruno Casal Laraña ,  Nuno Miguel Lourenço Diegues ,  Pedro Cardoso Lessa e Silva ,  Pedro Gustavo Santos Rodrigues Bizarro

IPC: G06Q20/40 ,  G06F17/18 ,  G06F18/214 ,  G06F40/30 ,  G06N20/00 ,  H04L9/40

CPC classification number: G06F40/30 ,  G06F17/18 ,  G06F18/2155 ,  G06N20/00 ,  G06Q20/4016

Abstract: In an embodiment, a process for semantic-aware feature engineering includes receiving semantic labels for data fields of training data. Each of the semantic labels is associated with a semantic meaning associated with a corresponding data field. The process includes automatically generating at least one new feature using at least a portion of the semantic labels.

公开(公告)号：US11989643B2

公开(公告)日：2024-05-21

申请号：US17174046

申请日：2021-02-11

Applicant: Feedzai—Consultadoria e Inovação Tecnológica, S.A.

Inventor： Bernardo José Amaral Nunes de Almeida Branco ,  Pedro Caldeira Abreu ,  Ana Sofia Leal Gomes ,  Mariana S. C. Almeida ,  João Tiago Barriga Negra Ascensão ,  Pedro Gustavo Santos Rodrigues Bizarro

IPC: G06Q40/12 ,  G06F7/08 ,  G06F16/23 ,  G06F16/27 ,  G06N3/042 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063 ,  G06N3/08 ,  G06Q20/40

CPC classification number: G06N3/045 ,  G06F7/08 ,  G06F16/2379 ,  G06F16/27 ,  G06N3/042 ,  G06N3/044 ,  G06N3/063 ,  G06N3/08 ,  G06Q20/4016 ,  G06Q20/409 ,  G06Q40/12

Abstract: A process for handling interleaved sequences using RNNs includes receiving data of a first transaction, retrieving a first state (e.g., a default or a saved RNN state for an entity associated with the first transaction), and determining a new second state and a prediction result using the first state and an input data based on the first transaction. The process includes updating the saved RNN state for the entity to be the second state. The process includes receiving data of a second transaction, where the second transaction is associated with the same entity as the first transaction. The process unloops an RNN associated with the saved RNN state including by: retrieving the second state, determining a new third state and a prediction result using the second state and an input data based the second transaction, and updating the saved RNN state for the entity to be the third state.

公开(公告)号：US20220114595A1

公开(公告)日：2022-04-14

申请号：US17461198

申请日：2021-08-30

Applicant: Feedzai - Consultadoria e Inovação Tecnológica, S.A.

Inventor： Vladimir Balayan ,  Pedro dos Santos Saleiro ,  Catarina Garcia Belém ,  Pedro Gustavo Santos Rodrigues Bizarro

IPC: G06Q20/40 ,  G06N3/08 ,  G06N3/04

Abstract: A multi-task hierarchical machine learning model is configured to perform both a decision task to predict a decision result and an explanation task to predict a plurality of semantic concepts for explainability associated with the decision task, wherein a semantic layer of the machine learning model associated with the explanation task is utilized as an input to a subsequent decision layer of the machine learning model associated with the decision task. Training data is received. The multi-task hierarchical machine learning model is trained using the received training data.

公开(公告)号：US20220114345A1

公开(公告)日：2022-04-14

申请号：US17461217

申请日：2021-08-30

Applicant: Feedzai - Consultadoria e Inovação Tecnológica, S.A.

Inventor： Catarina Garcia Belém ,  Vladimir Balayan ,  Pedro dos Santos Saleiro ,  Pedro Gustavo Santos Rodrigues Bizarro

IPC: G06F40/30 ,  G06N3/08 ,  G06N3/04 ,  G06F40/169 ,  G06Q40/02 ,  G06Q20/40

Abstract: A labeling function associated with generating one or more semantic concepts is received. The received labeling function is used to automatically annotate an existing dataset with the one or more semantic concepts to generate an annotated noisy dataset. A reference dataset annotated with the one or more semantic concepts is received. A training dataset is prepared including by combining at least a portion of the reference dataset with at least a portion of the annotated noisy dataset. The training dataset is used to train a multi-task machine learning model configured to perform both a decision task to predict a decision result and an explanation task to predict a plurality of semantic concepts for explainability associated with the decision task.

公开(公告)号：US11269684B1

公开(公告)日：2022-03-08

申请号：US17356310

申请日：2021-06-23

Applicant: Feedzai-Consultadoria e Inovação Tecnológica, S.A.

Inventor： João Miguel Forte Oliveirinha ,  Ana Sofia Leal Gomes ,  Pedro Cardoso Lessa e Silva ,  Pedro Gustavo Santos Rodrigues Bizarro

IPC: G06F9/54 ,  G06F9/48 ,  G06F9/50 ,  G06F11/30 ,  G06F16/21

Abstract: In various embodiments, a process for providing a distributed streaming system supporting real-time sliding windows includes receiving a stream of events at a plurality of distributed nodes and routing the events into topic groupings. The process includes using one or more events in at least one of the topic groupings to determine one or more metrics of events with at least one window and an event reservoir including by: tracking, in a volatile memory of the event reservoir, beginning and ending events within the at least one window; and tracking, in a persistent storage of the event reservoir, all events associated with tasks assigned to a respective node. The process includes updating the one or more metrics based on one or more previous values of the one or more metrics as a new event is added or an existing event is expired from the at least one window.