公开(公告)号：US20230205938A1

公开(公告)日：2023-06-29

申请号：US17998719

申请日：2021-12-08

Applicant: Google LLC

Inventor： Ondrej Stava

IPC: G06F30/10

CPC classification number: G06F30/10

Abstract: Systems and methods provide micro-credential accreditation. The systems and methods analyze, using one or more prediction models, received text submissions received from applicants via interaction with an applicant device. The prediction model(s) fit one or more micro-credentials to the received text submission, which may collectively or independently qualify the applicant for one or more accreditation credits. By processing the received text submission, the systems and methods allow for consistent and standard output of micro-credentials by the prediction model(s). Furthermore, the systems and methods provide for monitoring the prediction model output(s) to ensure ethical fairness across varying demographic groups of applicants.

公开(公告)号：US20230214953A1

公开(公告)日：2023-07-06

申请号：US18008285

申请日：2020-06-05

Applicant: Google LLC

Inventor： Innfarn Yoo ,  Xiyang Luo ,  Feng Yang ,  Ondrej Stava

IPC: G06T1/00 ,  G09C5/00

CPC classification number: G06T1/0028 ,  G09C5/00 ,  G06T2201/0065

Abstract: Systems and methods are directed to a computing system. The computing system can include one or more processors, a message embedding model, a message extraction model, and a first set of instructions that cause the computing system to perform operations including obtaining the three-dimensional image data and the message vector. The operations can include inputting three-dimensional image data and a message vector into the message embedding model to obtain encoded three-dimensional image data. The operations can include using the message extraction model to extract an embedded message from the encoded three-dimensional image data to obtain a reconstructed message vector. The operations can include evaluating a loss function for a difference between the reconstructed message vector and the message vector and modifying values for parameters of at least the message embedding model based on the loss function.

公开(公告)号：US20220020211A1

公开(公告)日：2022-01-20

申请号：US17309371

申请日：2019-12-05

Applicant: Google LLC

Inventor： Igor Vytyaz ,  Ondrej Stava ,  Michael Hemmer ,  Xiaoxu Meng

IPC: G06T17/20 ,  G06T9/00

Abstract: Techniques of compressing triangular mesh data involve generating a neighborhood table (i.e., a table) of fixed size that represents a neighborhood of a predicted vertex of a triangle within a triangular mesh for input into a machine-learning (ML) engine. For example, such a neighborhood table as input into a ML engine can output a prediction for a value (e.g., a position) of a vertex. The residual between the prediction and the actual value of the vertex is stored in an array. The data in the array representing the residuals may be compressed and transmitted over a network. Upon receipt by a computer, the array may be decompressed by the computer. Obtaining the actual value involves the receiving computer generating the same neighborhood table, inputting that neighborhood table into the same ML engine to produce the predicted value, and adding the predicted value to the residual from the decompressed file.

公开(公告)号：US11631218B2

公开(公告)日：2023-04-18

申请号：US17309371

申请日：2019-12-05

Applicant: Google LLC

Inventor： Igor Vytyaz ,  Ondrej Stava ,  Michael Hemmer ,  Xiaoxu Meng

IPC: G06T17/20 ,  G06T9/00

Abstract: Techniques of compressing triangular mesh data involve generating a neighborhood table (i.e., a table) of fixed size that represents a neighborhood of a predicted vertex of a triangle within a triangular mesh for input into a machine-learning (ML) engine. For example, such a neighborhood table as input into a ML engine can output a prediction for a value (e.g., a position) of a vertex. The residual between the prediction and the actual value of the vertex is stored in an array. The data in the array representing the residuals may be compressed and transmitted over a network. Upon receipt by a computer, the array may be decompressed by the computer. Obtaining the actual value involves the receiving computer generating the same neighborhood table, inputting that neighborhood table into the same ML engine to produce the predicted value, and adding the predicted value to the residual from the decompressed file.