公开(公告)号：US11899733B2

公开(公告)日：2024-02-13

申请号：US17792965

申请日：2020-01-14

Applicant: Google LLC

Inventor： Michael Shalai ,  Joseph Catalano ,  Bo Lin ,  Dustin Zelle ,  Rami Al-Rfou

IPC: G06F7/00 ,  G06F16/957

CPC classification number: G06F16/9574

Abstract: A solution arranged to build or train a machine learning model (ML model) that can be uploaded to a server arranged to deploy the ML model to communicating devices. The ML model builder can build the ML model and a ML production pipeline. The ML production pipeline can train the ML model, convert the ML model to a web browser compatible format, and upload the converted ML model to the server. The ML model can receive as input a sequence of prior activities on one communicating device in the communicating devices, analyze the sequence of prior activities on the communicating device, predict a next activity on the communicating device based on the analysis of the sequence of prior activities, preemptively search a computer network based on the predicted next activity to find a computer asset, and preload the found computer asset to a storage in the communicating device.

公开(公告)号：US20230325725A1

公开(公告)日：2023-10-12

申请号：US17718738

申请日：2022-04-12

Applicant: Google LLC

Inventor： Brian David Lester ,  Rami Al-Rfou ,  Noah Constant

IPC: G06N20/20 ,  G06V10/764 ,  G06V10/774

CPC classification number: G06N20/20 ,  G06V10/764 ,  G06V10/7747

Abstract: Systems and methods for natural language processing can leverage trained prompts to condition a large pre-trained machine-learned model to generate an output for a specific task. For example, a subset of parameters may be trained for the particular task to then be input with a set of input data into the pre-trained machine-learned model to generate the task-specific output. During the training of the prompt, the parameters of the pre-trained machine-learned model can be frozen, which can reduce the computational resources used during training while still leveraging the previously learned data from the pre-trained machine-learned model.

公开(公告)号：US11809993B2

公开(公告)日：2023-11-07

申请号：US16850570

申请日：2020-04-16

Applicant: Google LLC

Inventor： Rami Al-Rfou ,  Dustin Zelle ,  Bryan Perozzi

IPC: G06N3/084 ,  G06N20/20 ,  G06N3/02 ,  G06F18/22 ,  G06N3/045 ,  G06V10/82

CPC classification number: G06N3/084 ,  G06F18/22 ,  G06N3/02 ,  G06N3/045 ,  G06N20/20 ,  G06V10/82

Abstract: The present disclosure provides computing systems and methods directed to algorithms and the underlying machine learning (ML) models for evaluating similarity between graphs using graph structures and/or attributes. The systems and methods disclosed may provide advantages or improvements for comparing graphs without additional context or input from a person (e.g., the methods are unsupervised). In particular, the systems and methods of the present disclosure can operate to generate respective embeddings for one or more target graphs, where the embedding for each target graph is indicative of a respective similarity of such target graph to each of a set of source graphs, and where a pair of embeddings for a pair of target graphs can be used to assess a similarity between the pair of target graphs.

公开(公告)号：US20230050882A1

公开(公告)日：2023-02-16

申请号：US17792965

申请日：2020-01-14

Applicant: Google LLC

Inventor： Mikhail Shalai ,  Joseph Catalano ,  Bo Lin ,  Dustin Zelle ,  Rami Al-Rfou

IPC: G06F16/957

Abstract: A solution arranged to build or train a machine learning model and to upload the machine learning model to a server arranged to deploy the machine learning model to a plurality of communicating devices. The solution can include a machine learning model builder arranged to build the machine learning model and a machine learning production pipeline. The machine learning production pipeline can be arranged to train the machine learning model, convert the machine learning model to a web browser compatible format, and upload the converted machine learning model to the server. The machine learning model can be arranged to receive as input a sequence of one or more prior activities on one communicating device in the plurality of communicating devices, analyze the sequence of one or more prior activities on said one communicating device, predict a next activity on said one communicating device based on the analysis of the sequence of one or more prior activities, preemptively search a computer network based on the predicted next activity to find a computer asset, and preload the found computer asset to a storage in said one communicating device.

公开(公告)号：US20240020546A1

公开(公告)日：2024-01-18

申请号：US17863840

申请日：2022-07-13

Applicant: Google LLC

Inventor： Tu Thanh Vu ,  Daniel Matthew Cer ,  Noah Constant ,  Brian David Lester ,  Rami Al-Rfou

IPC: G06N5/02

CPC classification number: G06N5/022

Abstract: Systems and methods for prompt tuning can utilize previously-learned prompts for the initialization of tuning for prompts on different tasks that may differ from the task associated with the previously-learned prompt. The prompt being utilized for initialization can be a generic prompt and/or may be a prompt selected based on a determined similarity between two or more task embeddings.

公开(公告)号：US20200334495A1

公开(公告)日：2020-10-22

申请号：US16850570

申请日：2020-04-16

Applicant: Google LLC

Inventor： Rami Al-Rfou ,  Dustin Zelle ,  Bryan Perozzi

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06N20/20

Abstract: The present disclosure provides computing systems and methods directed to algorithms and the underlying machine learning (ML) models for evaluating similarity between graphs using graph structures and/or attributes. The systems and methods disclosed may provide advantages or improvements for comparing graphs without additional context or input from a person (e.g., the methods are unsupervised). In particular, the systems and methods of the present disclosure can operate to generate respective embeddings for one or more target graphs, where the embedding for each target graph is indicative of a respective similarity of such target graph to each of a set of source graphs, and where a pair of embeddings for a pair of target graphs can be used to assess a similarity between the pair of target graphs.