公开(公告)号：US20220398181A1

公开(公告)日：2022-12-15

申请号：US17347907

申请日：2021-06-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Richard FANG ,  Chang-Ling WU ,  Justin James WAGLE

IPC: G06F11/34 ,  G08B21/04 ,  G08B21/18 ,  G06N20/00

Abstract: The systems and methods may use machine learning models to process device data of user devices and determine device usage behaviors for the users of the user devices based on the device data. The systems and methods may provide relatable insights for the device usage behaviors in a user-friendly manner. The systems and methods may provide actional recommendations that users may take in response to the insights provided to promote healthy device usage behaviors or to prevent or reduce the device usage behavior. The systems and methods may also provide recommendations with access to information or other content related to the device usage behavior.

公开(公告)号：US20220277050A1

公开(公告)日：2022-09-01

申请号：US17188824

申请日：2021-03-01

Applicant: Microsoft Technology Licensing, LLC

Inventor： Justin James WAGLE ,  Alekhya NANDULA ,  Minah KIM

IPC: G06F16/951 ,  G06F16/953 ,  G06F40/289

Abstract: Systems and methods for identifying flagged content. One computer-based system includes an electronic processor configured to receive one or more websites, each website including a label identifying a flagged category and content, analyze one or more words included in the content of each of the one or more websites, and associate at least one of the one or more words included in the content of each of the one or more websites with the flagged category. The electronic processor is configured to perform, using the at least one of the one or more words, a query within a search engine to obtain one or more second websites, label each of the one or more second websites with the label identifying the flagged category, and update a model with the one or more websites, the one or more second websites, the one or more words, and the associated labels.

公开(公告)号：US20250110985A1

公开(公告)日：2025-04-03

申请号：US18478998

申请日：2023-09-30

Applicant: Microsoft Technology Licensing, LLC

Inventor： Justin James WAGLE ,  Rogerio BONATTI

IPC: G06F16/583 ,  G06F40/30 ,  G06V10/82

Abstract: Large language models (LLMs) are able to provide robust results based on specified formatting and organization. Traditionally, however, users must form detailed queries to obtain desired results in a desired format. Accordingly, although LLMs are designed to receive natural language input, users often lack the skill, knowledge, or patience to utilize LLMs to their full potential. Ambient information and user history associated with device screenshots are leveraged to provide proactive artificial-intelligence (AI) assistance and query resolution in an LLM environment. In particular, screenshots associated with a computer display are continuously captured and analyzed to detect activity triggers for plugins, for example. In response to detecting an activity trigger, local context associated with one or more prior screenshots is collected. The collected context is then used to inform the plugin for performing the task, thereby reducing the burden placed on the user to input the required information.

公开(公告)号：US20230420103A1

公开(公告)日：2023-12-28

申请号：US17850311

申请日：2022-06-27

Applicant: Microsoft Technology Licensing, LLC

Inventor： Rui ZHU ,  Alekhya NANDULA ,  Luke Nitish KUMAR ,  Justin James WAGLE

IPC: G16H20/30 ,  G06F9/451

CPC classification number: G16H20/30 ,  G06F9/451

Abstract: Systems, methods, and software are disclosed herein that provide a computer-based user experience that allows a user to consume information about physical and digital activities undertaken by one or more users. In an implementation, a software application on a computing device communicates with an online service to obtain activity information indicative of such activities, as well as activity topics produced by the service. The application groups the activities into activity groups based at least on the topics produced for the activities, and displays the activity groups in a user interface to the application.

公开(公告)号：US20250053748A1

公开(公告)日：2025-02-13

申请号：US18232485

申请日：2023-08-10

Applicant: Microsoft Technology Licensing, LLC

Inventor： Mohsen FAYYAZ ,  Eric Chris Wolfgang SOMMERLADE ,  Justin James WAGLE ,  Vivek PRADEEP

IPC: G06F40/35 ,  G06F40/284 ,  G06N20/00

Abstract: A technique uses a machine-trained model to generate a response based on a prompt which expresses current input information and abstract token information. The abstract token information summarizes a full dialogue history of a dialogue, and is generated by the model itself. The technique reduces the size of the prompt by incorporating the abstract summary information in lieu of the full dialogue history. A training system trains the machine-trained model by successively improving the predictive accuracy of the machine-trained model, while rewarding the machine-trained model based on an extent to which the machine-trained model compresses instances of abstract token information.

公开(公告)号：US20240354317A1

公开(公告)日：2024-10-24

申请号：US18137944

申请日：2023-04-21

Applicant: Microsoft Technology Licensing, LLC

Inventor： Mohsen FAYYAZ ,  Eric Chris Wolfgang SOMMERLADE ,  Justin James WAGLE

IPC: G06F16/31 ,  G06F16/33

CPC classification number: G06F16/313 ,  G06F16/3344 ,  G06F16/3347

Abstract: A technique uses an encoder system to produce an index of target item embeddings. Each target item embedding is input-agnostic and universal in the sense that different expressions of a target concept, produced using different combinations of input modes, map to the same target item embedding in the index. The encoder system throttles the amount of computations it performs based on the assessed capabilities of an execution platform. A retrieval system processes a multimodal input query by first generating a candidate set of target item embeddings in the index that match the input query, and then using a filtering operation to identify those target item embeddings that are most likely to match the input query. The encoder system and the retrieval system rely on language-based components having weights that are held constant during a training operation. Other weights of these systems are updated during the training operation.