知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

35 records (took 0.024 seconds)

    Efficient server-client machine learning solution for rich content transformation
    21.
    发明授权
    Efficient server-client machine learning solution for rich content transformation 有权

    公开(公告)号：US11810267B2

    公开(公告)日：2023-11-07

    申请号：US17240396

    申请日：2021-04-26

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

    Inventor： Ji Li ,  Huan Yang ,  Jianlong Fu

    IPC: G06T3/40 ,  G06N20/00

    CPC classification number: G06T3/4046 ,  G06N20/00 ,  G06T3/4084

    Abstract: A system and method for rich content transformation are provided. The system and method allow rich content transformation to be separately processed on a client device and on a cloud-based server. The client device downsizes a rich content and transmits the downsized rich content to the cloud-based server via a network. The cloud-based server calculates function parameters based on the downsized rich content using one or more machine learning models included in the server. The calculated function parameters are transmitted to the client device via the network. The client device then applies these function parameters to the rich content on the client device to obtain the transformed rich content.

    Automatic reaction-triggering for live presentations
    23.
    发明授权
    Automatic reaction-triggering for live presentations 有权

    公开(公告)号：US11570307B2

    公开(公告)日：2023-01-31

    申请号：US16983649

    申请日：2020-08-03

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Ji Li ,  Amit Srivastava ,  Derek Martin Johnson ,  Priyanka Vikram Sinha ,  Konstantin Seleskerov ,  Gencheng Wu

    IPC: H04M3/56 ,  G06N3/08 ,  H04L12/18 ,  H04L65/401 ,  H04L65/403

    Abstract: The present disclosure relates to processing operations configured to provide processing that automatically analyzes acoustic signals from attendees of a live presentation and automatically triggers corresponding reaction indications from results of analysis thereof. Exemplary reaction indications provide feedback for live presentations that can be presented in real-time (or near real-time) without requiring a user to manually take action to provide any feedback. As a non-limiting example, reaction indications may be presented in a form that is easy to visualize and understand such as emojis or icons. Another example of a reaction indication is a graphical user interface (GUI) notification that provides a predictive indication of user intent derived from analysis of acoustic signals. Further examples described herein extend to training and application of artificial intelligence (AI) processing, in real-time (or near real-time), that is configured to automatically analyze acoustic features of audio streams and automatically generate exemplary reaction indications.

    Automated intelligent content generation
    25.
    发明授权
    Automated intelligent content generation 有权

    公开(公告)号：US11494396B2

    公开(公告)日：2022-11-08

    申请号：US17152193

    申请日：2021-01-19

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Ji Li ,  Amit Srivastava ,  Muin Barkatali Momin ,  Muqi Li ,  Emily Lauren Tohir ,  SivaPriya Kalyanaraman ,  Derek Martin Johnson

    IPC: G06F16/248 ,  G06F16/242 ,  G06F16/93 ,  G06F16/2457 ,  G06N3/02

    Abstract: Automatic generation of intelligent content is created using a system of computers including a user device and a cloud-based component that processes the user information. The system performs a process that includes receiving a user query for creating content in a content generation application and determining an action from an intent of the user query. A prompt is generated based on the action and provided to a natural language generation model. In response to the prompt, output is received from the natural language generation model. Response content is generated based on the output in a format compatible with the content generation application. At least some of the response content is displayed to the user. The user can choose to keep, edit, or discard the response content. The user can iterate with additional queries until the content document reflects the user's desired content.

    AUTOMATIC REACTION-TRIGGERING FOR LIVE PRESENTATIONS
    26.
    发明申请
    AUTOMATIC REACTION-TRIGGERING FOR LIVE PRESENTATIONS 有权

    公开(公告)号：US20220038580A1

    公开(公告)日：2022-02-03

    申请号：US16983649

    申请日：2020-08-03

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Ji Li ,  Amit Srivastava ,  Derek Martin Johnson ,  Priyanka Vikram Sinha ,  Konstantin Seleskerov ,  Gencheng Wu

    IPC: H04M3/56 ,  H04L12/18 ,  H04L29/06 ,  G06N3/08

    Abstract: The present disclosure relates to processing operations configured to provide processing that automatically analyzes acoustic signals from attendees of a live presentation and automatically triggers corresponding reaction indications from results of analysis thereof. Exemplary reaction indications provide feedback for live presentations that can be presented in real-time (or near real-time) without requiring a user to manually take action to provide any feedback. As a non-limiting example, reaction indications may be presented in a form that is easy to visualize and understand such as emojis or icons. Another example of a reaction indication is a graphical user interface (GUI) notification that provides a predictive indication of user intent derived from analysis of acoustic signals. Further examples described herein extend to training and application of artificial intelligence (AI) processing, in real-time (or near real-time), that is configured to automatically analyze acoustic features of audio streams and automatically generate exemplary reaction indications.

    Multilingual model training using parallel corpora, crowdsourcing, and accurate monolingual models
    27.
    发明授权
    Multilingual model training using parallel corpora, crowdsourcing, and accurate monolingual models 有权

    公开(公告)号：US12236205B2

    公开(公告)日：2025-02-25

    申请号：US17131624

    申请日：2020-12-22

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Ji Li ,  Amit Srivastava

    IPC: G06F40/58 ,  G06F40/169 ,  G06F40/279 ,  G06F40/30 ,  G06F40/45 ,  G06N3/08 ,  G06N20/00

    Abstract: A data processing system for generating training data for a multilingual NLP model implements obtaining a corpus including first and second content items. The first content items are English-language textual content, and the second content items are translations of the first content items in one or more non-English target languages. The system further implements selecting a first content item from the first content items, generating a plurality of candidate labels for the first content item by analyzing the first content item with a plurality of first English-language NLP models, selecting a first label from the plurality of candidate labels, generating first training data by associating the first label with the first content item, generating second training data by associating the first label with a second content item of the second content items, and training a pretrained multilingual NLP model with the first training data and the second training data.

    Multilingual content recommendation pipeline
    28.
    发明授权
    Multilingual content recommendation pipeline 有权

    公开(公告)号：US12124812B2

    公开(公告)日：2024-10-22

    申请号：US17510850

    申请日：2021-10-26

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Ji Li ,  Amit Srivastava ,  Xingxing Zhang ,  Furu Wei

    IPC: G06F40/56 ,  G06F40/284 ,  G06F40/47

    CPC classification number: G06F40/56 ,  G06F40/284 ,  G06F40/47

    Abstract: A data processing system implements obtaining first textual content in a first language from a first client device; determining that the first language is supported by a first machine learning model; obtaining a guard list of prohibited terms associated with the first language; determining that the textual content does not include one or more prohibited terms associated based on the guard list; providing the first textual content as an input to the first machine learning model responsive to the textual content not including the one or more prohibited terms; analyzing the first textual content with the first machine learning model to obtain a first content recommendation; obtaining a first content recommendation policy that identifies content associated with the first language that may not be provided as a content recommendation; determining that the first content recommendation is not prohibited; and providing the first content recommendation to the first client device.

    Image classification modeling while maintaining data privacy compliance
    30.
    发明授权
    Image classification modeling while maintaining data privacy compliance 有权

    公开(公告)号：US12001514B2

    公开(公告)日：2024-06-04

    申请号：US18047324

    申请日：2022-10-18

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Ji Li ,  Youjun Liu ,  Amit Srivastava

    IPC: G06F18/21 ,  G06F18/25 ,  G06F21/62 ,  G06N20/00

    CPC classification number: G06F18/217 ,  G06F18/254 ,  G06F21/6218 ,  G06N20/00

    Abstract: The present disclosure relates to processing operations that execute image classification training for domain-specific traffic, where training operations are entirely compliant with data privacy regulations and policies. Image classification model training, as described herein, is configured to classify meaningful image categories in domain-specific scenarios where there is unknown data traffic and strict data compliance requirements that result in privacy-limited image data sets. Iterative image classification training satisfies data compliance requirements through a combination of online image classification training and offline image classification training. This results in tuned image recognition classifiers that have improved accuracy and efficiency over general image recognition classifiers when working with domain-specific data traffic. One or more image recognition classifiers are independently trained and tuned to detect an image class for image classification. Training of independent image recognition classifiers is also utilized for training and tuning of deeper learning models for image classification.

Patent Agency Ranking