公开(公告)号：US11495210B2

公开(公告)日：2022-11-08

申请号：US16710442

申请日：2019-12-11

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Ji Li ,  Amit Srivastava

IPC: G10L15/06 ,  G10L15/02 ,  G10L15/22 ,  G10L15/18 ,  G10L15/04 ,  G10L25/24 ,  G10L25/18 ,  G10L25/90 ,  G06N3/08 ,  G06N3/04

Abstract: A method and system for detecting one or more speech features in speech audio data includes receiving speech audio data, performing preprocessing on the speech audio data to prepare the speech audio data for use as an input into one or more models that detect one or more speech features, providing the preprocessed speech audio data to a stacked machine learning model, and analyzing the preprocessed speech audio data via the stacked ML model to detect the one or more speech features. The stacked ML model includes a feature aggregation model, a sequence to sequence model, and a decision-making model.

公开(公告)号：US11455466B2

公开(公告)日：2022-09-27

申请号：US16490440

申请日：2019-05-01

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

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

IPC: G06F40/274 ,  G06N20/00 ,  G06N3/08

Abstract: A method and system for providing an application-specific embedding for an entire text-to-content suggestions service is disclosed. The method includes accessing a dataset containing unlabeled training data collected from an application, the unlabeled training data being collected under user privacy constraints, applying an unsupervised ML model to the dataset to generate a pretrained embedding; and utilizing the pretrained embedding to train the text-to-content suggestion ML model utilized by the application.

公开(公告)号：US10891514B2

公开(公告)日：2021-01-12

申请号：US16222905

申请日：2018-12-17

Applicant: Microsoft Technology Licensing, LLC

Inventor： Youjun Liu ,  Ji Li ,  Amit Srivastava

IPC: G06K9/62 ,  G06K9/00 ,  G06N3/08

Abstract: The present disclosure relates to processing operations configured for an image recognition pipeline that is used to tailor real-time management of image recognition processing for technical scenarios across a plurality of different applications/services. Image recognition processing is optimized at run-time to ensure that latency requirements are met so that image recognition processing results are returned in a timely manner that aids task execution in an application-specific instances. An image recognition pipeline may manage a plurality of image recognition models that comprise a combination of image analysis service (IAS) models and deep learning models. A scheduler of the image recognition pipeline optimizes image recognition processing by selecting at least: a subset of the image recognition models for image recognition processing and a device configuration for execution of the subset of image recognition models, in order to return image recognition results within a threshold time period that satisfies application-specific execution.

公开(公告)号：US12242491B2

公开(公告)日：2025-03-04

申请号：US17716653

申请日：2022-04-08

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ji Li ,  Dachuan Zhang ,  Amit Srivastava ,  Adit Krishnan

IPC: G06F16/2457 ,  G06F16/22 ,  G06F18/214 ,  G06N20/00

Abstract: A system and method and for retrieving assets from a personalized asset library includes receiving a search query for searching for assets in one or more asset libraries, the one or more asset libraries including a personalized asset library; encoding the search query into embedding representations via a trained query representation machine-learning (ML) model; comparing, via a matching unit, the query embedding representations to a plurality of asset representations, each of the plurality of asset representations being a representation of one of the plurality of candidate assets; identifying, based on the comparison, at least one of the plurality of the candidate assets as a search result for the search query; and providing the identified plurality of candidate assets for display as the search result. The plurality of asset representations for the one or more assets in the personalized content library are generated automatically without human labeling.

公开(公告)号：US20230274096A1

公开(公告)日：2023-08-31

申请号：US17681250

申请日：2022-02-25

Applicant: Microsoft Technology Licensing, LLC

Inventor： Tapan BOHRA ,  Ji Li ,  Amit Srivastava

IPC: G06F40/49 ,  G06F40/284 ,  G06F40/242 ,  G06F40/253 ,  G06N20/00

CPC classification number: G06F40/49 ,  G06F40/284 ,  G06F40/242 ,  G06F40/253 ,  G06N20/00

Abstract: A data processing system implements obtaining textual content in a first language from a first client device and segmenting the textual content into a plurality of first tokens. The system also implements translating the first tokens from the first language to a second language using a bilingual dictionary, extracting features information from the second tokens to create a features vector, providing the feature vector to a first natural language processing model trained to analyze textual input in the second language and to output contextual information indicating one or more topics or subject matter of the first textual content, and providing the contextual information to a first machine learning model configured to analyze the contextual information and to identify one or more content items predicted to be relevant to the contextual information. The system further implements providing the information identifying the one or more content items to the first client device.

公开(公告)号：US11727270B2

公开(公告)日：2023-08-15

申请号：US16799091

申请日：2020-02-24

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

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

IPC: G06F40/40 ,  G06N3/08 ,  G06F40/205 ,  G06F18/214 ,  G10L15/16 ,  G10L15/18 ,  G06N3/088 ,  G06F40/30

CPC classification number: G06N3/08 ,  G06F18/2148 ,  G06F40/205 ,  G06F40/40 ,  G06F40/30 ,  G06N3/088 ,  G10L15/16 ,  G10L15/18

Abstract: A method and system for training a text-to-content recommendation ML model includes training a first ML model using a first training data set, utilizing the trained first ML model to infer information about the data contained in the first training data set, collecting the inferred information to generate a second training data set, and utilizing the first training data set and the second training data set to train a second ML model. The second ML model may be a text-to-content recommendation ML model.

公开(公告)号：US11657209B2

公开(公告)日：2023-05-23

申请号：US17232503

申请日：2021-04-16

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ji Li

IPC: G06F40/106 ,  G06N20/00 ,  G06F16/28 ,  G06F16/908 ,  G06F40/166 ,  G06F40/30

CPC classification number: G06F40/106 ,  G06F16/288 ,  G06F16/908 ,  G06F40/166 ,  G06F40/30 ,  G06N20/00

Abstract: For generating visual enhancement suggestions for source content, a system performs storing, in a data storage, a plurality of context data sets, each context data set including a set of visual enhancements and a context for selecting the set of visual enhancements; receiving the source content including source content data and source attribute data; providing, to an artificial intelligence (AI) engine, the received source content, the AI engine configured to select, based on the source content and the context data sets, a first set of visual enhancements and apply the selected first set of visual enhancements to the source content to generate a first visual enhancement suggestion for the source content; extracting, from the AI engine, the first visual enhancement suggestion; and causing the first visual enhancement suggestion to be displayed via a display of a user device.

公开(公告)号：US11429787B2

公开(公告)日：2022-08-30

申请号：US16490456

申请日：2019-05-01

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

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

IPC: G06F40/274 ,  G06N20/20 ,  G06F40/40

Abstract: Method and system for training a text-to-content suggestion ML model include accessing a dataset containing unlabeled training data collected from an application, the unlabeled training data being collected under user privacy constraints, applying an ML model to the dataset to generate a pretrained embedding, and applying a supervised ML model to a labeled dataset to train the text-to-content suggestion ML model utilized by the application by utilizing the pretrained embedding generated by the supervised ML model.

公开(公告)号：US20210064690A1

公开(公告)日：2021-03-04

申请号：US16552210

申请日：2019-08-27

Applicant: Microsoft Technology Licensing, LLC

Inventor： Ji Li ,  Xiaozhi Yu ,  Gregory Alexander DePaul ,  Youjun Liu ,  Amit Srivastava

IPC: G06F17/21 ,  G06N20/00

Abstract: A textual user input is received and a plurality of different text-to-content models are run on the textual user input. A selection system attempts to identify a suggested content item, based upon the outputs of the text-to-content models. The selection system first attempts to generate a completed suggestion based on outputs from a single text-to-content model. It then attempts to mix the outputs of the text-to-content models to obtain a completed content suggestion.

公开(公告)号：US20240248901A1

公开(公告)日：2024-07-25

申请号：US18158121

申请日：2023-01-23

Applicant: Microsoft Technology Licensing, LLC

Inventor： Adit KRISHNAN ,  Varun TANDON ,  Ji Li

IPC: G06F16/2457 ,  G06F16/2455 ,  G06F16/248

CPC classification number: G06F16/24578 ,  G06F16/24556 ,  G06F16/248

Abstract: A system for retrieving multimodal assets using domain-specific knowledge includes receiving a search query for searching for multimodal assets; encoding the search query into a first query representation via a first trained query representation machine-learning (ML) model and a second query representation via a second trained query representation ML model; comparing the first query representation to a plurality of multimodal representations to calculate a first similarity score, each of the plurality of multimodal representations being a representation of one of the plurality of candidate multimodal assets; comparing the second query representation to a plurality of domain-specific representations to calculate a second similarity score, the domain-specific representations being representations of domain-specific data associated with one or more of the plurality of the multimodal representations; calculating a third similarity score based on keyword matching between the domain-specific data and the one or more search terms in the search query; aggregating the first, second and third similarity scores to calculate a total similarity score for each of the plurality of candidate multimodal assets; ranking the plurality of candidate multimodal assets based on the total similarity scores to identify search results for the search query; and providing the identified candidate multimodal assets for display as the search results.