-
公开(公告)号：US12229669B2
公开(公告)日：2025-02-18
申请号：US17340607
申请日：2021-06-07
Applicant: Microsoft Technology Licensing, LLC
Inventor： Shuai Wang , Peide Zhong , Ji Yan , Feng Guo , Dan Shacham , Fei Chen
IPC: G06N3/08 , G06F16/334 , G06F18/2113 , G06F18/214 , G06F18/2413 , G06N3/04 , G06Q10/1053
Abstract: Described herein is a technique for mapping the raw text of a job title of an online job posting to an entity embedding, associated with an entity or entry of a title taxonomy. The raw text of the job title is first encoded to generate a multilingual word embedding in a multilingual word embedding space. Then, the vector representation of the job title, as represented in the multilingual word embedding space is translated, using a neural network, to a vector representation of the job title in the entity embedding space. Finally, a nearest neighbor search is performed to identify an entity embedding associated with an entity or entry in the title taxonomy that has a vector representation that is closest in distance to the vector output by the neural network.
-
公开(公告)号：US11710070B2
公开(公告)日：2023-07-25
申请号：US16853442
申请日：2020-04-20
Applicant: Microsoft Technology Licensing, LLC
Inventor： Baoxu Shi , Shan Li , Jaewon Yang , Mustafa Emre Kazdagli , Feng Guo , Fei Chen , Qi He
CPC classification number: G06N20/00 , G06N3/08 , G06N5/04 , G06Q10/1053
Abstract: In an example embodiment, a screening question-based online screening mechanism is provided to assess job applicants automatically. More specifically, job-specific questions are automatically generated and asked to applicants to assess the applicants using the answers they provide. Answers to these questions are more recent than facts contained in a user profile and thus are more reliable measures of an appropriateness of an applicant's skills for a particular job.
-
公开(公告)号：US11487947B2
公开(公告)日：2022-11-01
申请号：US16716402
申请日：2019-12-16
Applicant: Microsoft Technology Licensing, LLC
IPC: G06F17/00 , G06F40/30 , G06F16/93 , G06F40/289 , G06F40/284 , G06N20/00
Abstract: Techniques are provided for using machine learning techniques to analyze textual content. In one technique, a potential item is identified within a document. An analysis of the potential item is performed at multiple levels of granularity that includes two or more of a sentence level, a segment level, or a document level. The analysis produces multiple outputs, one for each level of granularity in the multiple levels of granularity. The outputs are input into a machine-learned model to generate a score for the potential item. Based on the score, the potential item is presented on a computing device. In response to user selection of the potential item, an association between the potential item and the document is created. The association may be used later to identify a set of users to which the document (or data thereof) is to be presented.
-
公开(公告)号：US11233980B2
公开(公告)日：2022-01-25
申请号：US16440597
申请日：2019-06-13
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： Raymond Kirk Price , Yarn Chee Poon , Fei Chen
Abstract: Techniques for improving laser image quality are disclosed herein. An ultra-compact illumination module includes multiple illuminators, photodetectors, and color filters. The illuminators each emit a different spectrum of light. Because of the compact nature of the module and the positioning of the illuminators relative to one another, the different spectrums of light overlap one another prior to being detected by the photodetectors. Each of the photodetectors is associated with a corresponding one of the illuminators, and each of the color filters is associated with a corresponding one of the photodetectors. Each color filter is positioned in-between its corresponding illuminator and photodetector and passes a particular spectrum of light while filtering out other spectrums of light. Consequently, the photodetectors each receive spectrally filtered light having passed through at least one of the color filters. The power output of the illuminators can also be corrected based on output from the photodetectors.
-
公开(公告)号：US20210303638A1
公开(公告)日：2021-09-30
申请号：US16836546
申请日：2020-03-31
Applicant: Microsoft Technology Licensing, LLC
Inventor： Peide Zhong , Feishe Chen , Weizhi Meng , Wei Kang , Feng Guo , Fei Chen , Jaewon Yang , Qi He
IPC: G06F16/903 , G06K9/62 , G06F40/30 , G06N20/00
Abstract: The disclosed embodiments provide a system for processing user-generated input. During operation, the system obtains a first embedding produced by an embedding model from an input string representing an entity and a hierarchy of clusters of embeddings generated by the embedding model from a set of standardized entities. Next, the system searches the hierarchy of clusters for a subset of the embeddings that are within a threshold proximity to the first embedding in a vector space. The system then calculates embedding match scores between the input string and a first subset of the standardized entities represented by the subset of the embeddings based on distances between the subset of the embeddings and the first embedding in the vector space. Finally, the system modifies, based on the embedding match scores, content outputted in response to the input string within a user interface of an online system.
-
Patent Agency Ranking
公开(公告)号：US20190228343A1
公开(公告)日：2019-07-25
申请号：US15878186
申请日：2018-01-23
Applicant: Microsoft Technology Licensing, LLC
Inventor： Songxiang Gu , Xuebin Yan , Shihai He , Andris Birkmanis , Fei Chen , Yu Gong , Chang-Ming Tsai , Siyao Sun , Joel D. Young
IPC: G06N99/00
Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a model definition and a training configuration for a machine-learning model, wherein the training configuration includes a set of required features, a training technique, and a scoring function. Next, the system uses the model definition and the training configuration to load the machine-learning model and the set of required features into a training pipeline without requiring a user to manually identify the set of required features. The system then uses the training pipeline and the training configuration to update a set of parameters for the machine-learning model. Finally, the system stores mappings containing the updated set of parameters and the set of required features in a representation of the machine-learning model.
-
公开(公告)号：US20230306372A1
公开(公告)日：2023-09-28
申请号：US17688409
申请日：2022-03-07
Applicant: Microsoft Technology Licensing, LLC
Inventor： Xilun Chen , Chen-Kun Chuang , Xing Wu , Fei Chen , Wenxuan Gao , Jingwei Wu , Rohan Rajiv , Swathi Singh , Mathias Arkayin , Andrew Wu
CPC classification number: G06Q10/1053 , G06N3/08
Abstract: In an example embodiment, a deep neural network is used to predict a classification for ingested job listings for a piece of information that is missing from the ingested job listings. More particularly, the deep neural network may comprise a multi-layer perceptron with a plurality of rectifier linear units (ReLUs). For a given category of information, a plurality of different information entities may be evaluated by the multi-layer perceptron against features of a job listing, producing a probability prediction of reach of those information entities for the job listing. The information entity with the highest predicted probability is identified by the multi-layer perceptron as the predicted information entity for that given category of information for the job listing.
-
公开(公告)号：US20220391690A1
公开(公告)日：2022-12-08
申请号：US17340607
申请日：2021-06-07
Applicant: Microsoft Technology Licensing, LLC
Inventor： Shuai Wang , Piede Zhong , Ji Yan , Feng Guo , Dan Shacham , Fei Chen
Abstract: Described herein is a technique for mapping the raw text of a job title of an online job posting to an entity embedding, associated with an entity or entry of a title taxonomy. The raw text of the job title is first encoded to generate a multilingual word embedding in a multilingual word embedding space. Then, the vector representation of the job title, as represented in the multilingual word embedding space is translated, using a neural network, to a vector representation of the job title in the entity embedding space. Finally, a nearest neighbor search is performed to identify an entity embedding associated with an entity or entry in the title taxonomy that has a vector representation that is closest in distance to the vector output by the neural network.
-
公开(公告)号：US11481448B2
公开(公告)日：2022-10-25
申请号：US16836546
申请日：2020-03-31
Applicant: Microsoft Technology Licensing, LLC
Inventor： Peide Zhong , Feishe Chen , Weizhi Meng , Wei Kang , Feng Guo , Fei Chen , Jaewon Yang , Qi He
Abstract: During operation, the system obtains a first embedding produced by an embedding model from an input string representing an entity and a hierarchy of clusters of embeddings generated by the embedding model from a set of standardized entities. Next, the system searches the hierarchy of clusters for a subset of the embeddings that are within a threshold proximity to the first embedding in a vector space. The system then calculates embedding match scores between the input string and a first subset of the standardized entities represented by the subset of the embeddings based on distances between the subset of the embeddings and the first embedding in the vector space. Finally, the system modifies, based on the embedding match scores, content outputted in response to the input string within a user interface of an online system.
-
公开(公告)号：US20190325352A1
公开(公告)日：2019-10-24
申请号：US15959023
申请日：2018-04-20
Applicant: Microsoft Technology Licensing, LLC
Inventor： Chang-Ming Tsai , Fei Chen , Siyao Sun , Shihai He , Yu Gong , Scott A. Banachowski , Joel D. Young
Abstract: The disclosed embodiments provide a system for processing data. During operation, the system obtains a feature dependency graph of features for a machine learning model and an operator dependency graph comprising operators to be applied to the features. Next, the system generates feature values of the features according to an evaluation order associated with the operator dependency graph and feature dependencies from the feature dependency graph. During evaluation of an operator in the evaluation order, the system updates a list of calculated features with one or more features that have been calculated for use with the operator. During evaluation of a subsequent operator in the evaluation order, the system uses the list of calculated features to omit recalculation of the feature(s) for use with the subsequent operator.
-
-
-
-
-
-
-
-
-
Search Results
16
records
(took 0.016 seconds)
