Microsoft Technology Licensing, LLC

Oussama Elachqar

Emmanouil Koukoumidis

Joseph Edwin Johnson, Jr

Oz Solomon

Ying Wang

Sergey Aleksandrovich Doroshenko

Maria Alexandropoulou

Badal Yadav

Nima Mohajerin

Di Li

Hailong Mu

Dustin Isaac Abramson

Qi Yao

Donald Brinkman

Kati Amanda London

Konstantinos Aisopos

Zhiying Zhang

James Bigbee Garver

Derrick Fu

Joseph Edwin Johnson

Ink-processing technology is set forth herein for detecting a gesture that a user performs in the course of interacting with an ink document. The technology operates by identifying a grouping of ink strokes created by the user. The technology then determines whether the grouping expresses a gesture based on a combination of spatial information and image information, both of which describe the grouping. That is, the spatial information describes a sequence of positions traversed by the user in drawing the grouping of ink strokes using an ink capture device, while the image information refers to image content in an image produced by rendering the grouping into image form. The technology also provides a technique for identifying the grouping by successively expanding a region of analysis, to ultimately provide a spatial cluster of ink strokes for analysis.

Detecting ink gestures based on spatial and image data processing

Technology is described herein for parsing an ink document having a plurality of ink strokes. The technology performs stroke-level processing on the plurality of ink strokes to produce stroke-level information, the stroke-level information identifying at least one characteristic associated with each ink stroke. The technology also performs object-level processing on individual objects within the ink document to produce object-level information, the object-level information identifying one or more groupings of ink strokes in the ink document. The technology then parses the ink document into constituent parts based on the stroke-level information and the object-level information. In some implementations, the technology converts the ink stroke data into an ink image. The stroke-level processing and/or the object-level processing may operate on the ink image using one or more neural networks. More specifically the stroke-level processing can classify pixels in the input image, while the object-level processing can identify bounding boxes containing possible objects.

Parsing an ink document using object-level and stroke-level processing

Systems and methods may be used to process and output information related to a non-speech vocalization, for example from a user attempting to mimic a non-speech sound. A method may include determine a mimic quality value associated with an audio file by comparing a non-speech vocalization to a prerecorded audio file. For example, the method may include determining an edit distance between the non-speech vocalization and the prerecorded audio file. The method may include assigning a mimic quality value to the audio file based on the edit distance. The method may include outputting the mimic quality value.

Audio processing for voice simulated noise effects

A system provides emotionally and intellectually relevant responses to user queries received by a chatbot instantiated by a computing device. The system also receives user data associated with the user query. The user query is communicated to a first supervised machine learning model to obtain a first plurality of ranked responses. The system also communicates the received user data to a second supervised machine learning model to obtain a first plurality of emotions associated with the user data. The system then determines determine a second plurality of emotions for the first plurality of responses and re-ranks the first plurality of responses based on a comparison of the first plurality of emotions and the second plurality of emotions. The system then selects a response to the user query from the re-ranked responses and outputs the selected response using the chatbot instantiated by the computing device.

Emotional intelligence for a conversational chatbot

Representative embodiments disclose mechanisms for discovering, synthesizing, presenting and interacting with multiple chat bots. A broker system can interact with a user and receive a query which is passed to a search engine. The search results are evaluated for bots provided by domains. The query can be submitted to the discovered bots. For domains that do not provide a bot, a bot can be synthesized if desired and the query submitted to the synthesized bots. Answers from the bots are retrieved. Answer are directly presented for bots that are directly surfaced to the user in the search results page. Answers can be fused for bots that are not directly surfaced to the user and presented via a broker bot. Answers from the one bot can be fed to other bots so that the bots can participate in a group chat between bots and the user.

Conversation bot discovery and response fusion

Growing community of inventors

Seattle, WA, United States of America

Oussama Elachqar