Microsoft Technology Licensing, LLC

Converzai Inc.

Ashwarya Poddar

Ami Turgman

Yun-Cheng Ju

Royi Ronen

Andreas Stolcke

Oron Nir

Yosef Dinerstein

Edan Hauon

Yu Shrike Zhang

Lei Lu

Embodiments described herein are configured to generate a smart contract deployed to a distributed ledger platform. In particular, a first party and a second party select a smart contract template and a user interface user interface is thereafter presented to the parties for inclusion of negotiable contract elements. Upon agreement, a smart contract is thereafter generated by augmenting smart contract template programming code to include the included contract elements, and the code is compiled and deployed to a smart contract platform such as, for example, a blockchain. Embodiments include meta-instructions in the smart contract programming code that at least in part determines how the specified contract elements are included in the smart contract programming code. In embodiments, the meta-instructions are embedded in comments in the smart contract programming code.

Smart contract template meta-programming system and method

A system for improving conversational skills using a virtual speech agent is disclosed, including a virtual speech agent to execute a phone call between the virtual agent and a user. The virtual speech agent and user engage in a back-and-forth conversation, wherein the virtual speech agent generates a summary and a feedback report in view of the conversation.

System and method for providing a virtual speech agent for simulated conversations and conversational feedback

A system and method for analyzing a response to an interview questions is disclosed, including a speech recognition engine to receive audio information corresponding to a response to create a transcription of the response. A segmentation engine segments the transcription into one or more segments. A segment classification engine classifies the one or more segments into one or more functional units and group the functional units by at least one structure. A presentation skill KPI engine, a structure sequence KPI engine, and a content KPI engine to analyze the response and applying the analysis to a composite model to provide an overall rating of the response.

System and method for evaluating interview response quality

Methods for speaker role determination and scrubbing identifying information are performed by systems and devices. In speaker role determination, data from an audio or text file is divided into respective portions related to speaking parties. Characteristics classifying the portions of the data for speaking party roles are identified in the portions to generate data sets from the portions corresponding to the speaking party roles and to assign speaking party roles for the data sets. For scrubbing identifying information in data, audio data for speaking parties is processed using speech recognition to generate a text-based representation. Text associated with identifying information is determined based on a set of key words/phrases, and a portion of the text-based representation that includes a part of the text is identified. A segment of audio data that corresponds to the identified portion is replaced with different audio data, and the portion is replaced with different text.

System and method for speaker role determination and scrubbing identifying information

An omni-channel orchestrated conversation system and virtual conversation agent for realtime contextual and orchestrated omni-channel conversation with a human and an omni-channel orchestrated conversation process for conducting realtime contextual and fluid conversation with a human by a virtual conversation agent in relation to a particular domain are disclosed.

Omni-channel orchestrated conversation system and virtual conversation agent for realtime contextual and orchestrated omni-channel conversation with a human and an omni-channel orchestrated conversation process for conducting realtime contextual and fluid conversation with the human by the virtual conversation agent

Solutions for automated labeling of child objects within tagged parents include: receiving a plurality of parent objects, each having a tag and including a plurality of child objects; receiving a machine learning (ML) component operable to rank objects according to relevance to queries; for each parent object: generating a set of restricted objects, wherein each restricted object corresponds to each child object in the plurality of child objects; for each of a plurality of queries, ranking, with the ML component, the restricted objects according to relevance; based at least on the query and an inverse of the rank of the restricted objects, assigning a child object label.

Automated labeling of child objects within tagged parents

Embodiments described herein provide a user interface for interacting with a smart contract deployed to a blockchain. The user interface is custom-generated for each party to the smart contract. In particular, representations of actions that a particular party is enabled to perform and/or has already taken with respect to the smart contract are provided to that party via a user interface. A user experience generator queries the smart contract itself to determine which representations are to be provided to each party. The smart contract comprises functions and/or user experience annotations that indicate to the user experience generator which user interface representations should be provided to a particular user based on the party identity and/or the smart contract's state. The smart contract provides an event notification to the user experience generator, which prompts the user experience generator to query the smart contract to determine the allowed actions for a particular user.

User interface and smart contract interaction model for generating user interface representations

Embodiments described herein are configured to generate a smart contract deployed to a distributed ledger platform. In particular, a first party and a second party negotiate the terms of an engagement, jointly choose a mediator from those available on a social networking platform, and choose a smart contract template, and a user interface is thereafter presented to the parties for inclusion of negotiable elements. Upon agreement, a smart contract is thereafter generated and deployed to a smart contract platform such as, for example, a blockchain. Embodiments permit escrow of funds to the smart contract platform. Embodiments of the smart contract enable the parties to indicate completion or take other actions with respect to the engagement, or to initiate a dispute in which case, a chosen mediator is thereafter enabled by the smart contract to mediate the dispute through one or more smart contract actions made available to the mediator.

Smart contract generation and execution system with built-in mediator selection and enforcement tools

Solutions for automated labeling of child objects within tagged parents include: receiving a plurality of parent objects, each having a tag and including a plurality of child objects; receiving a machine learning (ML) component operable to rank the parent objects; for each parent object: generating a set of restricted objects, wherein each restricted object is missing a child object; for each of a plurality of queries, ranking, with the ML component, the restricted objects according to relevance; based at least on the query and an inverse of the rank of the restricted objects, assigning a child object label. In some examples, the object missing from the restricted object having the lowest relevance rank is assigned a label based on the query. Various advantageous uses of the assigned child labels include enhancing search result reporting, automatically generating ML training data, and automatically generating and/or modifying reports.

Growing community of inventors

Seattle, WA, United States of America

Ashwarya Poddar