Microsoft Technology Licensing, LLC

Vishwac Sena Kannan

Aleksandar Uzelac

Daniel J Hwang

Marieke Watson Iwema

Christopher Michael Whitten

Sangwoo Han

Yochay Kiriaty

Andrew Stephen Brown

Benjamin Abraham Russell Brown

Robert L Chambers

John Anthony Taylor

Tanvi Surti

Lisa Joy Stifelman

Alice Jane Bernheim Brush

Thomas M Soemo

Sergio Paolantonio

Jonathan Campbell

Adina Magdalena Trufinescu

Khuram Shahid

Yaser Khan

Ali Reza Emami

Jenny Kam

Dennis Mooney, Ii

Mouni Reddy

Molly Rose Suver

David Pinch

Zachary Thomas John Siddall

Tanvi Saumil Surti

Dennis James Ii Mooney

A visual bot designer displays a user interface that has a visual authoring canvas and a property pane. It can also have a serialized file display pane. A user can provide authoring inputs on any of the user interfaces, and the visual bot designer computing system generates and displays updates on the other parts of the user interface.

Visual design of a conversational bot

A chatbot designer user interface (UI) has a visual authoring canvas that shows visual elements indicative of a logical flow of processing in a chatbot application. The designer UI receives an authoring input identifying a language processing system that is to be used during runtime. The chatbot application is configured to use the identified language processing system.

Configuring a chatbot with remote language processing

A chat bot computing system includes a bot controller and a natural language processor. The natural language processor receives a first textual input and identifies concepts represented by the first textual input. An indication of the concepts is output to the bot controller which generates a response to the first textual input. The concepts output by the natural language processor are also fed back into the input to the natural language processor, as context information, along with an expiration indicator when a second textual input is received. The natural language processor then identifies concepts represented in the second textual input, based on the second natural language, textual input and unexpired context information.

Contextual feedback, with expiration indicator, to a natural understanding system in a chat bot

A visual trigger node, indicative of a trigger, is displayed on a first display portion. A trigger configuration user interface is also displayed. A property input, indicative of a property that activates the trigger, is detected and code is generated to map the trigger to the property.

Visual trigger configuration of a conversational bot

Various embodiments provide a frequent sites module which is designed to generate frequent sites for a user that include websites that are relevant to the user based on browsing patterns of the user. In one or more embodiments, the frequent sites are generated from user-engagement data that indicates engagement by the user with websites identified in the user's browsing history. A web platform, e.g., a web browser, can display the frequent sites for the user in a frequent sites user interface container to enable the user to efficiently navigate to the websites that are relevant to the user by selection of websites from the frequent sites user interface container. Various embodiments describe other aspects of frequent sites based on browsing patterns, including multiple-device frequent sites, device-specific frequent sites, domain-specific frequent sites, URL-specific frequent sites, decaying of frequent sites, recent frequent sites, and contextual frequent sites.

Frequent sites based on browsing patterns

An electronic device can receive user input via voice or text that includes tasks to be performed. A digital personal assistant infrastructure service can control to which registered action provider the task is assigned. Per-task action provider preferences can be stored. If a preferred action provider is not able to complete the task, the task can still be performed by a registered action provider that has appropriate capabilities. Machine learning can determine a user's preferences. Resource conservation and effective user interaction can result.

Extending digital personal assistant action providers

Techniques are described for headlessly completing a task of an application in the background of a digital personal assistant. For example, a method can include receiving a voice input via a microphone. Natural language processing can be performed using the voice input to determine a user voice command. The user voice command can include a request to perform a task of the application. The application can be caused to execute the task as a background process without a user interface of the application appearing. A user interface of the digital personal assistant can provide a response to the user, based on a received state associated with the task, so that the response comes from within a context of the user interface of the digital personal assistant without surfacing the user interface of the application.

Headless task completion within digital personal assistants

Techniques are described for discovering capabilities of voice-enabled resources. A voice-controlled digital personal assistant can respond to user requests to list available voice-enabled resources that are capable of performing a specific task using voice input. The voice-controlled digital personal assistant can also respond to user requests to list the tasks that a particular voice-enabled resource can perform using voice input. The voice-controlled digital personal assistant can also support a practice mode in which users practice voice commands for performing tasks supported by voice-enabled resources.

Discovering capabilities of third-party voice-enabled resources

An electronic device in a topology of interconnected electronic devices can listen for a wake phrase and voice commands. The device can control when and how it responds so that a single device responds to voice commands. Per-task device preferences can be stored for a user. If a preferred device is not available, the task can still be performed on a device that has appropriate capabilities. Machine learning can determine a user's preferences. Power conservation and effective user interaction can result.

Device arbitration for listening devices

A method for providing digital personal assistant responses may include receiving, by a digital personal assistant associated with a plurality of reactive agents, a user input initiating a dialog with the digital personal assistant within the computing device. In response to receiving the input, an operation mode of the computing device may be detected from a plurality of available operation modes. One of the plurality of reactive agents can be selected based on the received input. A plurality of response strings associated with the selected reactive agent can be accessed. At least one of the plurality of response strings is selected based at least on the operation mode and at least one hardware characteristic of the computing device. The selected at least one of the plurality of response strings is providing during the dialog, as a response to the user input.

Scaling digital personal assistant agents across devices

A method for updating language understanding classifier models includes receiving via one or more microphones of a computing device, a digital voice input from a user of the computing device. Natural language processing using the digital voice input is used to determine a user voice request. Upon determining the user voice request does not match at least one of a plurality of pre-defined voice commands in a schema definition of a digital personal assistant, a GUI of an end-user labeling tool is used to receive a user selection of at least one of the following: at least one intent of a plurality of available intents and/or at least one slot for the at least one intent. A labeled data set is generated by pairing the user voice request and the user selection, and is used to update a language understanding classifier.

Growing community of inventors

Redmond, WA, United States of America

Vishwac Sena Kannan