Lenovo (singapore) Pte. Ltd.

Honda Motor Co., Ltd.

Facebook, Inc.

Other

Lenovo Limited

Antoine Roland Raux

Rakesh Gupta

Rod D Waltermann

Deepak Ramachandran

Rajen Subba

Grigori Zaitsev

Akshay Chandrashekaran

Benoit F Dumoulin

Wenhai Yang

Savas Parastatidis

Stefan Nelson-Lindall

Russell Speight VanBlon

Jianbang Zhang

Timothy Winthrop Kingsbury

Suzanne Marion Beaumont

Ian R Lane

Jian Yang

Hermann Franz Burgmeier

Igor V Karpov

Yi Ma

Adam C Vogel

Neville Mehta

Stefan Krawczyk

Matthew Hoffman

Martin Plouy

One embodiment provides an information handling device, including: a processor; a memory device that stores instructions executable by the processor to: receive, at an electronic device, a drawing input; receive, at the electronic device, secondary user input; and modify, the drawing input based on the secondary user input; wherein the secondary input is voice input. Other aspects are described and claimed.

Voice modified drawing

One embodiment provides a method, including: receiving, at an audio receiver, user voice data; identifying, using a processor, at least one characteristic of the voice data; obtaining, using the processor, a speech recognition processing result of the voice data; and changing a standard response to the user voice data to an adapted response based on the at least one characteristic and the speech recognition processing result. Other aspects are described and claimed.

Adapting voice input processing based on voice input characteristics

Exemplary embodiments relate to methods, mediums, and systems for managing a conversation. In an embodiment, a computer-implemented input interface is provided to receive an input comprising information in natural language. A dialog manager is configured to determine an intent of the input, determine information to fulfill the intent, and identify one or both of information available to the dialog manager or information that is unavailable to the dialog manager. A conversational understanding document documents the intent and the identified information. An output interface forwards the conversational understanding document towards a task completion handler separate and distinct from the dialog manager. Other embodiments are described and claimed.

Conversational understanding

For selecting multimodal elements, a method is disclosed that includes receiving a coarse-grained indication indicating a coarse-grained portion of an electronic document, receiving an audio signal comprising a fine-grained indication indicating a fine-grained portion of the coarse-grained portion and a command to be performed on the fine-grained portion, and executing the command on the fine-grained portion in response to receiving the audio signal.

Selecting multimodal elements

An embodiment provides a method, including: detecting, at an electronic device, a command input using a first modality; detecting, at the electronic device, a selecting input using a different modality; combining, using a processor, the command input and the selecting input into an application formatted command; and providing the application formatted command to an application running on the electronic device for execution. Other aspects are described and claimed.

Multi-modal fusion engine

This application addresses techniques for personalizing natural language generation by conversational agents. These solutions allow for human-like, large scale opinion expression using a consistent style or personality. Training sentences may be retrieved and a vocabulary may be built based on an analysis of the training sentences. The sentences may be analyzed to determine: (1) whether they express an opinion; (2) whether the opinion is positive or negative; (3) whether the sentence fits in the context of the currently communication; and (4) whether the sentence came from a person with first-hand experience of the topic. Further classifications may be made based on characteristics such as the age or gender of the person expressing the opinion. These opinions may be entered into a repository and used for opinion expression, for example by using the statements directly in a conversation or by training a language generation model with the opinions.

Analyzing language units for opinions

One embodiment provides a method, comprising: embedding, using a processor, code within an application; detecting, at an electronic device, a user input within the application, wherein the user input selects an object within the application; receiving, using a processor, data associated with the selected object; and sending, using a processor, data associated with the selected object to an application selected from the group consisting of the application and another application. Other aspects are described and claimed.

Identification of user input within an application

A method of providing notifications to users of a social networking service includes determining a user intent associated with a post from a user on the social networking service, based at least in part on content of the post. The method further includes generating a first notification of the user intent associated with the post and selecting a plurality of users of the social networking service to receive the first notification. The method further includes providing the first notification to the plurality of users, and after providing the first notification to the plurality of users: (1) receiving one or more responses to the first notification from one or more users of the plurality of users, the one or more responses including information responsive to the first notification, and (2) providing the information responsive to the first notification to the user.

Methods and systems for providing notifications to users of a social networking service

One embodiment provides a method, involving: detecting, at an electronic device, a location of user gaze; activating, based on the location of the user gaze, a voice input module, wherein the activating is based on a command input using a modality that detects an input in combination with the location of the user gaze, the modality comprising a change in velocity of the device; detecting, at the electronic device, a voice input; evaluating, using the voice input module, the voice input, and performing, based on evaluation of the voice input, at least one action. Other aspects are described and claimed.

Gaze triggered voice recognition incorporating device velocity

One embodiment provides a method, including: accepting, at a first input device of an electronic device, a first user input for an object resident on the electronic device; partially completing, using a processor, a user action based on the first user input; accepting, at another type of input device of the electronic device, a user input associated with the first user input for the object; combining, using a processor, the first user input for the object and the user input; and completing, using a processor, the user input action for the object based on the combined first user input and the user input. Other aspects are described and claimed herein.

Human interface device input fusion

One embodiment provides a method, including: receiving, at an input and display device, handwriting input; receiving, using a processor, voice input; generating, using a processor, at least one first word based on the handwriting input; generating, using a processor, at least one second word based on the voice input; and determining, using a processor, a highest probability word based on the at least one first word and the at least one second word. Other aspects are described and claimed.

OCR through voice recognition

One embodiment provides a method, including: receiving, at an audio receiver of a device, a voice input; selecting, using a processor of a device, an active target voice enabled resource for the voice input from among a plurality of active target voice enabled resources; and providing, using a processor of the device, the voice input to the active target voice enabled resource selected. Other aspects are described and claimed.

Multi-modal disambiguation of voice assisted input

One embodiment provides a method, including: displaying, on a display device, at least one notification; detecting, at an electronic device, a location of user gaze associated with the location of the at least one notification; determining, using a secondary detection, if a secondary input is detected; performing, based on the determining, at least one action. Other aspects are described and claimed.

Gaze based notification reponse

For hybrid language processing, a method is disclosed that includes identifying, by use of a processor, one or more user specific terms in a user generated portion of text, modifying the portion of text by replacing one or more of the user specific terms with general tokens, and converting the modified portion of text to one or more commands to be executed by the processor.

Growing community of inventors

Cupertino, CA, United States of America

Antoine Roland Raux