Apple Inc.

Other

Juan Carlos Garcia

Timothy S Paek

Kurt W Piersol

Moises Goldszmidt

Vishwas Kulkarni

Anatoly D Adamov

Pavan Chitta

Julia R Reisler

Yu-Chung Hsiao

Paul S McCarthy

Rushin N Shah

Nicholas K Treadgold

Jamil Dhanani

Mubarak Ali Seyed Ibrahim

Naga Rama Abhishek Pratapa

Gagan Aneja

Muhammad Amir Shafiq

Alexandra Garcia

Justin J Brinegar

Paul S Mccarthy

Geoffrey Nagy

SeyedMehdi Mohaimenianpour

Alan Qian

Richard T Vaughan

Systems and methods are disclosed for triggering an update to a machine-learning model upon detecting that a distribution of particular (e.g., recently collected) input data set is sufficiently different from a distribution training input data set used to train the model. The distributions may be determined to be sufficiently different when a classifier can identify to which distribution individual data elements belong (e.g., to at least a predetermined degree). An update to the machine-learning model can include morphing weights used by the model and/or retraining the model.

Automated input-data monitoring to dynamically adapt machine-learning techniques

Systems and processes for an integrated sensor framework are provided. For example, a first electronic device receives at least one input including sensor data from a second device. A representation of a physical environment associated with the first electronic device is obtained based on sensor data from the first electronic device and the sensor data from the second device. Movement information corresponding to movement of an object within the physical environment is identified. Event information is determined corresponding to activity within the physical environment, wherein the event information is determined based on the identified movement information and the representation of the physical environment. Accordingly, an output is provided to the user based on the event information.

Integrated sensor framework for multi-device communication and interoperability

A universal barrier system includes universal barrier components that may be assembled together to shield floors and walls from moisture and provide a thermal break in an operational area of the universal barrier component. A lap zone of the universal barrier component may allow universal barrier components to be assembled and installed to protect floors, walls, ceilings, footings and the like from moisture and heat gain or loss by minimizing the need for tapes and other joining methods. The universal barrier system may also act as a sound deadening material. The operational area and lap zone of the universal barrier component may be disposed on a vapor block layer to provide some rigidity. The operational area of the universal barrier component may include a thermal break disposed upon the vapor block layer. The thermal break may include an outer protective layer. In addition, universal barrier tape and universal barrier edging may be provided to couple adjoining universal barrier components.

Universal barrier system panels

Systems and processes for operating a virtual assistant to provide natural assistant interaction are provided. In accordance with one or more examples, a method includes, at an electronic device with one or more processors and memory: receiving a first audio stream including one or more utterances; determining whether the first audio stream includes a lexical trigger; generating one or more candidate text representations of the one or more utterances; determining whether at least one candidate text representation of the one or more candidate text representations is to be disregarded by the virtual assistant. If at least one candidate text representation is to be disregarded, one or more candidate intents are generated based on candidate text representations of the one or more candidate text representations other than the to be disregarded at least one candidate text representation.

Natural assistant interaction

Systems and processes for natural language processing using vocabularies with compressed serialized tries are described in the present disclosure. In one example process, natural language input is received. The natural language input is parsed, using a vocabulary, to determine a corresponding user intent. The parsing includes using a data structure of the vocabulary to map a first word of the natural language input to first semantic information and a second word of the natural language input to second semantic information. The data structure includes pointers that map to a same semantic data object of the vocabulary. The first semantic information and the second semantic information are determined using the same semantic data object. The user intent is determined based on the first semantic information and the second semantic information. Performance of a task corresponding to the determined user intent is initiated.

Natural language understanding using vocabularies with compressed serialized tries

Plant stand

Illuminated toilet seat

An improved bed covering is provided for a mattress on a bedstead, which consists of an apparatus for protecting the mattress and a mechanism for retaining the protecting apparatus to the mattress on the bedstead in a wrinkle free condition. A person resting on the protecting apparatus will be more comfortable.

Wrinkle free bedsheet

A wall plate is arranged for selective reception of a support member having a floor, with an internally threaded cylindrical skirt arranged to receive a mouthwash dispensing fluid container therewithin, with a valve plate reciprocatably mounted relative to a bottom surface of the floor to permit selective fluid flow therethrough. The apparatus is further arranged to include an adapter head arranged to receive a mouthwash bottle thereon having a truncated, conical directional conduit to receive an outlet opening of a fluid bottle.

Mouthwash dispenser kit apparatus

Growing community of inventors

San Francisco, CA, United States of America

Juan Carlos Garcia