Google Inc.

Numenta, Inc.

Linkedin Corporation

Microsoft Technology Licensing, LLC

Nest Labs, Inc.

Frank Emmanuel Astier

Yoky Matsuoka

Rangoli Sharan

Dileep George

Anthony Michael Fadell

Jeffrey Charles Hawkins

Mark Rajan Malhotra

Mark D Stefanski

Evan Jarman Fisher

Subutai Ahmad

Robert Gilchrist Jaros

Liang Zhang

Deepak Agarwal

Ronald Marianetti, Ii

Bo Long

Jeffrey L Edwards

Jonathan David Traupman

David Hendler Sloo

William Cooper Saphir

Ronald Marianetti

Anosh Raj

Charles Curry

Wiliam C Saphir

Methods for controlling temperature in a conditioned enclosure such as a dwelling are described that include an 'auto-away' and/or 'auto-arrival' feature for detecting unexpected absences which provide opportunities for significant energy savings through automatic adjustment of the setpoint temperature. According to some preferred embodiments, when no occupancy has been detected for a minimum time interval, an &#x201c;auto-away&#x201d; feature triggers a changes of the state of the enclosure, and the actual operating setpoint temperature is changed to a predetermined energy-saving away-state temperature, regardless of the setpoint temperature indicated by the normal thermostat schedule. The purpose of the &#x201c;auto away&#x201d; feature is to avoid unnecessary heating or cooling when there are no occupants present to actually experience or enjoy the comfort settings of the schedule, thereby saving energy.

Control unit with automatic setback capabtility

A method includes a system that operates according to a control schedule; detects events that indicate occupancy; stores a record of the events that indicate occupancy in one or more memory devices; and enters an auto-away state. A determination to enter the auto-away state may be based at least in part on a length of a time interval during which no events that indicate occupancy were detected and the stored record of the events that indicate occupancy. The system may also detect a pattern of instances where the auto-away state is entered over a plurality of days and adjusts the control schedule based at least in part on the pattern of instances where the auto-away state is entered.

Automated presence detection and presence-related control within an intelligent controller

A user-friendly programmable thermostat is described that includes receiving an immediate-control input to change set point temperature, controlling temperature according to the set point temperature for a predetermined time interval, and then automatically resetting the set point temperature upon the ending of the predetermined time interval such that the user is urged to make further immediate-control inputs. A schedule for the programmable thermostat is automatically generated based on the immediate-control inputs. Methods are also described for receiving user input relating to the user's preference regarding automatically generating a schedule, and determining whether or not to automatically adopt an automatically generated schedule based on the received user input.

Energy efficiency promoting schedule learning algorithms for intelligent thermostat

Techniques for predicting a user response to content are described. According to various embodiments, a configuration file is accessed, where the configuration file includes a user-specification of raw data accessible via external data sources and raw data encoding rules. In some embodiments, the raw data includes raw member data associated with a particular member and raw content data associated with a particular content item. Thereafter, source modules encode the raw data from the external data sources into feature vectors, based on the raw data encoding rules. An assembler module assembles one or more of the feature vectors into an assembled feature vector, based on user-specified assembly rules included in the configuration file. A prediction module performs a prediction modeling process based on the assembled feature vector and a prediction model, to predict a likelihood of the particular member performing a particular user action on the particular content item.

Systems and methods for content response prediction

A method includes operating a controller according to a control schedule; detecting events that indicate occupancy; storing a record of the events that indicate occupancy in one or more memory devices; and causing the controller to enter an auto-away state. A determination that the controller should enter the auto-away state may be based at least in part on a length of a time interval during which no events that indicate occupancy were detected; and the stored record of the events that indicate occupancy. The method also includes detecting a pattern of instances where the controller enters the auto-away state over a plurality of days; and adjusting the control schedule based at least in part on the pattern of instances where the controller enters the auto-away state.

A device includes a memory configured to store a preexisting schedule and one or more processors configured to perform operations including controlling a temperature within an enclosure according to a first setpoint, wherein the first setpoint is from the preexisting schedule and represents a temperature for when the enclosure is occupied. The operations also include accessing occupancy data indicating occupancy within the enclosure and automatically changing the first setpoint to a second setpoint upon expiration of a predetermined time interval during which no occupancy has been detected. The second setpoint requires less energy to maintain than the first setpoint, and the predetermined time interval is modified based at least in part on received manual settings that indicate occupancy following the changing to the second setpoint.

Control unit with automatic setback capability

A web-based hierarchical temporal memory (HTM) system in which one or more client devices communicate with a remote server via a communication network. The remote server includes at least a HTM server for implementing a hierarchical temporal memory (HTM). The client devices generate input data including patterns and sequences, and send the input data to the remote server for processing. The remote server (specifically, the HTM server) performs processing in order to determine the causes of the input data, and sends the results of this processing to the client devices. The client devices need not have processing and/or storage capability for running the HTM but may nevertheless take advantage of the HTM by submitting a request to the HTM server.

Hierarchical temporal memory (HTM) system deployed as web service

The current application is directed to intelligent controllers that use sensor output and electronically stored information, including one or more of electronically stored rules, parameters, and instructions, to determine whether or not one or more types of entities are present within an area, volume, or environment monitored by the intelligent controllers. The intelligent controllers select operational modes and modify control schedules with respect to the presence and absence of the one or more entities. The intelligent controllers employ feedback information to continuously adjust the electronically stored parameters and rules in order to minimize the number of incorrect inferences with respect to the presence or absence of the one or more entities and in order to maximize the efficiency by which various types of systems controlled by the intelligent controllers carry out selected operational modes.

Techniques for predicting a user response to content are provided. In example embodiments, one or more feature vectors are assembled into an assembled feature vector. A particular one of the feature vectors not being available is determined. In response to determining that the particular one of the feature vectors is not available, the particular feature vector is ignored based on an importance value associated with the particular feature vector. A substitute value associated with the particular feature vector is inserted into a portion of the assembled feature vector associated with the particular feature vector. A prediction modeling process based on the assembled feature vector and a prediction model is performed to predict a likelihood of a particular member performing a particular user action on a particular content item.

Growing community of inventors

Mountain View, CA, United States of America

Frank Emmanuel Astier