Google Inc.

Massachusetts Institute of Technology

Nio Usa, Inc.

Nadav Aharony

Christopher Richard Wren

Alan Lee Gardner, Iii

George Cody Sumter

Mohammed Waleed Kadous

Brian Patrick Williams

Andrew Ames Bunner

Pascal Tom Getreuer

Marc Stogaitis

Zhentao Sun

Ami Patel

Thomas Chao

Richard Daniel Webb

Benjamin Razon

Tony Weber

Liem Tran

Joseph A Farfel

Brian Duff

Daniel Estrada Alva

Richard Francis Lyon

Ryan Michael Rifkin

Denise Ho

Abhishek Singhal

Alex Paul Pentland

Anthony Tao Liang

Gautam Muralidhar

Michael D Siegel

Ralph Jacob Cressman

Yaniv Altshuler

Wei Pan

A system and method for associating users with a micro-community that is relevant to an object reference. The object reference is anything that can be perceived either physically or conceptually, such as a location, a document, a calendar entry, a document, a news feed, a biometric key, an image, a news feed, etc. A micro-community engine identifies users who are associated explicitly with the object reference as well as people who would be interested in the object implicitly and associates them with a micro-community. The micro-community engine provides an intuitive and flexible means for communication between members of the micro-community.

Tools for micro-communities

The disclosure includes a system and method for detecting proximity between users. The system includes a processor and a memory storing instructions that when executed cause the system to: determine a context associated with a first user device; query other user devices based on the context to create a set of other user devices that satisfy a query; generate a list of filtered devices by filtering the set of other user devices; notify the first user device of the list of filtered devices; and query for the list of filtered devices to determine which filtered devices are within proximity to the first user device.

Proximity detection

The disclosure includes a system and method for detecting fine grain copresence between users. The system includes a processor and a memory storing instructions that when executed cause the system to: transmit a wakeup signal to a plurality of devices based on coarse grain location information; send a request to a first device of the plurality of devices to transmit a token using a first communication technology to determine fine grain copresence; receive a first token acknowledgment from a first subset of the plurality of devices; send a request to a second device of the first subset of the plurality of devices to transmit the token using a second communication technology to determine fine grain copresence; receive a second token acknowledgment from a second subset of the plurality of devices; and refine copresence based on receiving the first and second token acknowledgment.

Server orchestrated connectivity

The disclosure includes a system and method for summarizing social interactions between users. The system includes a processor and a memory storing instructions that when executed cause the system to: receive a signal stream from at least one of a hardware sensor and a virtual detector, filter the signal stream and outputting filtered signal stream including data defining human-understandable actions, identify activities associated with a first user from the filtered signal stream, generate a summary of the first user's activities, determine that the first user is within proximity to a second user, determine a degree of separation between the first user and the second user in a social network, determine a time elapsed since a last interaction between the first user and the second user, classify the first user's relationship with the second user as being a first type of relationship, a second type of relationship or a third time of relationship, responsive to having the first type of relationship, generate a first summary for the first user that includes a notification that the second user is nearby, a last interaction with the second user and recent interactions with the second user, responsive to having the second type of relationship, generate a second summary for the first user that includes the notification that the second user is nearby, the last interaction with the second user and events that the first user and the second user share in common, and responsive to having the third type of relationship, generate a third summary for the first user that includes the notification that the second user is nearby and events that the first user and the second user share in common.

Summarizing social interactions between users

The systems and methods described herein can be applied to a vehicle equipped with a sensor suite that can observe information about a location, for example, a traffic light duration. The system can record information, e.g., the traffic light colors, duration of color changes, and location of the traffic lights and can upload this information to the cloud. Then, the system can augment or learn about the location, e.g., learning of traffic patterns, and store the augmented data as database-based information, where available. The learned information can help a requesting vehicle to better estimate an estimated time of arrival (ETA) for common routes taken, provide more accurate ETAs based on historical knowledge, and/or calculate or provide alternative route information.

Adaptive route and motion planning based on learned external and internal vehicle environment

A system and associated methods for generating a temporal event stream for a user is disclosed. The system includes a processor and a memory storing instructions that when executed cause the system to: receive a signal stream from a user device, determine one or more events from the signal stream, generate a first event stream based on the one or more events, generate one or more queries based on the signal stream, retrieve new events by applying the one or more queries against data stored by an event server and update the first event stream with the new events.

Event stream architecture for syncing events

A system and method for retrieving contact information based on image recognition searches is disclosed. A requestor takes a picture of a user or retrieves a storage image of a user and transmits the image to an image recognition module. The image recognition module identifies the user and determines whether the requestor can receive access to the user's contact information based on permission rules. For example, the permission rule includes a requirement that the user and the requestor be sufficiently related on a social graph generated by a social network application. The permission rules can also include a requirement that the requestor have a predetermined proximity to the image. Once the permission rules are satisfied, the image recognition module transmits the user's contact information to the requestor.

Retrieving contact information based on image recognition searches

The disclosure includes a system and method for creating event streams from raw data. The system includes a processor and a memory storing instructions that when executed cause the system to: receive a first event and a second event associated with a first user from a first user device; receive a third event associated with a second user from a second user device; determine one or more overlapping activities between the first event and the third event; update the first event using the third event to generate a first update event; update the third event using the first event to generate a second update event; generate a first event stream that includes the first update event and the second event for the first user; and generate a second event stream that includes the second update event for the second user.

Creating event streams from raw data

The disclosure includes a system and method for detecting fine grain copresence between users. The system includes a processor and a memory storing instructions that when executed cause the system to receive user input regarding copresence detection settings for a first user device, the copresence detection settings comprising a location and/or a user access control list, and determine a current location of the first user device. The system may determine whether copresence detection of the first user device is enabled at the current location based on the copresence detection settings and the current location. Based on determining that copresence detection is enabled, the system may refine copresence and perform an action based on fine grain copresence of the first and second user device.

Copresence permission model

The disclosure includes a system and method for summarizing social interactions between users. The system includes a processor and a memory storing instructions that when executed cause the system to: receive a signal stream from at least one of a hardware sensor and a virtual detector, filter the signal stream and outputting filtered signal stream including data defining human-understandable actions, identify activities associated with a first user from the filtered signal stream, generate a summary of the first user's activities, determine that the first user is within proximity to a second user, determine a degree of separation between the first user and the second user in a social network, determine a time elapsed since a last interaction between the first user and the second user, classify the first user's relationship with the second user as being a first type of relationship, a second type of relationship or a third type of relationship, responsive to having the first type of relationship, generate a first summary for the first user that includes a notification that the second user is nearby, a last interaction with the second user and recent interactions with the second user, responsive to having the second type of relationship, generate a second summary for the first user that includes the notification that the second user is nearby, the last interaction with the second user and events that the first user and the second user share in common, and responsive to having the third type of relationship, generate a third summary for the first user that includes the notification that the second user is nearby and events that the first user and the second user share in common.

A system and method for translating a social feed is disclosed. The system comprises a communication module, a decoding engine and a re-encoding engine. The communication module receives social feed data and a request from a social network application. The social feed data is configured to cause a client to display a social feed in a first language. The request includes data indicating that the social feed should be displayed in a second language. The decoding engine decodes the social feed data to generate decoded social feed data. The re-encoding engine re-encodes the decoded social feed data to cause the client to display the social feed in the second language based at least in part on the request. The communication module sends the translated social feed data to the client.

Feed translation for a social network

The disclosure includes a system and method for detecting fine grain copresence between users. The system includes a processor and a memory storing instructions that when executed cause the system to: process one or more signals to determine coarse grain location information of a first device and a second device; determine whether the first device and the second device are copresent based on the coarse grain location information; in response to determining that the first device and the second device are copresent based on the coarse grain location information, transmit a signal to the second device to alert the second device to listen for a fine grain copresence token from the first device; and refine copresence based on receiving an indication that the second device has received the fine grain copresence token.

Two-pass copresence

In exemplary implementations of this invention, mobile application (app) installations by users of one or more networks are predicted. Using network data gathered by smartphones, multiple 'candidate' graphs (including a call log graph) are calculated. The 'candidate' graphs are weighted by an optimization vector and then summed to calculate a composite graph. The composite graph is used to predict the conditional probabilities that the respective users will install an app, depending in part on whether the user's neighbors have previously installed the app. Exogenous factors, such as the app's quality, may be taken into account by creating a virtual candidate graph. The conditional probabilities may be used to select a subset of the users. Signals may be sent to the subset of users, including to recommend an app. Also, the probability of successful &#x201c;trend ignition&#x201d; may be predicted from network data.

Growing community of inventors

Mountain View, CA, United States of America

Nadav Aharony