US 9,866,927 B2 · Identifying entities based on sensor data

Abstract

Sensor data from multiple sensors associated with a user is received. The sensors may include sensors of a smart phone, and sensors associated with other devices such as fitness trackers, video game consoles, and cameras. The sensor data is processed to identify entities such as persons, locations, and objects that may be of interest to the user. A personal digital assistant application can present information related to the identified entities to the user, and can allow the user to perform various queries with respect to the identified entities, and previously identified entities. In addition, the identified entities can be used to trigger one or more rules including recording when and where a particular entity is identified, and generating an alert when a particular entity is identified.

Claims20

Dependent claims

A system for automatically identifying entities based on sensor data and for performing one or more actions based on the identified entities, the system comprising:

at least one computer;
and
an entity engine adapted to:
store a plurality of rules, wherein each rule is associated with an entity and an action;
receive sensor data from a plurality of sensors;
identify a plurality of entities from the sensor data;
determine one or more rules of the plurality of rules that match an entity of the plurality of entities;
perform the action associated with at least one of the determined one or more rules;
determine an entity of interest of the plurality of entities by scoring each of the plurality of entities and selecting the entity with the highest score as the entity of interest, wherein the scoring is based on at least one of user query data or global query data, wherein the user query data includes a history of queries associated with a user of the at least one computer, and wherein the global query data includes a history of queries associated with a plurality of users other than the user;
determine attributes associated with the entity of interest, wherein the attributes comprise descriptive information about the entity of interest;
and
display the entity of interest and one or more of the determined attributes on a device.

9 more elements

A method for automatically identifying entities based on sensor data and for determining attributes associated with the identified entities, the method comprising:

collecting sensor data from one or more sensors of a plurality of sensors associated with a device by the device;
identifying a plurality of entities from the sensor data by the device;
receiving user input by the device;
determining one or more entities of interest from the plurality of entities based on the received user input by the device and by scoring each of the plurality of entities and selecting the entity with the highest score as the entity of interest, wherein the scoring is based on at least one of user query data or global query data, wherein the user query data includes a history of queries associated with a user of the device, and wherein the global query data includes a history of queries associated with a plurality of users other than the user;
determining a query based on the received user input by the device;
determining attributes associated with the one or more entities of interest based on the query by the device, wherein the attributes comprise descriptive information about the one or more entities of interest;
and
displaying the one or more entities of interest and one or more attributes of the determined attributes on a display associated with the device by the device.

5 more elements

Dependencies are inferred from the claim text.

Identifying entities based on sensor data

Life of this patent

Identifying entities based on sensor data

Life of this patent

Abstract

Claims20