Context aware chat history assistance using machine-learned models
First Claim
1. A mobile computing device, comprising:
- at least one processor;
a display screen;
a machine-learned context determination model, wherein the context determination model has been trained to receive one or more portions of device data from one or more input sources accessible by the mobile computing device and determine a current user context indicative of one or more activities in which a user of the mobile computing device is currently engaged;
at least one tangible, non-transitory computer-readable medium that stores instructions that, when executed by the at least one processor, cause the mobile computing device to perform operations, the operations comprising;
obtaining a first set of one or more portions of device data from one or more input sources accessible by the mobile computing device;
inputting the first set of one or more portions of device data into the machine-learned context determination model;
receiving, as an output of the machine-learned context determination model, a determined user context;
determining one or more portions of text from one or more applications of the mobile computing device that have an assigned user context that matches the determined user context; and
providing the one or more portions of text for display on the display screen of the mobile computing device.
2 Assignments
0 Petitions
Accused Products
Abstract
The present disclosure provides systems and methods that leverage machine learning to implement context determination and/or text extraction in computing device applications. Particular embodiments can include and use a machine-learned text extraction model that has been trained to receive one or more messages containing text and determine one or more portions of extracted text from the one or more messages as well as a corresponding user context assigned to each of the one or more portions of extracted text. In addition, or alternatively, particular embodiments can include and use a machine-learned context determination model that has been trained to receive one or more portions of device data from one or more input sources available at the mobile computing device and determine a current user context indicative of one or more activities in which a user of the mobile computing device is currently engaged.
-
Citations
26 Claims
-
1. A mobile computing device, comprising:
-
at least one processor; a display screen; a machine-learned context determination model, wherein the context determination model has been trained to receive one or more portions of device data from one or more input sources accessible by the mobile computing device and determine a current user context indicative of one or more activities in which a user of the mobile computing device is currently engaged; at least one tangible, non-transitory computer-readable medium that stores instructions that, when executed by the at least one processor, cause the mobile computing device to perform operations, the operations comprising; obtaining a first set of one or more portions of device data from one or more input sources accessible by the mobile computing device; inputting the first set of one or more portions of device data into the machine-learned context determination model; receiving, as an output of the machine-learned context determination model, a determined user context; determining one or more portions of text from one or more applications of the mobile computing device that have an assigned user context that matches the determined user context; and providing the one or more portions of text for display on the display screen of the mobile computing device. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A mobile computing device, comprising:
-
at least one processor; a machine-learned text extraction model, wherein the text extraction model has been trained to receive one or more messages containing text and determine one or more portions of extracted text from the one or more messages and a corresponding user context assigned to each of the one or more portions of extracted text; at least one tangible, non-transitory computer-readable medium that stores instructions that, when executed by the at least one processor, cause the mobile computing device to perform operations, the operations comprising; obtaining a first set of messages containing text from one or more applications of the mobile computing device; inputting the first set of messages containing text into the machine-learned text extraction model; receiving, as an output of the machine-learned text extraction model, one or more portions of extracted text from the first set of messages and a corresponding user context assigned to each of the one or more portions of extracted text; and providing at least one portion of extracted text assigned to at least one corresponding user context as output. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 19, 20)
-
-
21. One or more tangible, non-transitory computer-readable media storing computer-readable instructions that when executed by one or more processors cause the one or more processors to perform operations, the operations comprising:
-
obtaining a first set of messages containing text from one or more applications of a mobile computing device; inputting the first set of messages containing text into a machine-learned text extraction model, wherein the text extraction model has been trained to receive one or more messages containing text and determine one or more portions of extracted text from the one or more messages and a corresponding user context assigned to each of the one or more portions of extracted text; receiving, as an output of the machine-learned text extraction model, one or more portions of extracted text from the first set of messages and a corresponding user context assigned to each of the one or more portions of extracted text; and providing at least one portion of extracted text assigned to at least one corresponding user context as output. - View Dependent Claims (22, 23)
-
-
24. One or more tangible, non-transitory computer-readable media storing computer executable instructions that when executed by one or more processors cause the processors to perform operations, the operations comprising:
-
obtaining a first set of one or more portions of device data from one or more input sources accessible by a mobile computing device; inputting the first set of one or more portions of device data into a machine-learned context determination model, wherein the context determination model has been trained to receive one or more portions of device data from the one or more input sources and determine a current user context indicative of one or more activities in which a user of the mobile computing device is currently engaged; receiving, as an output of the machine-learned context determination model, a determined current user context; determining one or more portions of text from one or more applications of the mobile computing device that are relevant to the determined user context; and providing the one or more portions of text for display on a display screen of the mobile computing device. - View Dependent Claims (25, 26)
-
Specification