User state-adaptive text input
First Claim
1. A method comprising:
- outputting, by a computing device and for display at a display device operatively coupled to the computing device, a graphical keyboard comprising a plurality of keys;
receiving, by the computing device, an indication of a gesture detected at a presence-sensitive input device operatively coupled to the computing device;
detecting, by the computing device, data indicative of one or more user states determined to affect gesture accuracy;
determining, for respective user states of the one or more user states, respective models that provide at least one value indicating a degree, in a range of degrees, to which the respective user state affects gesture accuracy;
selecting, by the computing device and based at least in part on the indication of the gesture and the data indicative of the one or more user states, a particular candidate string, wherein selecting the particular candidate string comprises;
determining, based on the gesture, a plurality of candidate character strings, wherein each of the plurality of candidate character strings is associated with at least one of a respective physical cost value from a spatial model and a respective lexical cost value from a language model;
adjusting, for a particular candidate character string of the plurality of candidate character strings and based at least in part on the detected one or more user states, at least one of a physical cost value associated with the particular candidate character string and a lexical cost value associated with the particular candidate character string, wherein the adjusting comprises adjusting a relative weight based on the respective models for each of the one or more user states; and
selecting, based at least in part on the adjusting, the particular candidate character string from the plurality of candidate character strings; and
outputting, by the computing device and for display at the display device, the particular candidate string.
2 Assignments
0 Petitions
Accused Products
Abstract
In one example, a method includes outputting, by a computing device (102) and for display at a display device (104) operatively coupled to the computing device, a graphical keyboard (124) comprising a plurality of keys, and receiving, by the computing device, an indication of a gesture detected at a presence-sensitive input device operatively coupled to the computing device. In this example, the method also includes detecting, by one or more sensors (154) of the computing device, data indicative of one or more user states determined to affect gesture accuracy; selecting, by the computing device and based at least in part on the indication of the gesture and the data, a particular candidate string; and outputting, by the computing device and for display at the display device, the particular candidate string.
18 Citations
16 Claims
-
1. A method comprising:
-
outputting, by a computing device and for display at a display device operatively coupled to the computing device, a graphical keyboard comprising a plurality of keys; receiving, by the computing device, an indication of a gesture detected at a presence-sensitive input device operatively coupled to the computing device; detecting, by the computing device, data indicative of one or more user states determined to affect gesture accuracy; determining, for respective user states of the one or more user states, respective models that provide at least one value indicating a degree, in a range of degrees, to which the respective user state affects gesture accuracy; selecting, by the computing device and based at least in part on the indication of the gesture and the data indicative of the one or more user states, a particular candidate string, wherein selecting the particular candidate string comprises; determining, based on the gesture, a plurality of candidate character strings, wherein each of the plurality of candidate character strings is associated with at least one of a respective physical cost value from a spatial model and a respective lexical cost value from a language model; adjusting, for a particular candidate character string of the plurality of candidate character strings and based at least in part on the detected one or more user states, at least one of a physical cost value associated with the particular candidate character string and a lexical cost value associated with the particular candidate character string, wherein the adjusting comprises adjusting a relative weight based on the respective models for each of the one or more user states; and selecting, based at least in part on the adjusting, the particular candidate character string from the plurality of candidate character strings; and outputting, by the computing device and for display at the display device, the particular candidate string. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A computing device comprising:
-
one or more processors; one or more sensors, coupled to the one or more processors, configured to detect data indicative of one or more user states determined to affect gesture accuracy; a presence-sensitive display, coupled to the one or more processors, comprising a display component and a presence-sensitive input component; and a storage device storing at least one module, wherein the at least one module is executable by the one or more processors to; output, for display at the display component, a graphical keyboard comprising a plurality of keys; receive an indication of a gesture detected at the presence-sensitive input component; determine, for respective user states of the one or more user states, respective models that provide at least one value indicating a degree, in a range of degrees, to which the respective user state affects gesture accuracy; select, based at least in part on the indication of the gesture and the data indicative of the one or more user states, a particular candidate string, wherein, to select the particular candidate string, the at least one module is executable by the one or more processors to; determine, based on the gesture, a plurality of candidate character strings, wherein each of the plurality of candidate character strings is associated with at least one of a respective physical cost value from a spatial model and a respective lexical cost value from a language model; adjust, for a particular candidate character string of the plurality of candidate character strings and based at least in part on the one or more user states, at least one of a physical cost value associated with the particular candidate character string and a lexical cost value associated with the particular candidate character string by at least adjusting a relative weight based on the respective models for each of the one or more user states; and select, based at least in part on the adjusting, the particular candidate character string from the plurality of candidate character strings; and output, for display at the display component, the particular candidate string. - View Dependent Claims (11, 12, 13, 14)
-
-
15. A non-transitory computer-readable storage medium storing instructions that, when executed, cause one or more processors of a computing device to:
-
output, for display at a display device that is operatively coupled to the computing device, a graphical keyboard comprising a plurality of keys; receive an indication of a gesture detected at a presence-sensitive input device that is operatively coupled to the computing device; detect data indicative of one or more user states determined to affect gesture accuracy; determine, for respective user states of the one or more user states, respective models that provide at least one value indicating a degree, in a range of degrees, to which the respective user state affects gesture accuracy; select, based at least in part on the indication of the gesture and the data indicative of the one or more user states, a particular candidate string, wherein the instructions that cause the one or more processors to select the particular candidate string comprise instructions that cause the one or more processors to; determine, based on the gesture, a plurality of candidate character strings, wherein each of the plurality of candidate character strings is associated with at least one of a respective physical cost value from a spatial model and a respective lexical cost value from a language model; adjust, for a particular candidate character string of the plurality of candidate character strings and based at least in part on the one or more user states, at least one of a physical cost value associated with the particular candidate character string and a lexical cost value associated with the particular candidate character string by at least adjusting a relative weight based on the respective models for each of the one or more user states; and select, based at least in part on the adjusting, the particular candidate character string from the plurality of candidate character strings; and output, for display at the display device, the particular candidate string. - View Dependent Claims (16)
-
Specification