Decoding imprecise gestures for gesture-keyboards

摘要

In one example, a method includes outputting, by a computing device and for display, a graphical keyboard comprising a plurality of keys. The method may also include receiving, by the computing device, an indication of a gesture detected at a presence-sensitive input device. The method may also include determining, by the computing device and based on a plurality of features associated with the gesture, a degree of precision of the gesture. The method may also include modifying, by the computing device and based at least in part on the degree of precision, a probability that the gesture indicates at least one key of the plurality of keys. The method may also include outputting, by the computing device and for display, a candidate word that is based at least in part on the probability that the gesture indicates at least one key of the plurality of keys.

主权项

1. A method comprising:
outputting, by a computing device and for display, 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 that traverses a first key and a second key that are each included in the plurality of keys; determining, by the computing device, a first distance of a portion of the gesture between the first key and the second key, and a second distance between the first key and the second key, wherein the first distance is a distance traversed by the gesture between first key and the second key, wherein the second distance is a distance of a straight-line path between the first key and the second key; comparing, by the computing device, the first distance and the second distance to determine a value that represents a degree of precision of the gesture; determining, by the computing device and based at least in part on comparing a particular location of the gesture with a spatial model associated with a particular key of the plurality of keys, a spatial model probability that indicates a probability that the particular key is selected by a user of the computing device; responsive to determining that the value that represents the degree of precision of the gesture satisfies a threshold degree of degree of precision, modifying, by the computing device and based at least in part on the value that represents the degree of precision, the spatial model probability that the gesture indicates the particular key; and outputting, by the computing device and for display, a candidate word that is based at least in part on the probability that the gesture indicates the the particular key of the plurality of keys.