String prediction
In a mobile device, the text entered by users is analyzed to determine a set of responses commonly entered by users into text applications such as SMS applications in response to received messages. This set of responses is used to provide suggested responses to a user for a currently received message in a soft input panel based on the text of the currently received message. The suggested responses are provided before any characters are provided by the user. After the user provides one or more characters, the suggested responses in the soft input panel are updated. The number of suggested responses displayed to the user in the soft input panel is limited to a total confidence value to reduce user distraction and to allow for easier selection. An undo feature for inadvertent selections of suggested responses is also provided.
1. A method comprising:
receiving a string from an application at a first computing device;
generating a first plurality of string predictions based on the received string by the first computing device, wherein each string prediction comprises a string and a confidence value and each string comprises a phrase that has been previously entered in response to the received string;
providing one or more of the strings of the first plurality of string predictions according to the associated confidence values by the first computing device;
receiving an indication of selection of one of the provided one or more strings by the first computing device; and
in response to the indication of selection, providing the selected string as an input to the application by the first computing device.
2. The method of claim 1 , wherein the first plurality of strings predictions is generated before a character is received from a user of the first computing device.
3. The method of claim 1 , wherein generating the first plurality of string predictions based on the received string comprises generating the first plurality of string predictions based on the received string and at least one prediction model.
4. The method of claim 3 , wherein the at least one prediction model is one or more of a local prediction model or a global prediction model.
5. The method of claim 1 , wherein the string is received from the application at a second computing device.
6. The method of claim 1 , wherein the one or more strings of the first plurality of string predictions comprise sentences.
7. The method of claim 1 , further comprising:
receiving a character;
in response to the received character, generating a second plurality of string predictions based on the received string and the received character; and
providing one or more of the strings of the second plurality of string predictions.
8. The method of claim 1 , further comprising:
storing the provided one or more strings of the first plurality of strings;
receiving an indication to undo the selected string;
in response to the indication to undo, retrieving the stored one or more strings from the first plurality of strings; and
providing the retrieved one or more strings.
9. The method of claim 8 , wherein the indication to undo comprises the selection of a user interface element or the selection of the provided selected string.
10. The method of claim 8 , wherein the provided one or more strings are stored in a buffer.
11. The method of claim 1 , wherein providing one or more of the strings of the first plurality of string predictions according to the associated confidence values comprises displaying one or more of the strings of the first plurality of string predictions according to the associated confidence values.
12. The method of claim 11 , wherein displaying one or more of the strings of the first plurality of string predictions according to the associated confidence values comprises:
retrieving a threshold confidence value;
selecting the smallest subset of strings from the first plurality of strings whose associated confidence values has a sum that is greater than the threshold confidence value; and
displaying the strings of the selected subset of strings.