Method to detect and assist user intentions with real time visual feedback based on interaction language constraints and pattern recognition of sensory features
First Claim
1. A language model back-off system for controlling user interaction with a user interface employing plural language models, selected from the group consisting of N-words, N-characters and combinations thereof, comprising:
- a navigation constraint module employing plural probabilistic language models, including a first language model and a second language model that provides a lower level of constraint than the first language model, to constrain navigation of selectable user interface input components each corresponding to a corresponding one of characters, so as to constrain the characters that a user is allowed to input,a user input interpretation module receiving user input and initially interpreting the user input using a level of constraint favoring the first language model to determine if a selection of a next character to be input is made of one or more user interface input components,wherein said user input interpretation module, if the selection is not made, determines whether conditions are met for backing off the language models employed to constrain navigation of the user interface input components; and
a language model back-off module backing off the language models to change the level of constraint by favoring the second language model over the first language model if the conditions are met, wherein the user input interpretation module and the language model back-off module are implemented by controller.
6 Assignments
0 Petitions
Accused Products
Abstract
A language model back-off system can be used with a user interface employing one or more language models to constrain navigation of selectable user interface input components. A user input interpretation module receives user input and interprets the user input to determine if a selection is made of one or more user interface input components. If a selection is not made, the user input interpretation module determines whether conditions are met for backing off one or more language models employed to constrain navigation of the user interface input components. If the conditions are met, a language model back-off module backs off the one or more language models.
12 Citations
22 Claims
-
1. A language model back-off system for controlling user interaction with a user interface employing plural language models, selected from the group consisting of N-words, N-characters and combinations thereof, comprising:
-
a navigation constraint module employing plural probabilistic language models, including a first language model and a second language model that provides a lower level of constraint than the first language model, to constrain navigation of selectable user interface input components each corresponding to a corresponding one of characters, so as to constrain the characters that a user is allowed to input, a user input interpretation module receiving user input and initially interpreting the user input using a level of constraint favoring the first language model to determine if a selection of a next character to be input is made of one or more user interface input components, wherein said user input interpretation module, if the selection is not made, determines whether conditions are met for backing off the language models employed to constrain navigation of the user interface input components; and a language model back-off module backing off the language models to change the level of constraint by favoring the second language model over the first language model if the conditions are met, wherein the user input interpretation module and the language model back-off module are implemented by controller. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A language model back-off method for controlling a user interface employing plural language models selected from the group consisting of N-words, N-characters and combinations thereof, comprising:
-
using a plurality of probabilistic language models including a first language model and a second language model that provides a lower level of constraint than the first language model to constrain navigation of selectable user interface components; using said first language model to constrain navigation of selectable user interface input components each corresponding to a corresponding one of characters, so as to constrain the characters that a user is allowed to input; receiving user input and interpreting the user input to determine if a selection of a next character to be input is made of one or more user interface input components; if the selection is not made, determining whether conditions are met for backing off the language models employed to constrain navigation of the user interface input components; and if the conditions are met, backing off the plural language models to a lower level of constraint by favoring the second language model over the first language model. - View Dependent Claims (13, 14, 15, 16, 17, 18, 19, 20, 21)
-
-
22. A language model back-off system for use with a user interface employing plural language models, selected from the group consisting of N-words, N-characters and combinations thereof and are employed to constrain navigation of selectable user interface input components each corresponding to a corresponding one of characters, so as to constrain the characters that a user is allowed to input, the language model back-off system comprising:
-
a user interface displaying the user interface input components with a focus indicator; a navigation constraint module having plural probabilistic language models including a first language model and a second language model that provides a lower level of constraint that the first language model, and operative based on previous selections to initially constrain navigation of the selectable user interface input components using the first language model; a user input interpretation module receiving user input and interpreting the user input to determine if a selection of a next character to be input is made of the plural user interface input components, wherein said user input interpretation module, if the selection is not made, determines whether conditions are met for backing off the plural language models based on;
(a) a time since a previous selection; and
(b) a probabilistic model taking into account a feature set of sensed user interaction with an input device of the user interface; anda language model back-off module backing off the plural probabilistic language models to change the level of constraint by favoring the second language model if the conditions are met and by adjusting weights of probabilities that are computed using the plural probabilistic language models to ensure that probabilities computed by employing a more highly constrained language model are given less weight while probabilities computed by employing a less highly constrained language model are given more weight.
-
Specification