Disambiguating system for disambiguating ambiguous input sequences by displaying objects associated with the generated input sequences in the order of decreasing frequency of use

• US 5,953,541 A
• Filed: 01/24/1997
• Issued: 09/14/1999
• Est. Priority Date: 01/24/1997
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Tegic Communications, Inc. (Microsoft Corporation)
• Inventors: Kushler, Clifford A., King, Martin T., Grover, Dale L., Grunbock, Cheryl A.
• Primary Examiner(s): Lee, Thomas C.
• Assistant Examiner(s): Ton, David
• Application Number:
  US08/792,969
• Time in Patent Office: 963 Days
• Field of Search: 400/110, 400/484, 379/93.18, 704/4, 395/887, 395/893
• US Class Current: 710/67
• CPC Class Codes: G06F 3/0234 using switches operable in different directions
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/0238 Programmable keyboards key guide holders G06F3/0224

Abstract

A reduced keyboard disambiguating system. The keyboard has twelve keys, nine of them labeled with numerous letters and other symbols, and those nine plus one more are labeled each with one of the ten digits. Textual entry keystrokes are ambiguous. The user strikes a delimiting "Select" key at the end of each word, delimiting a keystroke sequence that could match any of many words with the same number of letters. The keystroke sequence is processed with a complete vocabulary, and words which match the sequence of keystrokes are presented to the user in order of decreasing frequency of use. In addition, stems of longer words whose initial letters match the sequence of keystrokes are also presented to the user in order of decreasing frequency of use. The first word in the presented list is automatically selected by the input of the first character in the next word. The letters are assigned to the keys in a non-sequential order which reduces chances of ambiguities. The "Select" key is pressed to select the desired word other than the first word, and spacing between words and punctuation is automatically computed. For words which are not in the vocabulary, a simultaneous unambiguous interpretation of each keystroke is performed to specify each letter of a desired word. The system simultaneously interprets all keystroke sequences as both ambiguous and unambiguous keystrokes. The user selects the desired interpretation. The system also presents to the user the number which is represented by the sequence of keystrokes for possible selection by the user.

Claims

1. A disambiguating system for disambiguating ambiguous input sequences entered by a user, the disambiguating system comprising:

(a) a user input device having;

(i) a plurality of inputs, each of the plurality of inputs associated with a plurality of characters, an input sequence being generated each time an input is selected by manipulating the user input device, wherein the generated input sequence corresponds to the sequence of inputs that have been selected, wherein the generated input sequence has a textual interpretation that is ambiguous due to the plurality of characters associated with each input; and

(ii) at least one unambiguous input for generating an unambiguous output, wherein an input sequence is terminated when the user manipulates the user input device to an unambiguous input;

(b) a memory containing a plurality of objects, each of the plurality of objects associated with an input sequence and a frequency of use;

(c) a display to depict system output to the user; and

(d) a processor coupled to the user input device, memory and display, said processor comprising;

(i) an identifying component for identifying from the plurality of objects in the memory at least one object associated with each generated input sequence and having the highest frequency of use and identifying any additional objects associated with each generated input sequence;

(ii) an output component for displaying on the display at least one identified object associated with each generated input sequence as a textual interpretation of the generated input sequence, and displaying any additional identified objects associated with each input sequence as additional textual interpretations of the generated input sequence in order of decreasing frequency of use; and

(iii) a selection component for selecting the identified object with the highest frequency of use for entry into a text entry display location upon detecting the manipulation of the user input device to an unambiguous input, and selecting the identified objects having a lower frequency of use for entry into the text entry display location upon detecting the manipulation of the user input device to an unambiguous input a plurality of times, each manipulation of the user input device to the unambiguous input selecting an object having a next lower frequency of use from the identified objects.

2. The disambiguating system of claim 1, wherein the identified object having the highest frequency of use is displayed as the textual interpretation of the generated input sequence in a first distinguishing manner on the display prior to detecting the manipulation of the user input device to an unambiguous input, and in a second distinguishing manner on the display upon detecting the manipulation of the user input device to an unambiguous input, wherein the first or second distinguishing manner of display of the objects is removed when the generation of a next input sequence having an ambiguous textual interpretation begins or upon selecting an unambiguous input.

3. The disambiguating system of claim 2, wherein the identified objects associated with the generated input sequence are displayed in a selection list on the display, and wherein the object selected for entry into the text entry display location by manipulation of the user input device to the unambiguous input is also displayed in the selection list in said second distinguishing manner.

4. The disambiguating system of claim 1, wherein the identified object associated with the highest frequency of use is displayed as the textual interpretation of the generated input sequence at an insertion point where text is output to the text entry display location.

5. The disambiguating system of claim 4, wherein the identified objects associated with the generated input sequence are displayed in a selection list on the display upon detecting the manipulation of the user input device to the unambiguous input.

6. The disambiguating system of claim 5, wherein no more than a predetermined maximum number of the identified objects associated with the generated input sequence are displayed in the selection list.

7. The disambiguating system of claim 6, wherein the identified objects associated with the generated input sequence that are in excess of the predetermined maximum number that can be displayed in the selection list are displayed in the selection list upon detecting additional manipulations of the user input device to the unambiguous input.

8. The disambiguating system of claim 1, wherein each of the plurality of objects contained in the memory correspond to a sequence of Latin characters known as Romaji, wherein the sequence of Latin characters corresponds to a phonetic kana spelling, and wherein the phonetic kana spelling is associated with one or more Japanese words.

9. The disambiguating system of claim 8, wherein the frequency of use associated with each object in memory is equal to the sum of the frequencies of use of the Japanese words associated with an object contained in memory.

10. The disambiguating system of claim 9, wherein after each generated input sequence, the phonetic kana spelling, which corresponds to the object in the memory associated with the input sequence and having a highest frequency of use, is displayed.

11. The disambiguating system of claim 9, wherein after each generated input sequence, the phonetic kana spellings, which correspond to one or more objects in the memory associated with the input sequence, are displayed in decreasing order of frequency.

12. The disambiguating system of claim 9, wherein the processor automatically selects an object having a highest frequency of use as the phonetic kana spelling associated with the generated input sequence upon detecting the manipulation of the user input device to the unambiguous input, causing the display to display one or more textual interpretations associated with the selected object, said one or more textual interpretations being one or more of Latin characters, hiragana, katakana, kanji or kanji plus furigana, one or more of said textual interpretations associated with one or more of the plurality of inputs, wherein selection of the corresponding input selects the associated textual interpretation for output as a textual interpretation of the generated input sequence.

13. The disambiguating system of claim 12, wherein the user may select an object having a lower frequency of use as the phonetic kana spelling of the generated input sequence by manipulating the user input device to the unambiguous input a plurality of times, each manipulation of the user input device to the unambiguous input selecting an object having a next lower frequency of use, and causing the display to display said textual interpretations associated with said selected object.

14. The disambiguating system of claim 13, wherein the user may select an object having a lower frequency of use as the phonetic kana spelling of the generated input sequence by manipulating the user input device to the unambiguous input a plurality of times, each manipulation of the user input device to the unambiguous input selecting an object having a next lower frequency of use, and causing the display to display said selected phonetic kana spelling as the phonetic kana spelling associated with the generated input sequence.

15. The disambiguating system of claim 14, wherein the processor, upon detecting the manipulation of the user input device to a second unambiguous input, selects a textual interpretation associated with the selected phonetic kana spelling object and having a highest frequency of use as the textual interpretation of the selected phonetic kana spelling object, causing the display to display said textual interpretation, wherein said textual interpretation comprises one or more of Latin characters, hiragana, katakana, kanji or kanji plus furigana.

16. The disambiguating system of claim 15, wherein the user may select a textual interpretation having a lower frequency of use as the textual interpretation of the selected phonetic kana spelling object by manipulating the user input device to the second unambiguous input a plurality of times, each manipulation of the user input device to the second unambiguous input selecting a textual interpretation having a next lower frequency of use, and causing the display to display said textual interpretation as the textual interpretation of the selected phonetic kana spelling object.

17. The disambiguating system of claim 13, wherein said textual interpretations are displayed in order of decreasing frequency of use.

18. The disambiguating system of claim 17, wherein when there are more of said textual interpretations than of said associated plurality of inputs, said additional textual interpretations are displayed upon detecting manipulation of the user input device to a designated input.

19. The disambiguating system of claim 17, wherein when there are fewer of said textual interpretations than of said associated plurality of inputs, additional textual interpretations are displayed associated with other less frequent phonetic kana spellings of the generated input sequence.

20. The disambiguating system of claim 1, wherein the memory includes objects that are associated with input sequences that are shorter than the number of characters in the textual interpretation associated with the object.

21. The disambiguating system of claim 1, wherein the user input device is a TV remote control with a reduced keyboard.

22. The disambiguating system of claim 1, wherein the user input device is an eyegaze input system which determines which of a plurality of inputs is selected by monitoring the position and/or orientation of one or both of the user'"'"'s eyes.

23. The disambiguating system of claim 1, wherein the user input device is a wrist watch with a reduced keyboard.

24. The disambiguating system of claim 1, wherein the user input device is a keyboard constructed of mechanical keys which can be activated in a plurality of distinct ways, where each distinct activation corresponds to a distinct input.

25. The disambiguating system of claim 1, wherein the user input device is implemented as a simple grid outline pattern on a touch screen which outline indicates regions of the screen corresponding to the various inputs, and which outline appears super-imposed on the display.

26. The disambiguating system of claim 1, wherein the user input device is implemented as a touchscreen on which the user performs a plurality of simple touchscreen gestures, wherein the touchscreen is contacted and the point of contact is moved in a distinct fashion, wherein each distinct gesture corresponds to an input.

27. The disambiguating system of claim 1, wherein objects in the memory which include one or more characters with special diacritic marks are associated with input sequences composed of the input associated with the corresponding characters without diacritic marks.