US20150161245A1

US20150161245A1 - Explicit character filtering of ambiguous text entry

Info

Publication number: US20150161245A1
Application number: US14/599,401
Authority: US
Inventors: Ethan Robert Bradford; Keith Charles Hullfish; David Kay; Pim van Meurs; Michael R. Longé
Original assignee: Nuance Communications Inc
Current assignee: Nuance Communications Inc
Priority date: 1999-12-03
Filing date: 2015-01-16
Publication date: 2015-06-11
Also published as: KR20050013222A; JP2009116900A; EP1514357A1; US20130194191A1; EP1514357A4; WO2004001979A1; KR100693697B1; US20100174529A1; US8782568B2; US20020196163A1; EP1514357B1; US8990738B2; CN1618173B; US7712053B2; US20140292663A1; CA2485221A1; US20140292664A1; MXPA04012854A; US8381137B2; JP5501625B2

Abstract

The present invention relates to a method and apparatus for explicit filtering in ambiguous text entry. The invention provides embodiments including various explicit text entry methodologies, such as 2-key and long pressing. The invention also provides means for matching words in a database using build around methodology, stem locking methodology, word completion methodology, and n-gram searches.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

This application is a continuation of U.S. patent application Ser. No. 14/304,842, filed Jun. 13, 2014, which is a continuation of U.S. patent application Ser. No. 13/748,501, filed Jan. 23, 2013, now U.S. Pat. No. 8,782,568, issued Jul. 15, 2014, which is a continuation of U.S. patent application Ser. No. 12/725,334, filed Mar. 16, 2010, now U.S. Pat. No. 8,381,137, issued Feb. 19, 2013, which is a continuation of U.S. patent application Ser. No. 10/176,933, filed 20 Jun. 2002, now U.S. Pat. No. 7,712,053, issued May 4, 2010, which is a continuation-in-part of U.S. patent application Ser. No. 09/454,406, filed Dec. 3, 1999, now U.S. Pat. No. 6,646,573, issued Nov. 11, 2003, each of which is incorporated herein in its entirety by this reference thereto.

BACKGROUND OF THE INVENTION

1. Technical Field
The invention relates to text input technology. More specifically, the invention relates to text entry solutions to wireless communication devices with limited keypads.
2. Description of the Prior Art
For many years, portable computers have been getting smaller and smaller. The principal size-limiting component in the effort to produce a smaller portable computer has been the keyboard. If standard typewriter-size keys are used, the portable computer must be at least as large as the keyboard. Miniature keyboards have been used on portable computers, but the miniature keyboard keys have been found to be too small to be easily or quickly manipulated by a user. Incorporating a full-size keyboard in a portable computer also hinders true portable use of the computer. Most portable computers cannot be operated without placing the computer on a flat work surface to allow the user to type with both hands. A user cannot easily use a portable computer while standing or moving.
In the latest generation of small portable computers, called Personal Digital Assistants (PDAs), companies have attempted to address this problem by incorporating handwriting recognition software in the PDA. A user may directly enter text by writing on a touch-sensitive panel or screen. This handwritten text is then converted by the recognition software into digital data. Unfortunately, in addition to the fact that printing or writing with a pen is in general slower than typing, the accuracy and speed of the handwriting recognition software has to date been less than satisfactory.
Presently, a tremendous growth in the wireless industry has spawned reliable, convenient, and very popular mobile communications devices available to the average consumer, such as cell phones, two-way pagers, PDAs, etc. These handheld wireless communications and computing devices requiring text input are becoming smaller still. Recent advances in two-way paging, cellular telephones, and other portable wireless technologies have led to a demand for small and portable two-way messaging systems, and especially for systems which can both send and receive electronic mail (“e-mail”). Some wireless communications device manufacturers also desire to provide to consumers devices with which the consumer can operate with the same hand that is holding the device.
Disambiguation Background. Prior development work has considered use of a keyboard that has a reduced number of keys. As suggested by the keypad layout of a touch-tone telephone, many of the reduced keyboards have used a 3-by-4 array of keys. Each key in the array of keys contains multiple characters. There is therefore ambiguity as a user enters a sequence of keys, since each keystroke may indicate one of several letters. Several approaches have been suggested for resolving the ambiguity of the keystroke sequence, referred to as disambiguation.
One suggested approach for unambiguously specifying characters entered on a reduced keyboard requires the user to enter, on average, two or more keystrokes to specify each letter. The keystrokes may be entered either simultaneously (chording) or in sequence (multiple-stroke specification). Neither chording nor multiple-stroke specification has produced a keyboard having adequate simplicity and efficiency of use. Multiple-stroke specification is inefficient, and chording is complicated to learn and use.
Other suggested approaches for determining the correct character sequence that corresponds to an ambiguous keystroke sequence are summarized in the article “Probabilistic Character Disambiguation for Reduced Keyboards Using Small Text Samples,” published in the Journal of the International Society for Augmentative and Alternative Communication by John L. Arnott and Muhammad Y. Javad (hereinafter the “Arnott article”). The Arnott article notes that the majority of disambiguation approaches employ known statistics of character sequences in the relevant language to resolve character ambiguity in a given context.
Another suggested approach based on word-level disambiguation is disclosed in a textbook entitled Principles of Computer Speech, authored by I. H. Witten, and published by Academic Press in 1982 (hereinafter the “Witten approach”). Witten discusses a system for reducing ambiguity from text entered using a telephone touch pad. Witten recognizes that for approximately 92% of the words in a 24,500 word dictionary, no ambiguity will arise when comparing the keystroke sequence with the dictionary. When ambiguities do arise, however, Witten notes that they must be resolved interactively by the system presenting the ambiguity to the user and asking the user to make a selection between the number of ambiguous entries. A user must therefore respond to the system's prediction at the end of each word. Such a response slows the efficiency of the system and increases the number of keystrokes required to enter a given segment of text.
H. A. Gutowitz, Touch-Typable Devices Based on Ambiguous Codes and Methods to Design Such Devices, WO 00/35091 (Jun. 15, 2000) discloses that the design of typable devices, and, in particular, touch-type devices embodying ambiguous codes presents numerous ergonomical problems and proposes some solutions for such problems. Gutowitz teaches methods for the selection of ambiguous codes from the classes of strongly-touch-typable ambiguous codes and substantially optimal ambiguous codes for touch-typable devices such as computers, PDA's, and the like, and other information appliances, given design constraints, such as the size, shape and computational capacity of the device, the typical uses of the device, and conventional constraints such as alphabetic ordering or Qwerty ordering.
Eatoni Ergonomics Inc. provides a system called WordWise, (Copyright 2001 Eatoni Ergonomics Inc.), adapted from a regular keyboard, and where a capital letter is typed on a regular keyboard, and an auxiliary key, such as the shift key, is held down while the key with the intended letter is pressed. The key idea behind WordWise is to choose one letter from each of the groups of letters on each of the keys on the telephone keypad. Such chosen letters are typed by holding down an auxiliary key while pressing the key with the intended letter. WordWise does not use a vocabulary database/dictionary to search for words to resolve ambiguous, unambiguous, or a combination thereof entries.
Zi Corporation teaches a predictive text method, eZiText^(R)(2002 Zi Corporation), but does not teach nor anywhere suggest explicit text filtering in ambiguous mode, nor in combination with 2-key explicit entry, stem-locking, or n-gram searches.
A Need for Improvements to Current Disambiguation Methodologies.
Disambiguating an ambiguous keystroke sequence continues to be a challenging problem. A specific challenge facing disambiguation is providing sufficient feedback to the user about the keystrokes being input. With an ordinary typewriter or word processor, each keystroke represents a unique character which can be displayed to the user as soon as it is entered. But with word-level disambiguation, for example, this is often not possible, because each entry represents multiple characters, and any sequence of entries may match multiple objects, such as, words or word stems, for example. Such ambiguity is especially a problem when, for example, the user makes a spelling or entry error and the user is not certain of such error until the complete sequence is entered and the desired result is not presented. In another example, previous systems utilizing word-level disambiguation fail to provide any feedback until a predetermined selection, such as a specific key selection, is made that is recognizable by the system as a termination selection, e.g. the space key.
Moreover, some alphabets, such as Thai and Arabic, contain more letters than the alphabet for English, which leads to even greater ambiguity on a reduced number of keys. Efficient input of these languages demands a mechanism for reducing that ambiguity when needed.
Therefore, it would be advantageous to provide a disambiguating system which reduces the apparent ambiguity on the display during entry and improves the user's ability to detect and correct spelling and/or entry errors.
It would also be advantageous to provide a disambiguating system which reduces ambiguity and increases efficiency by providing explicit filtering capabilities such that a list of candidate words, word stems, sequence of symbols, and the like, is narrowed, and the user can subsequently be offered a word completion or sequence completion quicker. More specifically, it would be advantageous to allow locking in a current state of interpretation of a part of or all of previously entered characters including, but not limited to an object and/or word stems, and explicitly entered characters, thereby preventing reinterpretation of previous entries.
It would also be advantageous to build around explicitly entered characters as anchors, for the end of or beginning of new objects, words, or word stems.
It would also be advantageous to offer reasonable guesses for extending objects or words by n-gram analysis of preceding explicitly entered characters.
It would also be advantageous to reduce ambiguity and increase efficiency during the process of disambiguating a linguistic object, such as a word or word stem, for example, by preventing reinterpretation of previous entries.
It would also be advantageous to recognize common delimiters entered ambiguously or explicitly as suggesting a point connecting two separate sets of characters to suggest where the interpretation of keystrokes could be restarted.

SUMMARY OF THE INVENTION

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a hardware block diagram of the explicit character filtering system according of the invention;

FIG. 2 is a picture of a wireless handheld device showing each letter of the English alphabet associated with a key according to the invention;

FIG. 3 is an example chart of European letters and some special symbols shown on the 0-9 keys and their respective Shift keys according to the invention;

FIG. 4 is a sample screenshot of one 2-key matrix input method according to the invention;

FIG. 5 is a flow chart of 2-key explicit entry for the explicit character filtering in ambiguous text entry system of FIG. 1;

FIG. 6 is a flow chart for explicitly filtering in ambiguous mode according to a preferred embodiment of the invention;

FIG. 7 is a flow chart of a method for generating words not stored in the database according to the invention;

FIG. 8 shows an example of explicit entry by long-pressing on a key according to the invention; and

FIG. 9 is a flow chart depicting a build around example according to the invention.

DETAILED DESCRIPTION OF THE INVENTION

The present invention relates to a method and apparatus for explicit filtering in ambiguous text entry. The invention provides embodiments including various explicit text entry methodologies, such as 2-key and long pressing. The invention also provides means for matching words in a database using build around methodology, stem locking methodology, word completion methodology, and n-gram searches.
More specifically, the present invention relates to a method and apparatus for explicit filtering in an ambiguous text entry mode, for extending and interpreting objects, words, word stems, and the like, and for stem-locking. One specific embodiment of explicit filtering for reducing ambiguity uses a variety of explicit entry means, including a 2-key explicit entry feature, wherein a key depression in combination with a matrix display are used. An extending and interpreting methodology is provided wherein complex phrases are allowed to be typed in. Predetermined sets of characters are “built around” as anchors for the end or beginning of new words or word stems. Reasonable guesses are offered for extending words by “n-gram” analysis of preceding explicit letters. Specifically, three specific embodiments using stem-locking are provided, wherein the first embodiment uses a combination of the n letters of a desired object, such as a word, and a next key. The second embodiment locks in the stem portion of the object and resolves the unlocked portion of the object. The third embodiment uses n-gram searches.
A block diagram of a preferred embodiment of the reduced keyboard disambiguating system hardware is provided in FIG. 1. The keyboard 54 and the display 53 are coupled to a processor 100 through appropriate interfacing circuitry. Optionally, a speaker 102 is also coupled to the processor. The processor 100 receives input from the keyboard, and manages all output to the display and speaker. Processor 100 is coupled to a memory 104. The memory includes a combination of temporary storage media, such as random access memory (RAM), and permanent storage media, such as read-only memory (ROM), floppy disks, hard disks, or CD-ROMs. Memory 104 contains all software routines to govern system operation. Preferably, the memory contains an operating system 106, disambiguating software 108, and associated explicit character filtering in ambiguous text entry software and/or extending and interpreting software 110 that is discussed in additional detail below. The memory also includes a vocabulary database 30. Optionally, the memory may contain one or more application programs 112, 114. Examples of application programs include word processors, software dictionaries, and foreign language translators. Speech synthesis software may also be provided as an application program, allowing the reduced keyboard disambiguating system to function as a communication aid. Therefore, the output, in this case, might be vocally output from the speaker.
It should be appreciated and understood by one of ordinary skill in the art that the discussion applies to symbols and sequences of symbols, which, when combined make an object or part of an object. A typical example of a symbol is a character in any language, such as a letter, digit, punctuation mark, or any other symbol from a language. A typical example of an object or part of an object is a word or part of a word. However, the discussion herein equally applies to Japanese kana and Korean jamos. Also, it should be noted that the objects don't have to be linguistic, as the claimed disambiguating system herein can be used to look up icons, phone numbers, or inventory records, as long as a type of symbolic string representation is present. Therefore, it should be appreciated that use of the terms such as letter, word, word stem, and the like are not limited to only those applications, and are used to facilitate ease of reading and understanding the discussion herein.
Explicit Entry
One preferred embodiment of generating an explicit character for the purpose of filtering word choices according to the invention provides a 2-key explicit entry feature. In many languages, such as English, all the letters associated with a key are printed on the key, such as depicted in FIG. 2, where FIG. 2 is a picture of an example wireless handheld device showing each letter of the English alphabet associated with a key according to the invention.
However, other languages, such as French, include many more letters than can visually fit on a key, such as the cell phone key. FIG. 3 is an example chart of European letters and some special symbols shown on the 0-9 keys and their respective Shift keys. For example, if a user presses the 5 key, then a matrix display with the alphanumeric characters j, k, I, and 5 appear. FIG. 4 is a sample screenshot of one 2-key matrix input method according to the invention. After the first key has been pressed, the matrix of choices is displayed on the device panel. It should be appreciated that other labels printed on keys are possible, such as, for example, each key including a subset of predetermined sets of associated letters, such as displaying the first and last character of predetermined sets of associated letters.
FIG. 5 is a flow chart of 2-key explicit entry for the explicit character filtering in ambiguous text entry system of FIG. 1. According to a preferred embodiment of the invention, for a user to explicitly select one of many letters assigned to a key, as in the case of the French language, the user selects, such as by depression, the associated key (5000). The selection, e.g. depression, of the desired key causes the system to presents a second set of letters, such as in matrix form, that corresponds to the selected key (5100). Each block in the matrix includes a letter from the set of letters associated with the just selected/depressed key. FIG. 4 shows an example of what is displayed as a result of depressing the 1 key. All that is required at this point is for the user to select the key number of the matrix block that includes the desired character (5200). This explicit selection process only requires at maximum 2 key selections/depressions for the selection of a letter.
It should be readily apparent to one of ordinary skill in the art that the 2-key explicit entry method for the purpose of filtering can be extended to any other language. It should also be apparent to one of ordinary skill in the art that alternate configurations are possible, such as, for example, a scrolling list.
According to an alternate configuration, the user selects a key by way of a long-press to display and cycle through the character sequence on that key. As shown in FIG. 8, some or all of the characters may scroll past in a preview window as long as the key is being pressed. When the key is released, the last highlighted character is accepted.
In yet another configuration, after the character sequence is presented by way of the long-press on the key, the character appears or is highlighted each additional time the key is pressed. The presentation of each explicit character may end when a sufficient time elapses between one key press and the next or when a different key is pressed.
In yet another configuration, after the character sequence is presented by way of the long-press on the key, the character appears or is highlighted each additional time a navigation key is pressed, where a navigation key is, for example, an arrow key or a scrolling wheel.
Following is a list of other explicit entry means for filtering. It should be appreciated that the list is meant by example only, and is not exhaustive: long pressing on a key to enter a number/digit explicitly;
changing to a numbers mode and pressing a key to enter a number/digit explicitly (and then returning to ambiguous entry mode for filtering);
changing to a multi-tap mode and pressing a key repeatedly to enter a character explicitly (and then returning to ambiguous entry mode for filtering); interpreting ambiguous mode key presses as an explicit character, either by grouping each pair of key presses as a 2-key explicit entry, or by grouping repeated presses of the same key as a multi-tap entry;
using multi-switch keys, such as a 5-way rocker, which permits ambiguous entry on a simple press and an explicit character entry on a different kind of press; and
by “chording,” which means by pressing more than one key simultaneously, with a primary key indicating an ambiguous set of characters and a secondary key indicating which character in the set to select (e.g., on a video game controller).
Another means of explicit entry for filtering is when any character assigned to a key is offered to the user through a secondary means, e.g., displayed on the label of a programmable key, or “softkey”, which if chosen would be entered explicitly. The softkey mechanism allows correction of the last keystroke entered, e.g., if the user is extending a word with additional characters or wishes to correct the displayed interpretation before the entire word is entered. The additional character offered would be based on an analysis of the most likely character associated with the preceding keystroke, or based on the words in the current word candidate list. Assuming the most likely character was already displayed in the ambiguous word choice, then the second most likely character would be offered. For instance, if the user wants to type “ram” and enters the key sequence 726, the word “ran” appears. The most likely letter for that position in the word candidate list associated with 726 is “m”, then “m” could be offered on the softkey. When the user presses the softkey, the “m” replaces the “n” in the word “ran”.
Explicit Character Filtering in Ambiguous Mode
Explicit character filtering in ambiguous mode is when a character is explicitly entered during entry of a sequence of ambiguous entries. One embodiment of explicit entry already discussed is the 2-key explicit entry method using a matrix as described above. According to another preferred embodiment of the invention, explicit entry of a character is accomplished by a long depression of the associated key. When one or more characters in a sequence of characters is explicitly entered, only stored words with that explicitly selected character(s) in the corresponding position(s) are retrieved.
One way of retrieving the desired word according to one embodiment of the invention is when an explicit character is entered in ambiguous entry mode, then the disambiguating filtering system continues to match database words against the ambiguous and explicit letters as long as possible, rather than accepting the default word upon the first explicit letter. If there is no match, the last ambiguous word selected is accepted and a new letter is appended to it.
As an example, suppose a user wants to enter the word “home” in English T9. The user long presses the 6 key in the 3^rdposition to explicitly select “m,” resulting in only “home,” and, in addition, word stems “imme” and “gome” after 4 keystrokes.
Another example is using a mixed alphanumeric word like “cu2night”, which could be stored in a database. If the user long presses on the 2 key, then explicitly enters a “2,” words such as “cub” are thus filtered out from the word candidate list.
Explicit filtering is another way to quickly offer word completions. If “cu2night” was in a database, and “cu” was entered ambiguously followed by “2” explicitly, all ambiguous interpretations of the keystroke sequence “282” will be filtered out, leaving “cu2night” as a more likely choice to be offered through word completion.
FIG. 6 is a flow chart for explicitly filtering in ambiguous mode according to a preferred embodiment of the invention. A character is desired and its associated key is entered either ambiguously or explicitly (6000). The desired word is then interpreted based on the sequence of ambiguously selected keys (i.e. their associated characters) and the explicitly selected characters. The database is searched for words with the characters associated with ambiguously selected entries, e.g. keys, and with the explicitly entered characters, in their respective corresponding positions (6100). The searched words are then presented or displayed in a predetermined prioritized order (6200), such as a most frequently used order. If the desired word is among the set of presented searched words (6300), then the desired word is chosen (6400) and the process ends. Otherwise, the process is not over and steps are repeated from selecting a desired key (6000).
Build Around
In another aspect of the disambiguating filtering system, words from the database can be “built around” explicitly or ambiguously entered characters, or, additionally characters from a predetermined set of characters. According to one interpretation, the matching words, if any, include the explicit character for a particular sequence. However, additional interpretations of the sequence may include: one or more words that match the ambiguous keys that precede and/or end with the explicit character; one or more matching words that begin with the explicit character if any; and one or more words that match the ambiguous keys that follow the explicit character. For example, if the key sequence for “gifts4less” is entered, with the digit “4” entered explicitly, the words “gifts” matches the ambiguous key sequence preceding the explicit character and “less” matches the key sequence following it, even if “gifts4less”, “gifts4”, and “4less” are not found in the database. Similarly, “mobile.com” may be typed as one word automatically constructed from the database entries “mobile” and “.com”, or from the entries “mobile” and “.” and “com” if there is a key for ambiguous punctuation; in either of those cases the period may not need be explicitly entered.
One embodiment of the build around concept can be described with reference to FIG. 9, a flow chart depicting a build around example. The build around method starts (9000) with a key sequence being entered, e.g., [k1 k2 k3 kd k5 k6 k7 k8]. The k#'s refer to ambiguously entered keys and kd refers to a delimiting key that can be either an explicitly entered character an ambiguously entered punctuation character. The method then determines if the database found a match (9100). If yes, a word is displayed (9200). If the user desires to proceed to the next choice in the list of words found by the database, the user presses a next key to request further lookups by the database (9300). Specifically, the database is multiply searched for matches to key sequences. A key sequence is divided into two sets on either side of a delimiter. An example of various groupings of two sets of sequences divided by a delimiter follows:
[k1 k2 k3 kd] [k5 k6 k7 k8];
[k1 k2 k3] [kd k5 k6 k7 k8]; and
[k1 k2 k3] kd [k5 k6 k7 k8].
If a match is found among any of the groups (9400), then the desired word is chosen and displayed (9500). If the user desires to build around this sequence, the user can press a next key to obtain the next set of results from multiple searches to the database (9600).
If the database did not find an initial match (9100), then the database is multiply searched for matches to key sequences (9700), wherein a key sequence is divided into two sets on either side of a delimiter, description of which and examples of which are presented above.
It should be appreciated that means to search for and display/present the set of possible desired words can vary and still remain within the scope and spirit of the invention.
Stem-locking
In the preferred embodiment of the invention, stem-locking is locking one or more subsequences or substrings of characters within a sequence. For example, the first n-numbers of sequence of characters of a word can be locked in. The way stem-locking works is that only words with those locked in characters are searched. For instance, suppose a user selects the 4 and then the 6 key of a wireless cell phone using T9 technology. The word “go” is presented in the display. If “go” is locked in, then upon subsequent key selections, only words with “go” in the first two positions are selected.
The locking of letters can be performed in a number of different ways. For example, two such ways are by a “full next locking” mechanism and an “unbounded” methodology by moving a cursor over characters to select. As an example of implementing “full next locking,” a “next” key is used. That is, according to one embodiment of the invention, selecting a “next” key locks in a previously presented series of characters, thereby eliminating the possibility of the system re-interpreting the object by re-interpreting the locked in series of characters. The selected series of characters are now marked as explicitly entered. An example of moving the cursor over characters (unbounded) according to one embodiment of the invention, the cursor is moved to the beginning of a series and by the user selecting a right-arrow key (or a left-arrow key, for example, in the Hebrew language), all the characters that the cursor moved over are locked in.
Another aspect of full next locking is locking a previously presented series of characters when likely word boundaries are identified. Such boundaries can be identified based on certain sequences of interactions, such as, for example, when the user “nexts” and then selects a symbol or punctuation character; or, when the user “nexts” and then enters an explicit number.
It should be appreciated that other methods to “lock” include, but are by no means limited to:
pressing a key assigned to the “lock” function, such as an OK or Select key; and pressing an appropriate arrow key to “lock” in a word completion being offered.
Stem locking approaches, such as those discussed above, can be related to “build around” as described herein above. That is, once a sequence has been locked in, it can be “built around.”
Japanese Kana Example
Another example of the disambiguating filtering methodology is in the Japanese language. Sub-phrases in kana (phonetic) character form can be converted to kanji (Yomikata), and those converted sub-phrases may in turn filter interpretations of the remaining ambiguous kana preceding or following the converted sub-phrases, excluding interpretations that can't be used to construct valid phrases.
In another embodiment of the invention, a hierarchy of locks mechanism is used. For example, a right arrow key can lock in all characters to the left of the cursor. Therefore, in this implementation, a right-arrow key locks in a first-choice stem, while a “next” key locks in a not-first-choice stem.
Another implementation is using a “select” key instead of a right-arrow key in combination with a “next” key. For example, the “select” key can be used at the end of each ambiguous key sequence for either selecting and accepting the default choice (the select key is pressed once) or for selecting an alternative choice (the select key is pressed more than once until the desired choice appears or is highlighted). In this case, the “select” key is used to stem lock either the first or alternate choices, rather than using the right-arrow key for the first choice and the “next” key for other choices (or vice-versa, as the choice of keys is arbitrary, yet predetermined).
Word Extension and Completion
Another aspect of the invention is the system automatically starting a new word at a lock position. For example, the user enters “car” and locks it, and then enters the keys for “pet”. “Carpet” is shown because it is a complete word in the database. The word “carset” is also shown because it is “car”+“set”, which is another example of the “build around” concept, where an ambiguous sequence may follow an explicit character entry, causing one interpretation to be the beginning of a new ambiguous word.
Alternatively, when one or more previously-accepted characters precedes (is adjacent to, without spaces) the current and active ambiguous key sequence. The system uses the preceding characters to match words and phrases (e.g., in the user database) that begin with those characters and that match an ambiguous key sequence following those characters. Optionally, one or more word completions is offered. An example follows. A user enters and locks in (accepts) the characters, “con.” Then, the user types ambiguous keys for “stan” and is offered “constantinople” as a word completion. In this example, the user could have used a left-/right-arrow key to accept “con” to be used to filter and to suggest word completions that begin with the accepted chars and are immediately adjacent to an ambiguous key sequence. Hebrew and other languages go the other direction, hence right-side-only is not assumed.
FIG. 7 is a flow chart of a method for generating words not stored in the database according to the invention. That is, in an equally preferred alternate embodiment, if a series of entries is locked in (7000) and subsequent ambiguous characters entered (7100) and a corresponding stored word is not found in the database (7200), then searches are performed for likely combinations based on the previous n locked in characters (7300). In one preferred embodiment of the invention, an n-gram is used to find stored words. This is contrary to using the entire set of locked in letters. For example, suppose a user has entered and explicitly selected the word “flight”, but the user, however, wants to enter the word “flightplan” which is not in the database. In this embodiment of the invention, the user then explicitly locks in the letter “p” and “I” after “flight”. The system then searches for words using the last explicitly entered bigram (p and I). Thus, words that are not stored in the database are generated.
Although the invention is described herein with reference to the preferred embodiment, one skilled in the art will readily appreciate that other applications may be substituted for those set forth herein without departing from the spirit and scope of the present invention.
Accordingly, the invention should only be limited by the Claims included below.

Claims

1. A computer-implemented method comprising:

receiving a series of key entries from a user input device;

determining at least one entry in the series of key entries is ambiguous, wherein each ambiguous entry corresponds to two or more potential characters in a human language;

determining one or more entry groups in the series of key entries and one or more potential character sequences associated with the entry groups, wherein, when a first entry group of the entry groups includes an ambiguous entry, the first entry group corresponds to at least two potential character sequences;

matching a potential character sequence of the potential character sequences against a language database; and

presenting the potential character sequence on a character input interface when the potential character sequence matches at least a portion of a known word or object in the language database.

2. The computer-implemented method of claim 1, further comprising:

locking the potential character sequence such that the first entry group is considered unambiguous and explicitly corresponding to the potential character sequence.

3. The computer-implemented method of claim 2, wherein locking the potential character sequence is in response to receiving a user input via the user input device.

4. The computer-implemented method of claim 3, wherein the user input corresponds to a character indicating a word boundary.

5. The computer-implemented method of claim 3, wherein the user input corresponds to a command to move a cursor of the character input interface toward a next character.

6. The computer-implemented method of claim 1, further comprising:

receiving user input to move a cursor over one or more characters in the potential character sequence; and

locking the one or more characters that the cursor moved over such that entries corresponding to the one or more characters are considered unambiguous and explicitly entered.

7. The computer-implemented method of claim 1, further comprising locking a subsequence of the potential character sequence thereby causing one or more entries to correspond explicitly to respective characters in the subsequence.

8. The computer-implemented method of claim 7, further comprising:

determining one or more new entry groups in the series of key entries and one or more new potential character sequences associated with the new entry groups; and

selecting at least one of the new potential character sequences corresponding to a second entry group to present on a character input interface based on whether the selected new potential character sequence matches at least a portion of a known word or object in the language database.

9. The computer-implemented method of claim 1, wherein said matching includes performing an N-Gram search.

10. The computer-implemented method of claim 1, wherein the user input device is a keyboard component of a mobile device and wherein the character input interface is displayed on a display component of the mobile device.

11. A computer-implemented method comprising:

receiving a series of key entries via a user input device;

determining, based on a user interaction with a text entry interface, at least a first key entry being explicitly associated with a character in a human language;

determining, based on a known attribute of the user input device, two or more potential characters for at least a second key entry;

identifying character combinations based on characters, explicit or ambiguous, of the series of key entries; and

performing a search to identify a likely character combination from among the character combinations that at least partially matches a word or object in a language database.

12. The computer-implemented method of claim 11, further comprising:

responsive to the search not identifying any character combination that at least partially matches a word or object in the language database, performing a modified search to identify the likely character combination as a character combination including most number of explicit or locked-in characters.

13. The computer-implemented method of claim 11, wherein performing the search includes determining whether there is a match in the language database to a character combination sequence of an entire length of the series of key entries.

14. The computer-implemented method of claim 13, further comprising displaying the character combination sequence when there is a match in the language database for the character combination sequence of the entire length of the series of key entries.

15. The computer-implemented method of claim 13, wherein performing the search further comprises:

dividing the series of key entries into subsets of entries when there is no match in the language database for the character combination sequence of the entire length.

16. The computer-implemented method of claim 15, wherein performing the search further comprises: determining whether there is a match for a character subsequence corresponding to a first subset of entries, wherein the character subsequence includes an explicit character, a potential character, or any combination thereof.

17. The computer-implemented method of claim 16, further comprising displaying the character subsequence for user verification via the text entry interface when there is a match for the character subsequence in the language database.

18. An apparatus for typing in a human language comprising:

a user input device to receive a series of key entries;

a display device for displaying a text entry interface;

a processor;

a memory storing a language object database and executable instructions to implement an engine when executed by the processor;

wherein the engine is operable to configure the processor to:

determine, based on a user interaction with the text entry interface, at least a first key entry being explicitly associated with a character in a human language;

determine, based on a known attribute of the user input device, two or more potential characters for at least a second key entry;

identify character combinations based on characters, explicit or ambiguous, corresponding to the series of key entries; and

perform a search to identify a likely character combination from among the character combinations that at least partially matches a word or object in a language database.

19. The apparatus of claim 18, wherein the user input device includes a button that, when pressed, generates an ambiguous key entry that corresponds to at least two potential characters in the human language.

20. The apparatus of claim 19, wherein the known attribute of the user input device specifies the potential characters corresponding to the button.