Systems and methods for an automated personalized dictionary generator for portable devices

• US 8,386,241 B2
• Filed: 03/29/2012
• Issued: 02/26/2013
• Est. Priority Date: 06/06/2008
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: ZI Corporation of Canada Incorporated (Microsoft Corporation)
• Inventors: Goud, Corneil John, Williams, Roland Emlyn, Templeton-Steadman, William James
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US13/434,730
• Publication Number:
  US 20120185239A1
• Time in Patent Office: 334 Days
• Field of Search: 704/1, 704/9, 704/10
• US Class Current: 704/10
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs

Abstract

A system and method for automated dictionary population is provided to facilitate the entry of textual material in dictionaries for enhancing word prediction. The automated dictionary population system is useful in association with a mobile device including at least one dictionary which includes entries. The device receives a communication which is parsed and textual data extracted. The text is compared to the entries of the dictionaries to identify new words. Statistical information for the parsed words, including word usage frequency, recency, or likelihood of use, is generated. Profanities may be processed by identifying profanities, modifying the profanities, and asking the user to provide feedback. Phrases are identified by phrase markers. Lastly, the new words are stored in a supplementary word list as single words or by linking the words of the identified phrases to preserve any phrase relationships. Likewise, the statistical information may be stored.

Claims

1. A computer implemented method for automated dictionary population, useful in association with a personal appliance including at least one dictionary which includes entries, the method for automated dictionary population comprising:

retrieving a message containing words, wherein the message is received by the personal appliance;

parsing the words of the message;

comparing the parsed words to the entries of the at least one dictionary, wherein the comparing identifies new words of the parsed words which are not found within the at least one dictionary;

generating statistical information for the parsed words;

identifying phrases from the parsed words by identifying phrase markers, wherein the phrase markers include at least one of italicized word groups, quoted word groups, bolded word groups, capitalized word groups, and word groups containing more than one new word;

linking the words of the identified phrases and storing the linking of the words of the identified phrases with additional information that allows them to remain linked without storing the entire identified phrases; and

storing the new words within at least one of the at least one dictionary, wherein the storing the new words enables recall of the new words for generating a candidate word list.

2. The method of automated dictionary population, as recited in claim 1, further comprising processing profanities, wherein the processing profanities comprises:

identifying profanities within the parsed words by comparing the parsed words to a profanity word list;

modifying the profanities by replacing at least some of the profanity with a place marker;

displaying the modified profanity to a user in a candidate list;

requesting feedback from the user;

receiving user feedback, wherein the feedback includes selection and de-selection of the profanities, wherein de-selection of the profanity may be at least one of explicit and implicit;

if the feedback includes selection of the profanities;

then, displaying the profanity to the user; and

storing the profanities;

else, if the feedback includes de-selection of the profanities;

then, removing the profanities from the candidate list.

3. The method of automated dictionary population, as recited in claim 1, wherein the parsing and comparing of the words is performed as each word is retrieved.

4. The method of automated dictionary population, as recited in claim 1, wherein the storing the new words includes preserving the generated statistical information.

5. The method of automated dictionary population, as recited in claim 4, wherein the generated statistical information includes at least one of word usage frequency, recency, or likelihood of use.

6. The method of automated dictionary population, as recited in claim 1, wherein retrieval occurs when a user accesses a received message.

7. The method of automated dictionary population, as recited in claim 1, wherein the message includes at least one of text messages, voice messages, embedded audio feeds and video data.

8. An automated dictionary system, useful in association with a personal appliance including at least one dictionary which contains entries, the automated dictionary system comprising:

a retriever configured to retrieve a message containing words, wherein the message is received by the personal appliance;

a message parser configured to parse the words of the text message;

a dictionary comparator configured to compare the parsed words to the entries of the at least one dictionary, wherein the dictionary comparer is further configured to identify new words of the parsed words which are not found within the at least one dictionary;

a statistical analyzer configured to generate statistical information for the parsed words;

a phrase group identifier configured to identify phrases from the parsed words by identifying phrase markers, wherein the phrase markers include at least one of italicized word groups, quoted word groups, bolded word groups, capitalized word groups, and word groups containing more than one new word, said phrase group identifier further configured to apply semantic rules to identify phrases from the parsed words by identifying word groups that include joining words and further comprising a linker configured to link the words of the identified phrases; and

a word storage moderator configured to store the new words within at least one of the at least one dictionary, wherein the storing the new words enables recall of the new words for generating a candidate word list, and wherein the word storage moderator is further configured to store the linkage of the words of the identified phrases with additional information that allows them to remain linked without storing the entire identified phrases.

9. The automated dictionary system of claim 8, further comprising a profanity interrupter configured to identify profanities within the parsed words by comparing the parsed words to a profanity word list, modify the profanities by replacing at least some of the profanity with a place marker, display the modified profanity to a user in a candidate list, request feedback from the user, receive user feedback wherein the feedback includes selection and de-selection of the profanities, wherein de-selection of the profanity may be at least one of explicit and implicit, and if the feedback includes selection of the profanities then displaying the profanity to the user and storing the profanities, else, if the feedback includes de-selection of the profanities then removing the profanities from the candidate list.

10. The automated dictionary system of claim 8, wherein the parsing and comparing of the words is performed as each word is retrieved.

11. The automated dictionary system of claim 8, wherein the word storage moderator is further configured to preserve the generated statistical information.

12. The automated dictionary system of claim 11, wherein the generated statistical information includes at least one of word usage frequency, recency, or likelihood of use.

13. The automated dictionary system of claim 8, wherein the retriever is configured to initiate retrieval when a user accesses the received message.

14. The automated dictionary system of claim 8, wherein the message includes at least one of text messages, voice messages, embedded audio feeds and video data.

15. A computer implemented method for automated dictionary population, useful in association with a personal appliance including at least one dictionary which includes entries, the method for automated dictionary population comprising:

retrieving a message containing words, wherein the message is received by the personal appliance;

parsing the words of the message;

comparing the parsed words to the entries of the at least one dictionary, wherein the comparing identifies new words of the parsed words which are not found within the at least one dictionary;

generating statistical information for the parsed words;

applying semantic rules to identify phrases from the parsed words by identifying word groups that include joining words;

linking the words of the identified phrases and storing the linking of the words of the identified phrases with additional information that allows them to remain linked without storing the entire identified phrases; and

storing the new words within at least one of the at least one dictionary, wherein the storing the new words enables recall of the new words for generating a candidate word list.

16. The method of automated dictionary population, as recited in claim 15, wherein the message includes at least one of text messages, voice messages, embedded audio feeds and video data.