Alphanumeric information input method

• US 20040201607A1
• Filed: 01/15/2002
• Published: 10/14/2004
• Est. Priority Date: 01/15/2002
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Airtox, Inc. (Eurofins Scientific SE)
• Inventors: Demartines, Pierre, Mulvey, Joseph
• Granted Patent: US 7,111,248 B2
• Time in Patent Office: Days
• US Class Current: 715/708
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models

Abstract

An alphanumeric information entry process that includes provision and use of a personal context model that correlates various examples of user context against a unique personal language model for the user. The personal language model itself along with considerable correlation examples can be developed by statistical analysis of user documents and files including particularly email files (including address books). Such processing can be done locally or remotely. The personal context model is used to predict subsequent alphanumeric entries for a given user. In one embodiment predictions are presented one word at a time. Predictions can be automatically changed in one embodiment when the user fails to make any input for a predetermined period of time.

Claims

1. A method comprising:

receiving first data from a user representing alphanumeric information;

predicting at least one additional item of alphanumeric information based upon the first data and a personal context model.

2. The method of claim 1 wherein receiving first data includes detecting bio-sourced physical indicia from a user.

3. The method of claim 2 wherein detecting bio-sourced physical indicia from a user includes detecting at least one of:

a keypad key assertion;

tactile script input;

audio waves;

electromagnetic biological signals.

4. The method of claim 2 wherein detecting bio-sourced physical indicia from a user includes detecting a plurality of sequential bio-sourced physical indicia from a user.

5. The method of claim 2 wherein detecting bio-sourced physical indicia from a user includes detecting multi-tap entry-mode bio-sourced physical indicia from a user.

6. The method of claim 2 wherein detecting bio-sourced physical indicia from a user includes detecting disambiguation entry-mode bio-sourced physical indicia from a user.

7. The method of claim 1 wherein predicting at least one additional item of alphanumeric information based upon the first data and a personal context model includes basing the prediction upon a personal context model comprising previously analyzed alphanumeric information for the user.

8. The method of claim 7 wherein basing the prediction upon a personal context model comprising previously analyzed alphanumeric information for the user includes basing the prediction at least upon previously analyzed alphanumeric information for the user as obtained from e-mail files for the user.

9. The method of claim 1 wherein predicting at least one additional item of alphanumeric information based upon the first data and a personal context model includes basing the prediction upon a personal context model comprising information content of a previously received message to which the user is replying.

10. The method of claim 1 wherein predicting at least one additional item of alphanumeric information based upon the first data and a personal context model includes basing the prediction upon a personal context model comprising information regarding at least one of:

a recipient device to which the at least one additional item of alphanumeric information is likely to be sent;

a recipient'"'"'s name;

a time of day;

a given day;

a given message subject;

a given geographic location;

a given transactional context.

11. The method of claim 1 and further comprising presenting predicted alphanumeric information to the user.

12. The method of claim 11 wherein presenting predicted alphanumeric information to the user comprises presenting only a single word to the user.

13. The method of claim 1 and further comprising predicting a new at least one item of alphanumeric information based at least in part upon the first data and the personal context model when at least a predetermined period of time expires without the user accepting the at least one additional item of alphanumeric information.

14. The method of claim 13 wherein predicting a new at least one item of alphanumeric information based at least in part upon the first data and the personal context model when at least a predetermined period of time expires without the user accepting the at least one additional item of alphanumeric information includes predicting a new at least one item of alphanumeric information based at least in part upon the first data and the personal context model when at least a predetermined period of time as uniquely determined for the user expires without the user accepting the at least one additional item of alphanumeric information.

15. The method of claim 1 and further comprising presenting at least one synonym that corresponds to at least one item of predicted alphanumeric information.

16. The method of claim 1 and further comprising:

providing a first device that receives the first data;

providing a second device that includes the personal context model; and

providing the personal context model from the second device to the first device.

17. A method comprising:

providing a plurality of e-mail files for a user;

processing the plurality of e-mail files to develop a personal context model for the user;

using the personal language model to predict subsequent alphanumeric information when receiving input data representing alphanumeric information from the user.

18. The method of claim 17 wherein providing a plurality of e-mail files for a user includes transmitting at least some information regarding the plurality of e-mail files to a remote location.

19. The method of claim 17 wherein providing a plurality of e-mail files for a user includes providing subject matter content of the plurality of e-mail files.

20. The method of claim 17 wherein providing a plurality of e-mail files for a user includes providing at least some content from an address book.

21. The method of claim 17 wherein processing the plurality of e-mail files to develop a personal language model for the user includes developing a personal language model for the user based, at least in part, upon a statistical analysis of alphanumeric information usage with respect to user context.

22. The method of claim 21 wherein developing a personal language model for the user based, at least in part, upon a statistical analysis of alphanumeric information usage with respect to user context includes correlating specific alphanumeric items with specific e-mail recipients.

23. A method comprising:

providing alphanumeric information as digitally stored by a user on a first device to a remote location;

receiving at least portions of a personal language model for the user as based, at least in part, upon the alphanumeric information;

using the personal language model to predict subsequent alphanumeric information when receiving input data representing alphanumeric information from the user.

24. The method of claim 23 to wherein receiving at least portions of the personal language model for the user includes receiving at least portions of the personal language model for the user at a second device.

25. The method of claim 24 wherein using the personal language model to predict subsequent alphanumeric information when receiving input data representing alphanumeric information from the user includes using the personal language model to predict subsequent alphanumeric information when receiving input data at the second device representing alphanumeric information from the user.

26. The method of claim 24 wherein receiving at least portions of the personal language model for the user at a second device includes receiving at least portions of the personal language model for the user at a second device comprising a two-way wireless communications device.

27. The method of claim 24 wherein receiving at least portions of the personal language model for the user at a second device includes receiving at least portions of the personal language model for the user at a second device comprising at least one of:

a personal digital assistant;

a pre-recorded audio playback device;

a remote control;

a teletext interface.

28. A method comprising:

using a personal language model for a user to predict subsequent alphanumeric information when receiving input data representing alphanumeric information from the user, which prediction is based upon the input data and a personal context model;

modifying the personal language model based upon subsequently entered input data representing alphanumeric information from the user.