Nonstandard text entry

• US 8,392,453 B2
• Filed: 06/25/2004
• Issued: 03/05/2013
• Est. Priority Date: 06/25/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Baluja, Shumeet
• Primary Examiner(s): Lewis, Cheryl
• Assistant Examiner(s): Hoffler, Raheem
• Application Number:
  US10/876,989
• Publication Number:
  US 20050289141A1
• Time in Patent Office: 3,175 Days
• Field of Search: None
• US Class Current: 707/771
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• 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 computer-implemented method of providing text entry assistance data comprises receiving at a computer information indicative of predictive textual outcomes, generating dictionary data from the received information; and providing the dictionary data to a text entry device remote from the computer. The received information may relate to search requests made by a plurality of remote searchers, and the received information may be indicative of search term popularity.

Claims

1. A method, implemented by a computer system, for providing text entry assistance data, comprising:

receiving, at the computer system, information that characterizes search requests submitted to one or more search engines by a plurality of users;

producing frequency information that is indicative of a frequency of usage of terms in the search requests;

receiving, at the computer system, one or more terms of a first search request, wherein the one or more terms of the first search request are received from a text entry device remote from the computer system;

generating, using the computer system, predictive text entry dictionary probability data based at least in part on the frequency information and the first search request, wherein the predictive text entry dictionary probability data are probabilities of usage of terms other than the first search request at the remote text entry device; and

outputting, from the computer system, the predictive text entry dictionary probability data to the text entry device remote from the computer system, wherein the predictive text entry dictionary probability data comprises a plurality of terms with a corresponding plurality of predictive weightings to the remote text entry device, wherein the predictive weightings include weightings for co-concurrence events between two or more terms,

wherein the predictive text entry dictionary probability data is suitable for suggesting completions for ambiguous text other than the first search request entered at the text entry device.

2. The method of claim 1, wherein the predictive text entry dictionary probability data is generated based in part on information obtained by crawling one or more internet-accessible information storage locations.

3. The method of claim 1, wherein the predictive text entry dictionary probability data is provided to the remote text entry device in response to a request from the remote text entry device.

4. The method of claim 3, wherein:

the request comprises the first search request; and

the predictive text entry dictionary probability data is provided along with results to the search request.

5. The method of claim 2, wherein the one or more information storage locations comprise e-mail storage.

6. The method of claim 2, wherein the one or more storage locations correspond to a predefined group of locations for an organization, and the predictive text entry dictionary probability data is indicative of the expected usage of terms by that organization.

7. The method of claim 1, further comprising compressing the predictive text entry dictionary probability data before providing it to the remote text entry device.

8. The method of claim 1, wherein the predictive text entry dictionary probability data comprises supplemental data for addition to a preexisting predictive text entry dictionary.

9. The method of claim 1, further comprising:

generating a search result in response to the first search request; and

providing the search result along with the predictive text entry dictionary probability data.

10. The method of claim 9, wherein the predictive text entry dictionary probability data comprises data from documents identified in the search result.

11. A data collection and distribution system comprising:

one or more computers having

one or more search engines to receive search requests from a plurality of users;

a dictionary generator to produce, based on the search requests, probability data reflecting respective probabilities of usage of a plurality of terms other than the search requests at each of respective devices submitting the search requests received by the one or more search engines, the dictionary generator comprising a concurrence rater that calculates concurrence scores for a plurality of objects, the probability data including the concurrence scores; and

a response formatter to receive, for each search request, search results responsive to the search request and the probability data for the search request and output the search results responsive to the search request and the probability data based on the search request from the data collection and distribution system to the device submitting the search request,

wherein the probability data produced by the dictionary generator is suitable for suggesting completions for ambiguous text other than the search requests entered into the devices submitting the search requests.

12. The data collection and distribution system of claim 11, wherein the plurality of objects comprises a plurality of terms in a search request.

13. The data collection and distribution system of claim 11, further comprising an object picker to identify objects in a document for submission to the concurrence rater.

14. The data collection and distribution system of claim 13, wherein the object picker is adapted to scan a plurality of defined documents for data indicative of the occurrence of words in the documents and concurrence between words in the documents.

15. A portable communication device comprising:

a data entry interface to interface with a human user;

a transceiver to receive and transmit information;

memory storing a vocabulary repository containing vocabulary information indicative of probable intended usage of ambiguous input entered by a user of the communication device, the vocabulary information including occurrence data reflecting recent usage practices of users other than the human user of the communication device;

data processing apparatus programmed to implement a disambiguation engine to resolve the ambiguous input provided to the device over the data entry interface by the human user to a probable solution for presentation to the human user by identifying possible solutions to the ambiguous input and applying the vocabulary information indicative of probable intended usage to the possible solutions; and

an output device to present the probable solutions to the human user under direction of the data processing apparatus,

wherein the occurrence data of the vocabulary information indicative of probable intended usage of ambiguous input includes

base vocabulary usage information that reflects vocabulary usage that is not associated with a particular time period, and

supplemental vocabulary usage information that reflects vocabulary usage within a recent time period by the users other than the human user of the communication device, wherein the supplemental vocabulary usage information comprises a collection of entries, each entry comprising a word, a probability that the word of that entry is to be typed or selected at the communication device, and concurrence probabilities of the word of that entry and a collection of other words at the communication device.

16. The communication device of claim 15, wherein the transmitter comprises a wireless transmitter.

17. The communication device of claim 15, wherein the occurrence data contains data that represents usage practices by members of a demographic group.

18. The communication device of claim 15, wherein the display is to present one or more of the identified possible solutions in order from most probable solution to least probable solution under the direction of the data processing apparatus.

19. The communication device of claim 15, wherein the disambiguation engine is configured to select a solution and provide the solution to the transceiver for transmission.

20. The communication device of claim 19, wherein the vocabulary repository can be updated with information indicative of probable intended usage based on the selected solution.

21. A method implemented by a data collection and distribution system of one or more data processing devices, the method comprising:

updating a first predictive text entry dictionary stored at a first device having a first text entry system, the updating comprising;

receiving, at the data collection and distribution system from the first device, a first search request;

generating first entries for updating the first predictive text entry dictionary based on the first search request, each of the first entries comprising;

a word,

a probability that the word of that entry is to be typed or selected at the first device, and

concurrence probabilities of the word of that entry and a collection of other words at the first device; and

outputting the first entries for updating the first predictive text entry dictionary from the data collection and distribution system to the first device; and

updating a second predictive text entry dictionary stored at a second device having a second text entry system, the updating comprising;

receiving, at the data collection and distribution system from the second device, a second search request;

generating second entries for updating the second predictive text entry dictionary based on the second search request, each of the second entries comprising;

a word,

a probability that the word of that entry is to be typed or selected at the second device, and

concurrence probabilities of the word of that entry and a collection of other words at the second device; and

outputting the second entries for updating the second predictive text entry dictionary from the data collection and distribution system to the second device,

wherein

the first device differs from the second device,

the first search request differs from the second search request,

at least some of the first entries are not found in the second entries, and

at least some of the second entries are not found in the first entries.

22. The method of claim 21, wherein updating the first predictive text entry dictionary comprises:

receiving text found at locations identifiable by a search engine using the first search request;

analyzing the locations for usage data of terms; and

generating the concurrence probabilities based on the analysis of the locations.

23. A method, implemented by a computer system, for providing text entry assistance data, comprising:

receiving, at the computer system, information that characterizes search requests submitted to one or more search engines by a plurality of users;

producing frequency information that is indicative of a frequency of usage of terms in the search requests;

receiving, at the computer system, one or more terms of a first search request, wherein the one or more terms of the first search request are received from a text entry device remote from the computer system;

generating, using the computer system, predictive text entry dictionary probability data based at least in part on the frequency information and the first search request, wherein the predictive text entry dictionary probability data are probabilities of usage of terms other than the first search request at the remote text entry device and the predictive text entry dictionary probability data is generated based in part on information obtained by crawling one or more internet-accessible information storage locations, wherein the locations correspond to a predefined group of locations for an organization and the predictive text entry dictionary probability data is indicative of the expected usage of terms by that organization; and

outputting, from the computer system, the predictive text entry dictionary probability data to the text entry device remote from the computer system,

wherein the predictive text entry dictionary probability data is suitable for suggesting completions for ambiguous text other than the first search request entered at the text entry device.

24. The method of claim 23, wherein the predictive text entry dictionary probability data is provided to the remote text entry device in response to a request from the remote text entry device.

25. The method of claim 24, wherein:

the request comprises the first search request; and

the predictive text entry dictionary probability data is provided along with results to the search request.

26. The method of claim 23, wherein the one or more information storage locations comprise e-mail storage.

27. The method of claim 23, further comprising compressing the predictive text entry dictionary probability data before providing it to the remote text entry device.

28. The method of claim 23, wherein the predictive text entry dictionary probability data comprises supplemental data for addition to a preexisting predictive text entry dictionary.

29. The method of claim 23, further comprising:

generating a search result in response to the first search request; and

providing the search result along with the predictive text entry dictionary probability data.