Managing autocorrect actions

• US 9,292,621 B1
• Filed: 09/12/2012
• Issued: 03/22/2016
• Est. Priority Date: 09/12/2012
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Roth, Gregory B.
• Primary Examiner(s): Gofman, Alex
• Assistant Examiner(s): Mian, Umar
• Application Number:
  US13/611,550
• Time in Patent Office: 1,287 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3322 using system suggestions G06F16/3325 takes precedence
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 3/023 Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/04886 by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/242 Dictionaries

Abstract

Text input that is automatically “corrected” by an auto-correction process can be analyzed to determine whether to also include text as input before the correction. A set of words particular to an environment can be run through a number of auto-correct processes to determine which words are likely to be corrected, as well as the corrected versions. These “corrected” versions can be added to an index or other collection as synonyms, or alternatives, for the uncorrected words. When a request or other input is received that includes a corrected term, a determination can be made as to whether to include content for the synonymous uncorrected term. Such an approach can enable a user to obtain content that is more likely of interest to the user based at least in part upon known corrections made to terms that did not necessarily need correcting.

Claims

1. A computer-implemented method of managing automatically corrected text, comprising:

determining a set of terms specific to an environment;

processing each term in the set of terms using at least one text-correction algorithm to determine a subset of terms that are able to be auto-corrected by the at least one text-correction algorithm, as well as autocorrected terms for the subset of terms that were generated by the at least one text-correction algorithm, wherein an autocorrected term is generated by autocorrecting a term using the at least one text-correction algorithm, wherein processing each term in the set of terms using the at least one text-correction algorithm includes processing each term in the set of terms with a plurality of text-correction algorithms, each text-correction algorithm being utilized by at least one type of computing device;

storing the autocorrected terms with the set of terms as a set of synonyms;

receiving a communication including a first term that matches one of the autocorrected terms in the set of synonyms;

determining a matching term from the set of terms for the first term;

calculating, via at least one processor, a likelihood that the matching term was auto-corrected to the first term; and

reverting, via the at least one processor, the first term to the matching term in the communication when the calculated likelihood meets at least one correction criterion.

2. The computer-implemented method of claim 1, wherein the communication is received from a client device, and where the set of synonyms is specific to a type of the client device.

3. A computer-implemented method, comprising:

receiving a communication from a computing device, the communication including at least one text portion;

analyzing the at least one text portion using a set of environment-specific terms, at least a portion of environment-specific terms in the set each having at least one corresponding autocorrected term determined by running the environment-specific term through at least one text-correction process to generate the at least one corresponding autocorrected term, wherein a given environment-specific term in the set is capable of being associated with a plurality of autocorrected terms, each of the plurality of autocorrected terms corresponding to a different text-correction algorithm;

reverting a word in the at least one text portion of the communication to the environment-specific term associated with the corresponding autocorrected term upon a determination, via the at least one processor, that the word matches a corresponding autocorrected term in the set; and

processing the communication.

4. The computer-implemented method of claim 3, wherein reverting the word to the environment-specific term is in response to the environment-specific term meeting at least one correction criterion with respect to the communication.

5. The computer-implemented method of claim 3, wherein processing the communication includes forwarding the communication to at least one intended recipient of the communication.

6. The computer-implemented method of claim 3, further comprising:

running at least a portion of the environment-specific terms in the set through at least one text correction algorithm to determine the at least one corresponding autocorrected term for the portion of environment-specific terms.

7. The computer-implemented method of claim 3, wherein processing the communication includes causing advertising to be displayed on the computing device, the advertising being selected based at least in part upon the environment-specific term used to replace the word in the at least one text portions.

8. The computer-implemented method of claim 3, further comprising:

including information with the communication indicating that the word was replaced with the environment-specific term associated with the corresponding autocorrected term, enabling a recipient of the communication to revert back to the word that was replaced.

9. The computer-implemented method of claim 3, wherein the communication from the computing device includes an indication as to whether the word corresponds to autocorrected text.

10. The computer-implemented method of claim 9, wherein the indication results from an addition of one letter to a text entry causing a change of the word corresponding to the text entry.

11. The computer-implemented method of claim 3, further comprising:

sending a request to the computing device causing the computing device to prompt a user as to whether to correct the word to the environment-specific term.

12. The computer-implemented method of claim 3, wherein an environment-specific term is determined to match an autocorrected term when the autocorrected term was generated using a text-correction algorithm utilized by the computing device from which the communication was received.

13. The computer-implemented method of claim 3, wherein running the environment-specific term through at least one text-correction process is performed by at least one third party service.

14. The computer-implemented method of claim 3, wherein the environment-specific term is included in a domain associated with at least one of the computing device or a user of the computing device.

15. The computer-implemented method of claim 3, wherein the communication includes at least one of an email message, a text message, an instant message, a social networking post, a review submission, a medical record, an address input, or a chat message.

16. A computer system comprising:

at least one processor; and

a memory device including instructions that, when executed by the at least one processor, cause the computing system to;

determine a set of terms specific to an environment;

processing each term in the set of terms using at least one text-correction algorithm to determine a subset of terms that are able to be auto-corrected by the text-correction algorithm, as well as alternative autocorrected terms for that the subset of terms that were generated by the at least one text-correction algorithm, wherein an autocorrected term is generated by auto-correcting a term using the at least one text-correction algorithm, wherein processing each term in the set of terms using the at least one text-correction algorithm includes processing each term in the set of terms with a plurality of text-correction algorithms, each text-correction algorithm being utilized by at least one type of computing device;

store the autocorrected terms with the set of terms as a set of synonyms for use by at least one of an application or a service utilizing auto-correct functionality, each autocorrected term in the set of synonyms having a corresponding term, wherein the application or the service is configured to revert a first term to a term that corresponds to one of the autocorrected terms upon a determination, via the at least one processor, that the first term was auto-corrected to the one of the autocorrected terms.

17. The computing system of claim 16, wherein the instructions when executed further cause the computing system to:

receive a communication from a computing device, the communication including at least one word;

compare the word against the set of terms and the set of synonyms;

upon the word in the communication matching a synonym in the set of terms, reverting the word with the term corresponding to the synonym.

18. The computer system of claim 16, wherein at least a portion of the terms in the set correspond to names specific to a provider of the computing system.

19. The computer system of claim 16, wherein a term specific to an environment is determined to match an autocorrected term when the autocorrected term was generated using the text-correction algorithm utilized by the type of computing device.

20. A non-transitory computer-readable storage medium storing instructions that, when executed by at least one processor of a computing device, cause the computing device to:

receive a communication from a computing device, the communication including at least one word;

compare the word against a plurality of environment-specific terms, at least a portion of the plurality of environment-specific terms each having at least one corresponding autocorrected term determined by running the environment-specific term through at least one text-correction process to generate the at least one corresponding autocorrected term, wherein a given environment-specific term in the plurality of environment-specific terms is capable of being associated with a plurality of autocorrected terms, each of the plurality of autocorrected terms corresponding to a different text-correction algorithm;

revert the word in the communication with the environment-specific term associated with at least one autocorrected term in the set upon a determination, via the at least one processor, that the word matches the corresponding autocorrected term; and

process the communication.

21. The non-transitory computer-readable storage medium of claim 20, wherein reverting the word with the environment-specific term is in response to the environment-specific term meeting at least one correction criterion with respect to the communication.

22. The non-transitory computer-readable storage medium of claim 20, wherein processing the communication includes forwarding the communication to at least one intended recipient of the communication.

23. The non-transitory computer-readable storage medium of claim 20, wherein the instructions when executed further cause the computing device to:

pass at least a portion of the environment-specific terms in the set through at least one text correction algorithm to determine the at least one corresponding autocorrected term for the portion of the plurality of environment-specific terms.

24. The non-transitory computer-readable storage medium of claim 20, wherein processing the communication includes causing advertising to be displayed on the computing device, the advertising being selected based at least in part upon the environment-specific term used to replace the word in the at least one text portions.

25. The non-transitory computer-readable storage medium of claim 20, wherein an environment-specific term is determined to match an autocorrected term when the autocorrected term was generated using a text-correction algorithm utilized by the computing device from which the communication was received.