Word order suggestion processing

• US 10,089,297 B2
• Filed: 12/15/2016
• Issued: 10/02/2018
• Est. Priority Date: 12/15/2016
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Smith, Andrew Nicholas Paul
• Primary Examiner(s): RIES, LAURIE ANNE
• Application Number:
  US15/380,840
• Publication Number:
  US 20180173690A1
• Time in Patent Office: 656 Days
• 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 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06F 3/04895 Guidance during keyboard input operation, e.g. prompting
• CPC Class Codes: G06F 40/103 Formatting, i.e. changing of presentation of documents automatic justification G06F40/189; automatic line break hyphenation G06F40/191
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/258 Heading extraction; Automatic titling; Numbering
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs

Abstract

Non-limiting examples of the present disclosure describe processing that improves suggestions for a misspelt word. Examples described herein relate to processing executed by a client device or computing devices connected via a distributed network. In one example, an electronic document that comprises a misspelt word is accessed. An order of word suggestions for the misspelt word is determined based on an application of an exemplary word order suggestion model that analyzes the misspelt word based on: an analysis of an unformatted state of content within the electronic document and an analysis of formatting associated with content of the electronic document. Further aspects of an electronic document including file metadata may be analyzed by the word order suggestion model. A listing of suggestions for the misspelt word is provided, where an order of word suggestions included in the listing is determined based on the application of the word order suggestion model.

Claims

1. A method comprising:

accessing an electronic document that comprises a misspelt word;

determining an order of word suggestions for the misspelt word based on an application of a word order suggestion model that analyzes the misspelt word based on;

an analysis of an unformatted state of content within the electronic document, and

an analysis evaluating types of formatting associated with the content of the electronic document; and

providing a listing of suggestions for the misspelt word, wherein an order of word suggestions included in the listing is determined based on the application of the word order suggestion model.

2. The method of claim 1, wherein the application of the word order suggestion model further analyzes the misspelt word based on an analysis of file metadata associated with the electronic document.

3. The method of claim 2, wherein in analyzing the file metadata, the application of the word order suggestion model evaluates a title of the electronic document and file path information corresponding with the electronic document.

4. The method of claim 2, wherein the application of the word order suggestion model comprises assigns weighting to each of the analysis of the content of the electronic document, the analysis of the formatting of the content of the electronic document and the analysis of the file metadata associated with the electronic document.

5. The method of claim 1, wherein the analysis of an unformatted state of content within the electronic document comprises:

evaluating a frequency of words used in the electronic document and determining a priority for ordering word suggestions of the listing based on an evaluation of the frequency of words, and wherein the analysis of the formatting associated with the content of the electronic document comprises;

evaluating an importance of particular words of the electronic document based on formatting associated with the particular words and determining a priority for ordering word suggestions of the listing based on an evaluation of the formatting.

6. The method of claim 1, further comprising receiving input selecting a word suggestion from the listing and replacing the misspelt word with a selected word suggestion.

7. The method of claim 1, further comprising receiving a request to provide suggestions for the misspelt word and wherein the listing is provided based on the received request.

8. The method of claim 1, wherein the determining further comprises re-ordering a generated listing of suggestions based on the application of the word order suggestion model, and wherein the re-ordering comprises adding at least one new word suggestion based on the application of the word order suggestion model.

9. A system comprising:

at least one processor; and

a memory operatively connected with the at least one processor storing computer-executable instructions that, when executed by the at least one processor, causes the at least one processor to execute a method that comprises;

accessing an electronic document that comprises a misspelt word,

determining an order of word suggestions for the misspelt word based on a word order suggestion model that analyzes the misspelt word based on;

an analysis of an unformatted state of content within the electronic document, and

an analysis evaluating types of formatting associated with the content of the electronic document, and

providing a listing of word suggestions for the misspelt word, wherein an order of word suggestions included in the listing is determined based on the application of the word order suggestion model.

10. The system of claim 9, wherein the application of the word order suggestion model further analyzes the misspelt word based on an analysis of file metadata associated with the electronic document.

11. The system of claim 10, wherein in analyzing the file metadata, the application of the word order suggestion model evaluates a title of the electronic document and file path information corresponding with the electronic document.

12. The system of claim 10, wherein the application of the word order suggestion model comprises assigns weighting to each of the analysis of an unformatted state of content within the electronic document, the analysis of the formatting of the content of the electronic document and the analysis of the file metadata associated with the electronic document.

13. The system of claim 9, wherein the analysis of an unformatted state of content within the electronic document comprises:

evaluating a frequency of words used in the electronic document and determining a priority for ordering word suggestions of the listing based on an evaluation of the frequency of words, and wherein the analysis of the formatting associated with the content of the electronic document comprises;

evaluating an importance of particular words of the electronic document based on formatting associated with the particular words and determining a priority for ordering word suggestions of the listing based on an evaluation of the formatting.

14. The system of claim 9, wherein the method, executed by the at least one processor, further comprises:

receiving input selecting a word suggestion from the listing and replacing the misspelt word with a selected word suggestion.

15. The system of claim 9, wherein the method, executed by the at least one processor, further comprises:

receiving a request to provide suggestions for the misspelt word and wherein the listing is provided based on the received request.

16. The system of claim 9, wherein the determining further comprises re-ordering a generated listing of suggestions based on the application of the word order suggestion model, and wherein the re-ordering comprises adding at least one new word suggestion based on the application of the word order suggestion model.

17. A computer-readable medium storing computer-executable instructions that, when executed by at least one processor, causes the at least one processor to execute a method comprising:

accessing an electronic document that comprises a misspelt word;

determining an order of word suggestions for the misspelt word based on an application of a word order suggestion model that analyzes the misspelt word based on;

an analysis of an unformatted state of content within the electronic document, and

an analysis evaluating types of formatting associated with the content of the electronic document; and

providing a listing of word suggestions for the misspelt word, wherein an order of word suggestions included in the listing is determined based on the application of word order suggestion model.

18. The computer-readable medium of claim 17, wherein the application of the word order suggestion model further analyzes the misspelt word based on an analysis of file metadata associated with the electronic document, and wherein in analyzing the file metadata, the application of the word order suggestion model evaluates a title of the electronic document and file path information corresponding with the electronic document.

19. The computer-readable medium of claim 17, wherein the analysis of an unformatted state of content within the electronic document comprises:

evaluating a frequency of words used in the electronic document and determining a priority for ordering word suggestions of the listing based on an evaluation of the frequency of words, and wherein the analysis of the formatting associated with the content of the electronic document comprises;

evaluating an importance of particular words of the electronic document based on formatting associated with the particular words and determining a priority for ordering word suggestions of the listing based on an evaluation of the formatting.

20. The computer-readable medium of claim 17, wherein the determining further comprises re-ordering a generated listing of suggestions based on the application of the word order suggestion model and wherein the re-ordering comprises adding at least one new word suggestion based on the application of the word order suggestion model.