Auto-complete methods for spoken complete value entries

• US 10,529,335 B2
• Filed: 04/09/2019
• Issued: 01/07/2020
• Est. Priority Date: 08/19/2015
• Status: Active Grant

• Current Assignee: Hand Held Products Incorporated (Honeywell International Inc.)
• Original Assignee: Hand Held Products Incorporated (Honeywell International Inc.)
• Inventors: Nichols, Matthew, Mracna, Alexander Nikolaus, Miller, Kurt Charles, Evans, Russell, Kriley, Bernard, Sadecky, Luke, Manuel, Brian, Myaka, Navaneetha
• Primary Examiner(s): Riley, Marcus T
• Application Number:
  US16/379,285
• Publication Number:
  US 20190237077A1
• Time in Patent Office: 273 Days
• Field of Search: 704 1-504
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

An auto-complete method for a spoken complete value entry is provided. A processor receives a possible complete value entry having a unique subset, prompts a user to speak the spoken complete value entry, receives a spoken subset of the spoken complete value entry, compares the spoken subset with the unique subset of the possible complete value entry, and automatically completes the spoken complete value entry to match the possible complete value entry if the unique subset matches the spoken subset. The spoken subset has a predetermined minimum number of characters.

Claims

1. An auto-complete method comprising:

displaying a request for information adjacent to a graphical input field;

in response to displaying the request for information, receiving from a user, via a microphone, a spoken response comprising a set of spoken language characters, wherein the spoken response is associated with the request for information;

translating a subset of the set of spoken language characters into a set of written characters to create a set of translated written characters associated with the spoken response;

displaying the set of translated written characters in the graphical input field;

comparing the set of translated written characters to a collection of sets of written characters to determine whether the set of translated written characters matches a portion of the collection of sets of written characters; and

in response to matching the set of translated written characters to a first portion of a first set of written characters of the collection of sets of written characters, displaying a second portion that is a remainder of the first set of written characters as appended to the set of translated written characters displayed in the graphical input field.

2. The auto-complete method of claim 1, wherein the second portion is displayed in a first format, and the set of translated written characters is displayed in a second format different from the first format.

3. The auto-complete method of claim 2, wherein the first format is associated with a first text color, and the second format is associated with a second text color.

4. The auto-complete method according to claim 1, further comprising receiving a list of the collection of sets of written characters wherein each set of written characters in the collection of sets of written characters includes a unique subset of characters.

5. The auto-complete method according to claim 4, further comprising receiving the collection of sets of written characters based on collecting sets of written characters from at least one of common responses and responses expected to be received from the user in a particular context.

6. The auto-complete method according to claim 1, further comprising transmitting an alert if the set of translated written characters does not match the portion of the collection of sets of written characters.

7. The auto-complete method according to claim 1, further comprising prompting the user to confirm an automatically completed subset of spoken language characters as the information, after the second portion that is the remainder of the first set of written characters as appended to the set of translated written characters is displayed in the graphical input field.

8. The auto-complete method according to claim 7, wherein prompting the user to confirm the automatically completed subset of spoken language characters comprises reading back the automatically completed subset of spoken language characters by the user.

9. The auto-complete method according to claim 1, further comprising:

displaying, in the graphical input field, the second portion that is the remainder of the first set of written characters as a suggestion; and

receiving at least one of a user acceptance or user declination of the suggestion.

10. The auto-complete method according to claim 9, further comprising:

upon receiving the user declination repeating, in order, at least comparing the set of translated written characters to the collection of sets of written characters to determine whether the set of translated written characters matches the portion of the collection of sets of written characters;

in response to matching the set of translated written characters to another portion of another set of written characters of the collection of sets of written characters, displaying another portion that is a remainder of the another set of written characters as appended to the set of translated written characters displayed in the graphical input field; and

removing the first set of written characters from a suggestion list.

11. An auto-complete method comprising:

receiving, via a microphone, a spoken response, comprising a set of spoken language characters, wherein the spoken response is associated with a request for information displayed in a graphical input field that is visible to a user;

translating a subset of the set of spoken language characters into a set of written characters to create a set of translated written characters associated with the spoken response, wherein the set of translated written characters are adapted to be displayed in the graphical input field to the user;

determining the set of translated written characters to match with a portion of, at least, a set from amongst a collection of sets of written characters; and

in response to the matching of the set of translated written characters to a first portion of a first set of written characters of the collection of sets of written characters, automatically completing the subset of the set of spoken language characters to match the information, by appending to the set of translated written characters, a second portion that is a remainder of the first set of written characters.

12. The auto-complete method according to claim 11, further comprising displaying the second portion that is the remainder of the first set of written characters as appended to the set of translated written characters in the graphical input field.

13. The auto-complete method of claim 11, further comprising receiving the collection of sets of written characters based on collecting sets of written characters from at least one of common responses and responses expected to be received from the user in a particular context and wherein each set of written characters in the collection of sets of written characters includes a unique subset of characters.

14. The auto-complete method of claim 11, wherein the second portion is displayed in a first format, and the set of translated written characters is displayed in a second format different from the first format and wherein the first format is associated with a first text color, and the second format is associated with a second text color.

15. The auto-complete method of claim 11, further comprising transmitting an alert if the set of translated written characters does not match the first portion of the first set of written characters of the collection of sets of written characters.

16. The auto-complete method according to claim 11, further comprising prompting the user to confirm the automatically completed the subset of the set of spoken language characters as the information based on one of:

reading back the automatically completed the subset of the set of spoken language characters by the user;

or

an input provided by the user on an input interface associated with the graphical input field.

17. A system, comprising:

one or more processors configured to;

cause a display screen to display a task instruction, wherein the task instruction is configured to prompt a request to a user to speak an information;

receive a spoken response from a microphone, wherein the spoken response comprises a set of spoken language characters;

translate a subset of the set of spoken language characters to a set of written characters to create a set of translated written characters associated with the spoken response;

display the set of translated written characters in a graphical input field of the display screen;

compare the set of translated written characters to a collection of sets of written characters to determine whether the set of translated written characters matches a portion of the collection of sets of written characters;

determine, based on the comparison of the set of translated written characters to the collection of sets of written characters, that the translated subset of the set of spoken language characters matches with a subset of characters from a set of characters, wherein the subset of characters represents a possible complete value entry from amongst a set of possible complete value entries; and

in response to matching the set of translated written characters to a first portion of a first set of written characters of the collection of sets of written characters, cause to display a second portion that is a remainder of the first set of written characters as appended to the set of translated written characters displayed in the graphical input field of the display screen.

18. The system of claim 17, wherein the one or more processors are configured to:

cause the second portion to be displayed in a first format and the set of translated written characters is displayed in a second format different from the first format and wherein the first format is associated with a first text color, and the second format is associated with a second text color.

19. The system of claim 17, wherein the one or more processors are configured to:

generate and transmit an alert if the set of translated written characters does not match the first portion of the first set of written characters of the collection of sets of written characters.

20. The system of claim 17, wherein the one or more processors are configured to:

cause to display the second portion, on the graphical input field, that is the remainder of the first set of written characters as a suggestion;

receive one of a user acceptance or user refusal of the suggestion;

upon receiving the user acceptance, continue to cause the display of the second portion that is the remainder of the first set of written characters as appended to the set of translated written characters displayed in the graphical input field of the display screen; and

upon receiving the user refusal of the suggestion, cause to repeat, in order, at least compare the set of translated written characters to the collection of sets of written characters to determine whether the set of translated written characters matches the portion of the collection of sets of written characters;

in response to matching the set of translated written characters to another portion of another set of written characters of the collection of sets of written characters, cause to display another portion that is the remainder of the first set of written characters as appended to the set of translated written characters displayed in the graphical input field of the display screen and remove the first set of written characters from a suggestion list.