System and methods for matching an utterance to a template hierarchy

• US 9,043,206 B2
• Filed: 10/28/2013
• Issued: 05/26/2015
• Est. Priority Date: 04/26/2010
• Status: Active Grant

• Current Assignee: Ascend Hit LLC
• Original Assignee: Cyberpulse, L.L.C.
• Inventors: Roberge, James
• Primary Examiner(s): Vy, Hung T
• Application Number:
  US14/065,348
• Publication Number:
  US 20140052444A1
• Time in Patent Office: 575 Days
• Field of Search: 704/4, 704/9, 704/200, 704/246, 704/230, 704/243, 704/251, 704/257, 707/758
• US Class Current: 704/243
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning

Abstract

A system and methods for matching at least one word of an utterance against a set of template hierarchies to select the best matching template or set of templates corresponding to the utterance. Certain embodiments of the system and methods determines at least one exact, inexact, and partial match between the at least one word of the utterance and at least one term within the template hierarchy to select and populate a template or set of templates corresponding to the utterance. The populated template or set of templates may then be used to generate a narrative template or a report template.

Claims

1. A system by which a user inputs information into a record, comprising:

a processor;

a main memory in communication with the processor via a communication infrastructure and storing instructions that, when executed by the processor, cause the processor to;

(a) receive an input utterance from an input device, wherein the input utterance includes at least one word;

(b) retrieve a program code that includes one or more markers, each of which is associated with a certain utterance and correspond to a computer-implemented task;

(c) assess the program code for the presence of one or more markers for which the certain utterance with which it is associated is the input utterance;

(d) if the input utterance is associated with one or more markers, perform the computer-implemented task corresponding to the one or more markers associated with the input utterance;

(e) access a set of template hierarchies from a database, wherein each template hierarchy of the set includes at least one template and where each template includes one or more markers, each of which is associated with a certain utterance and correspond to a computer-implemented task;

(f) compare the at least one word of the input utterance to at least one term of the at least one template of template hierarchy in the set of template hierarchies;

(g) determine whether the at least one word of the input utterance matches the at least one term of the at least one template of the template hierarchy;

(h) calculate a score based on the match between the at least one word of the input utterance and the at least one term of the at least one template of the template hierarchy;

(i) repeat steps (f)-(h) until there are no more words of the input utterance for said compare step;

(j) populate the at least one template with at least one data element corresponding to the at least one term of the at least one template of the template hierarchy to obtain one or more populated templates;

(k) compute a total score of each populated template of the one or more populated templates based on the match between all words of the input utterance to each populated template of the one or more populated templates;

(l) select at least one populated template with a high total score;

(m) ascertain by the processor whether the high total score of the selected template meets a threshold score and, if so, perform computer-implemented task corresponding to the one or more markers associated with the template;

(n) establish by the processor whether there is any template that scores at or above the threshold score;

(o) if no template scores at or above the threshold score record the utterance as a sequence of words; and

(p) communicate the sequence of words to the user.

2. The system of claim 1, wherein step (p) further comprises the step of presenting visually the sequence of words.

3. The system of claim 1, wherein the input utterance associated with one or more markers instep d corresponds to the computer implemented task of displaying an information-entry interface configured to permit inputting an information item for entry into the record.

4. The system of claim 1, wherein the input utterance associated with the template with the high total score over a threshold score in step m corresponds to the computer implemented task of displaying an information-entry interface configured to permit inputting an information item for entry into the record.

5. The system of claim 1, wherein the input utterance associated with one or more markers in step d corresponds to the computer implemented task of recording data for entry into the record.

6. The system of claim 1, wherein the input utterance associated with the template with the high total score over a threshold score in step m corresponds to the computer implemented task of recording data for entry into the record.

7. The system of claim 1, wherein the input utterance associated with one or more markers in step d corresponds to the computer implemented task of executing a sequence of instructions.

8. The system of claim 1, wherein the input utterance associated with the template with the high total score over the threshold score in step m corresponds to the computer implemented task of executing a sequence of instructions or commands.

9. The system of claim 1, wherein the main memory in communication with the processor via a communication infrastructure and storing instructions that, when executed by the processor, cause the processor to:

(a) receive an additional utterance from an input device, wherein the additional utterance includes at least one word;

(b) retrieve a program code that includes one or more markers, each of which is associated with a certain utterance and correspond to a computer-implemented task;

(c) assess the program code for the presence of one or more markers for which the certain utterance with which it is associated is the additional utterance;

(d) if the additional utterance is associated with one or more markers, perform computer-implemented task corresponding to the one or more markers associated with the additional utterance;

(e) if the additional utterance is not associated with one or more markers, show notification configured to convey same to user.

10. The system of claim 9, wherein the additional utterance a term such as “

Done”

that is associated with the marker that corresponds to the computer implemented tasks of saving any entered information items in the record and closing an open information-entry interface.

11. The system of claim 9, wherein the additional utterance is an input utterance associated with termination of initiated screen for which the marker corresponds to the computer implemented tasks of:

(a) evaluating whether any information item was entered;

(b) performing computer implemented tasks upon any entered information item;

(c) saving the resulting information items in the record; and

(d) closing an open information-entry interface.

12. The system of claim 11, wherein the additional utterance is an input utterance associated with a termination of initiated screen for which the marker corresponds to the computer implemented tasks of:

(a) saving any entered information items in the record;

(b) closing an open information-entry interface; and

(c) displaying a second information-entry interface.

13. The system of claim 1, wherein the input device is a microphone.

14. A computer system method by which a user inputs information into a record, the computer system including a processor, an input device, a memory, a database and a program including instructions, wherein the program resides in the memory and the processor configured to execute the program including the instructions comprising:

receiving a first utterance from an input device, wherein the first utterance includes at least one word;

retrieving a program code that includes one or more markers, each of which is associated with a certain utterance and correspond to a computer-implemented task;

assessing the program code for the presence of one or more markers for which the certain utterance with which it is associated is the first utterance;

if the first utterance is associated with one or more markers, perform computer-implemented task corresponding to the one or more markers associated with the first utterance;

if the first utterance is not associated with one or more markers, show notification configured to convey same to user;

receiving a second utterance by the input device;

entering the second utterance into the memory;

accessing by the processor a set of template hierarchies from the database, wherein the set of template hierarchies includes at least one template;

performing a matching algorithm instructing the processor to compare words of the second utterance to terms of the template hierarchy to determine a match between the words and terms, the matching algorithm further instructing the processor to perform the steps of;

calculating a score based on the match between the words of the second utterance to terms of the template hierarchy;

populating the at least one template with data elements of the database that correspond to the terms of the template hierarchy to obtain a populated template;

computing a total score based on the match between all words of the second utterance to the populated template;

selecting the at least one template with a high total score;

establishing there is no template with the high total score recording by the processor the second utterance as a sequence of words; and

communicating the sequence of words to the user.

15. The computer system method of claim 14, wherein said communicating step further comprises the step of presenting visually the sequence of words.

16. The computer system of claim 14, wherein said communicating step further comprises the step of presenting audibly the sequence of words through a speaker.

17. The computer system method of claim 14, wherein the first utterance is associated with a marker that corresponds to the computer implemented task of displaying an information-entry interface.

18. The computer system method of claim 14, wherein the database is located on a memory of a remote computer.