Active lab

• US 10,176,827 B2
• Filed: 01/15/2008
• Issued: 01/08/2019
• Est. Priority Date: 01/15/2008
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Inventors: Miller, Tanya M.
• Primary Examiner(s): Utama, Robert J
• Application Number:
  US12/014,229
• Publication Number:
  US 20090182702A1
• Time in Patent Office: 4,011 Days
• Field of Search: 434169, 434350, 434353, 434323, 434322
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/63 Querying
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 25/48 specially adapted for particular use

Abstract

Various embodiments provide a tool, referred to herein as “Active Lab” that can be used to develop, debug, and maintain knowledge bases. These knowledge bases (KBs) can then engage various applications, technology, and communications protocols for the purpose of task automation, real time alerting, system integration, knowledge acquisition, and various forms of peer influence. In at least some embodiments, a KB is used as a virtual assistant that any real person can interact with using their own natural language. The KB can then respond and react however the user wants: answering questions, activating applications, or responding to actions on a web page.

Claims

1. A system comprising:

one or more non-transitory computer-readable storage media;

computer-readable instructions stored on the one or more non-transitory computer-readable storage media which, when executed, provide a tool to enable a user to create and maintain a knowledge base that connects to a virtual assistant receiving a speech input string, wherein the tool is configured to;

enable a user to create one or more units, wherein at least one unit comprises a response paired with one or more vocabulary patterns that will trigger the response;

label the one or more vocabulary patterns with a respective label;

convert the speech input string to converted data by substituting portions of the speech input string with sets of terms bearing corresponding labels that refer back to at least one of the respective labels of the vocabulary patterns,

wherein a computer matching the corresponding labels with the respective labels identifies the response to be triggered and provided from the knowledge base to the virtual assistant, and

the sets of terms substituted for portions of the speech input string comprise;

vocabulary terms, wherein respective sets of vocabulary terms in the knowledge base comprise a grouping of synonyms and misspellings for a term in the speech input string, and/or

at least one helper term and/or

wild cards that function as a placeholder representing at least a portion of an identified word or words.

2. The system of claim 1, wherein the tool enables the one or more units to be grouped together in situation groups.

3. The system of claim 1, wherein the at least one unit comprises multiple concepts, wherein the concepts comprise the vocabulary patterns and the helper terms.

4. The system of claim 3, wherein the multiple concepts comprise an order and a proximity, wherein:

the vocabulary pattern will trigger if an input is received in that order; and

the vocabulary pattern will trigger if an input has the proximity.

5. The system of claim 1, wherein the tool utilizes cascades, wherein cascades can be selected from a group of cascades comprising:

a pre-vocabulary cascade that takes in contractions and outputs separate words,

a vocabulary cascade that takes in synonyms and outputs a vocabulary term,

a post-vocabulary cascade that takes in separate compound words and outputs single vocabulary words,

a concept cascade that takes in the vocabulary terms and helper terms and outputs concepts, or

a unit cascade that takes in concepts and outputs a response.

6. The system of claim 5, wherein a cascade provides a FPML runtime contained within a larger runtime.

7. The system of claim 1, wherein the tool is configured to provide a main application window, wherein the main application window includes a drop down menu bar, multiple tabs, a main display that displays currently selected/active tabs, and a status bar.

8. The system of claim 1, wherein the knowledge base comprises a FPML knowledge base.

9. The system of claim 1, wherein the tool is configured to enable a user to produce documents comprising one or more of:

(a) an FPML statistics document displaying percentage statistics of unit test questions or (b) a print units document displaying all units along with their respective test questions.

10. The system of claim 1, wherein the tool comprises a text-to-speech component which provides an ability to translate on-screen text into audio speech.