- Contents
Interaction Administrator Help
Interaction Analyzer keyword definitions
This topic provides descriptions of the various methods you can use to create keywords for use in Interaction Analyzer.
Interaction Analyzer keyword entry
You enter keywords, up to 120 characters, through the Interaction Analyzer interface of Interaction Administrator or Interaction Center Server Manager. Spell keywords as you would enter them in any document intended for communication. The speech recognition engine uses that spelling entry to match it to its usual phonetic pronunciation.
Interaction Analyzer keyword spelling entries
You can also add multiple spelling entries of a keyword, depending on the different ways in which a person pronounces a word, such as data. For this word, some people pronounce it as dayta while others pronounce it as dahta. The dictionary through which Interaction Analyzer compares pronunciations already handles many words with multiple pronunciations. However, if you enter terms that are specific to a specialized field, such as medicine or science, you may need to provide alternate spelling entries or user-defined pronunciations to ensure recognition by Interaction Analyzer.
Keyword synonyms
One method you must avoid regarding spelling entries is that of synonyms. For example, if you wanted a keyword of home, do not enter the following synonyms as alternate spelling entries:
-
House
-
Abode
-
Domicile
-
Casa
-
Hacienda
-
Chateau
-
Castle
-
Shack
-
Hut
-
Home
-
Condominium
-
Apartment
-
Dwelling
Do not enter synonyms as alternate spelling entries because Interaction Analyzer determines the spotability factor by the lowest, least discernible entry. In the previous example, the lowest, least discernible spelling entry would be "Hut." Instead, create a keyword set with the name of home and enter each synonym as a keyword. This method insures that each synonym keyword has a separate spotability factor and confidence threshold, and can be further discerned through more spelling entries and user-defined pronunciations.
Keyword acronyms
If you want to create a keyword that contains an acronym that is pronounced as separate letters, enter the acronym with either periods or spaces between letters.
Examples:
-
F.B.I.
-
I D
-
E.T.A.
-
E U
-
C.O.D.
-
H T T P
-
F.T.P.
For acronyms that are pronounceable as a word, enter the acronym as you would any other keyword without spaces or periods between letters. Letter case is not important.
Examples:
-
SCSI (scuzzy)
-
RAM
-
PIN
-
NASA
-
SCUBA
In the case of mixed pronunciation acronyms, such as DVD-ROM, you must enter the acronym so that the portion pronounced as letters contain spaces or periods between letters while the portion pronounced as a single word does not, as in the following example:
D.V.D.-ROM
Keyword punctuation
Interaction Analyzer ignores any punctuation characters in keywords. These characters include commas, periods, exclamation points, hyphens, dashes, question marks, colons, semicolons, special characters ($, %, &, (, ), @), and quotation marks.
Keyword numbers
Each digit that you enter in a keyword is recognized as a word. For example, if you enter H20, Interaction Analyzer recognizes this keyword as "H two O." However, if you enter multiple digits, Interaction Analyzer recognizes each number separately. For example, if you enter 100, Interaction Analyzer recognizes this keyword as "one, zero, zero", not "one-hundred." Likewise, "21" is identified as "two, one", not "twenty-one."
Keyword contractions
Interaction Analyzer recognizes contractions when you enter them as keywords. Words such as "don't," "can't," "won't," "couldn't," "it's," and "I'll" are acceptable.
Keyword abbreviations
Interaction Analyzer does not recognize abbreviations, such as Dr., Mrs., Mr., Jr., Sr., and others.
Interaction Analyzer anti-spellings
After you define keywords, you have the option of entering anti-spellings that specify similar-sounding words that you do not want mistaken for that keyword. These words could confuse Interaction Analyzer, which could mark them incorrectly as instances of that keyword; these mistakes are false positives.
For example, the following table presents some keywords and possible anti-spellings that you can add to the definitions:
|
Keyword |
Anti-keywords |
|
Lawyer |
Lower Loiter Foyer Employer |
|
Surely |
Charlie Surly Purely Journey |
|
Guarantee |
Warranty Guillotine Green tea |
|
Unfair |
Conveyor Unveil Affair A fare On there |
Additionally, you can also specify anti-spellings where the keyword is part of a larger word. For example, consider the word form. You probably would not want Interaction Analyzer to spot this word when it is a part of larger words, such as uniform, formatted, and formation. In this case, if Interaction Analyzer does spot the keyword within the larger words, you can enter the larger words as anti-spellings.
Do not try to determine anti-spellings when you define a keyword. Instead, when your keywords are used in real interactions in a test environment or in the contact center, you can analyze recordings, identify words mistaken as keywords, and then add them as anti-spellings to the keyword definitions.
If you eventually enter anti-spellings in a keyword definition, you can also consult numerous websites that list other rhyming words for that specific keyword.
Interaction Analyzer keyword user-defined pronunciations
When you define keywords, Interaction Analyzer also enables you to enter phonetic, user-defined spellings, which are referred to as pronunciations. The set of phonemes that Interaction Analyzer uses is a customized version of ARPAbet. ARPAbet was a project that used ASCII characters to define the phonemes that make up all possible sounds in the English (US) language. The Interaction Analyzer phonemes differ from ARPAbet to provide more robust keyword spotting and to support languages other than English (US).
Some languages have sequences of letters that are pronounced differently when they appear in different words. For example, in English (US), tough, cough, dough, through, and bough are all similar in their spellings ("ough"), but have different pronunciations. Using user-defined pronunciations enables Interaction Analyzer to identify these words correctly. For example, the following table displays how these words are specified using phonemes:
|
Word |
Pronunciation |
|
tough |
t ah f |
|
cough |
c ao f |
|
dough |
d ow |
|
through |
th r uw |
|
bough |
b aw |
Note: The example words in the pervious table are common and already phonetically-defined in the Interaction Analyzer dictionary. The example words are for conceptual purposes only.
User-defined pronunciations are also useful for the different dialects that you can encounter in a language. For example, consider the English (US) word "lawyer" (l ao y er). Someone from the New England region of the United States could pronounce the word as "lahyah" (l aa y ah) while someone from the Deep South of the United States could pronounce it "lawryer" (l ao r y uh r). User-defined spellings enable you to define the keyword further so that Interaction Analyzer can correctly produce a match.
Important!
There are words in the medical and scientific fields that are based on
Latin and Greek, but the associated pronunciations transformed over centuries
of usage, such as peritonitis. If Interaction Analyzer
has difficulty identifying the keyword based on the correct spelling,
enter user-defined pronunciations to ensure proper identification of those
unique keywords.
Defining multiple words in pronunciations
If you want to create a pronunciation or anti-pronunciation, which use phonemes, and it consists of multiple words, you must enter a wd character string between each word. This character string enables Interaction Analyzer to focus on the phonemes for each word, which provides a more accurate comparison, instead of the entire phrase.
For example, "Hi my name is" would be entered as "hh ay wd m ay wd n ey m wd ih s." Enter a user-defined pronunciation only for keywords that Interaction Analyzer does not recognize.