Method and apparatus for natural language query in a workspace analytics system

1. A computer-implemented method for providing a natural language interface to process user queries for information managed in a workspace analytics system, comprising:

establishing an extent of known entities associated with the workspace analytics system;

receiving a user input including capturing input text, wherein the input text defines a natural language user query;

identifying, in the captured user input text, at least one entity included in the extent of the known entities associated with the workspace analytics system;

replacing the text in the captured user input text that corresponds to the identified entity with a neutralized, generic marker;

matching the received input text to one of a plurality of pattern-form questions which defines a jump target, and associating, for each one of a plurality of answer definitions, at least one or more pattern-form questions, wherein each answer definition has an associated jump target that defines a respective entry point into the workspace analytics system to provide information responsive to the associated one or more pattern-form questions; and

generating a response to the natural language user query by retrieving information from the workspace analytics system by referencing a link based on a selected jump target and the identified at least one entity, said method further comprising:

pre-processing the pattern-form questions according to a first predetermined strategy;

pre-processing the captured user input text according to a second predetermined strategy;

determining, for each pre-processed pattern-form question, a respective similarity to the pre-processed input text and generating a respective output score;

selecting one of the pre-processed pattern-form questions as a best match based on the determined output score;

determining the jump target based on the identity of the answer definition in which the selected best match pre-processed pattern form question resides.

2. The method of claim 1 wherein determining the similarity between the pre-processed pattern-form questions and the pre-processed user input text includes a first approach comprising determining a starting string similarity between the pre-processed pattern-form questions and pre-processed user input text and producing a starting similarity score.

3. The method of claim 2 further including a second approach that is performed when the first starting string similarity approach does not produce a match, as reflected by the starting similarity score, that exceeds a predetermined threshold.

4. The method of claim 3 wherein the second approach comprises determining a Dice Coefficient.

5. The method of claim 1 wherein the pre-processing of the captured user input text includes replacing at least one word identified in the user input text with a predetermined replacement word.

6. The method of claim 5 further comprising providing a configuration file that includes a synonym replacement list that defines replacement words associated with pattern words, wherein pattern words identified in the user input text are replaced by the corresponding replacement word as defined in the replacement list.

7. The method of claim 1 wherein the pre-processing of the captured user input text includes ignoring at least one word identified in the user input text.

8. The method of claim 7 further comprising providing a configuration file that includes an ignore word list that defines words to be ignored for matching purposes.

9. The method of claim 1 wherein pre-processing of the captured user input text comprises a cleaning operation to remove at least one of (i) trailing punctuation, (ii) whitespace between tokens, and (iii) any parameters.