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

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

• receiving a user input from a user including capturing input text, wherein the input text defines a natural language user query;
• matching the received input text to one of a plurality of predefined pattern-form questions defined in and using a first, local entity matcher executing in a first computer at a first location, wherein the matching is further performed in and using a second, cloud entity matcher executing in a second computer at a second location when the first local entity matcher does not find a match having a confidence level exceeding a predetermined threshold;
• selecting a jump target that is associated with the matched pattern-form question;
• generating a response to the natural language user query by retrieving information from the workspace analytics system by referencing a link that is based on at least the selected jump target, wherein the workspace analytics system has associated therewith a first extent of known entities, said method further comprising identifying, in the captured user input text, at least one entity in the first extent of known entities, using the first, local entity matcher, said method further comprising establishing the first extent of known entities in the workspace analytics system includes defining one or more matcher definitions wherein each matcher definition is associated with an entity type, and retrieving from the workspace analytics system, for each matcher definition, a respective set of values for the entity type.

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

• receiving a user input from a user including capturing input text, wherein the input text defines a natural language user query;
• matching the received input text to one of a plurality of predefined pattern-form questions defined in and using a first, local entity matcher executing in a first computer at a first location, wherein the matching is further performed in and using a second, cloud entity matcher executing in a second computer at a second location when the first local entity matcher does not find a match having a confidence level exceeding a predetermined threshold;
• selecting a jump target that is associated with the matched pattern-form question;
• generating a response to the natural language user query by retrieving information from the workspace analytics system by referencing a link that is based on at least the selected jump target said method further comprising detecting an entity contained in the user input text and replacing the text corresponding to the detected entity with a neutralized, generic marker.