CONCEPT-BASED SEARCH AND CATEGORIZATION
A system and method for concept-based search and categorization that uses a lexical database to take a search term and from this to build a set of concepts and related terms and then searches stemmed or lemmatized text from a call transcription, email or chat message to perform categorization based on these concepts.
1 . A system for concept-based search and categorization, comprising:
a network-connected media server computer comprising at least a processor, a memory, and a plurality of programming instructions stored in the memory, the programming instructions, when executed by the processor, cause the processor to:
receive an interaction via a network,
produce a full-text transcript of the interaction's content, and
store the full-text transcript in a searchable database;
a network-connected concept-based search engine comprising at least another processor, another memory, and another plurality of programming instructions stored in the another its memory, the another plurality of programming instructions, when executed by the another processor, cause the another processor to:
create a plurality of search terms from the full-text transcript retrieved from the searchable database;
perform a plurality of stemming or lemmatizing operations on the plurality of search terms;
query a lexical database via the network using the plurality of search terms to find a plurality of additional search terms, the plurality of additional search terms related and similar to the plurality of search terms;
expand, using the plurality of additional search terms, the plurality of search terms into an expanded search query;
search at least a portion of the searchable database based at least in part on the expanded search query to create a plurality of search results; and
produce a stemmed or lemmatized transcript based on at least a portion of the plurality of search results;
store the stemmed or lemmatized transcript in the searchable database.
2 . A method for concept-based search and categorization, comprising the steps of:
at a network-connected media server computer comprising at least a processor, a memory, and a plurality of programming instructions stored in the memory, the programming instructions, when executed by the processor, cause the processor to process interactions:
receiving an interaction;
producing a full-text transcript based at least in part on the received interaction; and
storing the full-text transcript in a searchable database;
at a network-connected concept-based search engine comprising at least another processor, another memory, and another plurality of programming instructions stored in the another memory and operating on the another processor:
creating a plurality of search terms from the full-text transcript retrieved from the searchable database;
performing stemming or lemmatizing operations on at least a portion of the stored full-text transcript;
querying a lexical database via the network using the plurality of search terms to find a plurality of additional search terms, the plurality of additional search terms related and similar to the plurality of search terms;
expanding, using the plurality of additional search terms, the plurality of search terms into an expanded search query;
searching at least a portion of the searchable database based at least in part on the expanded search query to create a plurality of search results;
producing a stemmed or lemmatized transcript based on at least a portion of the plurality of search results;
storing stemmed or lemmatized transcript in the searchable database.
3 . (canceled)