SYSTEMS AND METHODS FOR INTERPRETING NATURAL LANGUAGE SEARCH QUERIES
Systems and methods are described herein for interpreting natural language search queries that account for contextual relevance of words of the search query that would ordinarily not be processed, including, for example, processing each word of the query. Each term or phrase is associated with a respective part of speech, and a frequency of occurrence of a combination of adjacent terms or phrases public domain is determined. A relevance of each term is then determined based on its respective type of term and frequency of occurrence in the public domain. The natural language search query is then interpreted based on the importance or relevance of each term.
1 .- 32 . (canceled)
33 . A method comprising:
receiving a natural language search query;
identifying a plurality of terms in the natural language search query;
comparing each of the plurality of terms to a relevant words list;
identifying, based on the relevant words list, a first term type of a first term of the plurality of terms and a second term type of a second term of the plurality of terms, wherein the first term type is different than the second term type;
performing a first search for the first term in a public domain based on the first term type and a second search for the second term in the public domain based on the second term type to retrieve search results; and
generating for display the search results.
34 . The method of claim 33 , wherein performing the first search for the first term in a public domain based on the first term type comprises performing a search for a metadata type that matches the first term type, and performing the second search for the second term in a public domain based on the second term type comprises performing a search for a metadata type that matches the second term type.
35 . The method of claim 33 , further comprising:
determining a respective frequency with which the second term immediately follows the first term of the plurality of terms in metadata describing a plurality of content items;
determining a relevance for each term of the plurality of terms based on its respective term type and frequency; and
interpreting the natural language search query based on the relevance of each term.
36 . The method of claim 35 , wherein determining the respective frequency with which the second term immediately follows the first term of the plurality of terms in metadata describing a plurality of content items comprises:
retrieving the metadata describing the plurality of content items; and
counting the total occurrences of the second term immediately following the first term contained in the metadata.
37 . The method of claim 33 , wherein the natural language search query is received as audio data, and the method further comprises transcribing the natural language search query into a plurality of words.
38 . The method of claim 33 , wherein the first term type and the second term type are based on the frequency of occurrence of the first term and the second term within a database.
39 . The method of claim 33 , wherein identifying a plurality of terms in the natural language search query further comprises:
splitting the natural language search query into a plurality of words;
analyzing a first word of the plurality of words;
determining, based on analyzing the first word, whether the first word can be part of the first term type;
in response to determining that the first word can be part of the first term type, analyzing the first word together with a second word that immediately follows the first word;
determining, based on analyzing the first word together with the second word, whether the first word and the second word can be analyzed using the first term type; and
in response to determining that the first word and the second word can be analyzed using the first term type, identifying the first and second word as associated with the first term type.
40 . The method of claim 33 , wherein the term type is selected from a keyword, a genre, and content type.
41 . The method of claim 33 , further comprising:
generating a respective vector for each term of the plurality of terms;
accessing a knowledge graph associated with content metadata;
identifying a plurality of terms to which each term of the plurality of terms connects in the knowledge graph;
calculating a distance between each respective term and each term connected to the respective term; and
generating the vector for each term based on connections of each respective term and the distance between each respective term and each term to which each respective term is connected.
42 . The method of claim 33 , wherein the relevant words list comprises at least one of a dictionary, a word list, and a phrase list.
43 . A system for interpreting a natural language search query, the system comprising control circuitry configured to:
receive a natural language search query;
identify a plurality of terms in the natural language search query;
compare each of the plurality of terms to a relevant words list;
identify, based on the relevant words list, a first term type of a first term of the plurality of terms and a second term type of a second term of the plurality of terms, wherein the first term type is different than the second term type;
perform a first search for the first term in a public domain based on the first term type and a second search for the second term in the public domain based on the second term type to retrieve search results; and
generate for display the search results.
44 . The system of claim 43 , wherein performing the first search for the first term in a public domain based on the first term type comprises performing a search for a metadata type that matches the first term type, and performing the second search for the second term in a public domain based on the second term type comprises performing a search for a metadata type that matches the second term type.
45 . The system of claim 43 , wherein the control circuitry is further configured to:
determine a respective frequency with which the second term immediately follows the first term of the plurality of terms in metadata describing a plurality of content items;
determine a relevance for each term of the plurality of terms based on its respective term type and frequency; and
interpret the natural language search query based on the relevance of each term.
46 . The system of claim 45 , wherein determining the respective frequency with which the second term immediately follows the first term of the plurality of terms in metadata describing a plurality of content items comprises:
retrieving the metadata describing the plurality of content items; and
counting the total occurrences of the second term immediately following the first term contained in the metadata.
47 . The system of claim 43 , wherein the natural language search query is received as audio data, and wherein the control circuitry is further configured to transcribe the natural language search query into a plurality of words.
48 . The system of claim 43 , wherein the first term type and the second term type are based on the frequency of occurrence of the first term and the second term within a database.
49 . The system of claim 43 , wherein identifying a plurality of terms in the natural language search query further comprises:
splitting the natural language search query into a plurality of words;
analyzing a first word of the plurality of words;
determining, based on analyzing the first word, whether the first word can be part of the first term type;
in response to determining that the first word can be part of the first term type, analyzing the first word together with a second word that immediately follows the first word;
determining, based on analyzing the first word together with the second word, whether the first word and the second word can be analyzed using the first term type; and
in response to determining that the first word and the second word can be analyzed using the first term type, identifying the first and second word as associated with the first term type.
50 . The system of claim 43 , wherein the term type is selected from a keyword, a genre, and content type.
51 . The system of claim 43 , wherein the control circuitry is further configured to:
generate a respective vector for each term of the plurality of terms;
access a knowledge graph associated with content metadata;
identify a plurality of terms to which each term of the plurality of terms connects in the knowledge graph;
calculate a distance between each respective term and each term connected to the respective term; and
generate the vector for each term based on connections of each respective term and the distance between each respective term and each term to which each respective term is connected.
52 . The method of claim 33 , wherein the relevant words list comprises at least one of a dictionary, a word list, and a phrase list.