Semantic decoding of user queries
First Claim
1. A method of performing semantic decoding of a user question presented in a speech utterance to a networked online natural language processing system to determine a meaning of the user question, the method comprising the steps of:
- (a) receiving a set of words forming the user question at the networked online natural language processing system;
wherein the user question can be associated with one or more known queries, and which known queries have a meaning that is understood by the networked online natural language processing system;
(b) determining a frequency of occurrence of one or more terms identified in the user question and in each of said one or more known queries;
(c) determining a percentage of terms which appear in the user question that also appear in each of said one or more known queries, including calculating a semantic similarity W between the user question (UQ) and each of said one or more known queries using a semantic dictionary, and computing a semantic distance between UQ (q) and a known query (d) as follows;
Sem(Tuq,Tr)=[I(uq,r)+I(r,uq)]/[Abs[Tuq]+Abs[Tr]]where I(uq,r) and I(r,uq) are values corresponding to the inverse semantic distances computed at a given sense and level of the semantic dictionary in both directions, and T is a term frequency metric;
(d) measuring a semantic similarity between said set of words in the user question, and a corresponding set of words in each of said one or more known queries;
(e) combining the results of steps (b) through (d) to identify which one of said one or more known queries is to be used in identifying the meaning of the user question.
1 Assignment
0 Petitions
Accused Products
Abstract
An intelligent query system for processing voiced-based queries is disclosed, which uses semantic based processing to identify the question posed by the user by understanding the meaning of the user'"'"'s utterance. Based on identifying the meaning of the utterance, the system selects a single answer that best matches the user'"'"'s query. The answer that is paired to this single question is then retrieved and presented to the user. The system, as implemented, accepts environmental variables selected by the user and is scalable to provide answers to a variety and quantity of user-initiated queries.
434 Citations
14 Claims
-
1. A method of performing semantic decoding of a user question presented in a speech utterance to a networked online natural language processing system to determine a meaning of the user question, the method comprising the steps of:
-
(a) receiving a set of words forming the user question at the networked online natural language processing system; wherein the user question can be associated with one or more known queries, and which known queries have a meaning that is understood by the networked online natural language processing system; (b) determining a frequency of occurrence of one or more terms identified in the user question and in each of said one or more known queries; (c) determining a percentage of terms which appear in the user question that also appear in each of said one or more known queries, including calculating a semantic similarity W between the user question (UQ) and each of said one or more known queries using a semantic dictionary, and computing a semantic distance between UQ (q) and a known query (d) as follows;
Sem(Tuq,Tr)=[I(uq,r)+I(r,uq)]/[Abs[Tuq]+Abs[Tr]]where I(uq,r) and I(r,uq) are values corresponding to the inverse semantic distances computed at a given sense and level of the semantic dictionary in both directions, and T is a term frequency metric; (d) measuring a semantic similarity between said set of words in the user question, and a corresponding set of words in each of said one or more known queries; (e) combining the results of steps (b) through (d) to identify which one of said one or more known queries is to be used in identifying the meaning of the user question. - View Dependent Claims (2, 3, 4, 5, 6)
-
-
7. A system for performing semantic decoding of a user question presented in a speech utterance, comprising:
a natural language engine running on a server computing system connected to a communications network, the natural language engine being configured and adapted to receive a set of words forming the user question, receive or access one or more known queries associated with the user question or the set of words, each of the one or more known queries having a meaning known to the natural language engine, use a statistically-based processing routine to determine whether two or more known queries potentially correspond with the user question or the set of words, and if the statistically-based processing routine determines that two or more known queries potentially correspond with the user question or the set of words, (a) determine a frequency of occurrence of one or more terms identified in the user question and in each of the one or more known queries, (b) determine a percentage of terms which appear in the user question that also appear in each of the one or more known queries, (c) measure a semantic similarity between the set of words in the user question and a corresponding set of words in each of the one or more known queries using a semantic dictionary, and combine the results of (a)-(c) by calculating a combined metric to determine which of the one or more known queries is to be used in identifying the meaning of the user question, and if the statistically-based processing routine determines that only one known query potentially corresponds with the user question or the set of words, use the corresponding known query to identify the meaning of the user question. - View Dependent Claims (8, 9, 10, 11)
-
12. A method of performing semantic decoding of a user question presented in a speech utterance to a networked online natural language processing system to determine a meaning of the user question, the method comprising the steps of:
-
(a) receiving a set of words forming the user question at the networked online natural language processing system; wherein the user question can be associated with one or more known queries, and the known queries have a meaning that is understood by the networked online natural language processing system; (b) determining a frequency of occurrence of one or more terms identified in the user question and in each of said one or more known queries; (c) determining a percentage of terms which appear in the user question that also appear in each of said one or more known queries; (d) measuring a semantic similarity between said set of words in the user question, and a corresponding set of words in each of said one or more known queries using a semantic dictionary that organizes words based on hyponymy; (e) calculating a combined metric based on the results of steps (b)-(d) and a corresponding set of weighing factors to identify which one of said one or more known queries is to be used in identifying the meaning of the user question. - View Dependent Claims (13, 14)
-
Specification