Method and system for enhanced query term suggestion
Method, system, and programs for providing enhanced query term suggestions. Candidate query terms may be obtained based on a prefix of incomplete query terms received. The candidate query terms may be ranked, at least partially based on, their similarities with respect to query terms previously entered in the same search session as the incomplete query term. In some implementations, for determining such similarities, feature vectors and/or signatures may be stored in association with query terms. Similarity between a candidate query term and query terms in the same search session as the incomplete query term may be determined using the feature vectors and/or signatures associated therewith.
1. A method, implemented on a machine having at least one processor, storage, and a communication platform connected to a network, for providing query term suggestions, the method comprising:
receiving, in a first search session, a prefix of a query term from a user;
obtaining two or more query terms that have been previously entered by the user within the first search session;
obtaining one or more candidate query terms based on the prefix;
determining, for each of the candidate query terms, a similarity between the candidate query term and the two or more query terms by:
obtaining, for the candidate query term, a first feature vector having one or more features associated with the candidate query term;
obtaining, for each of the two or more query terms, a second feature vector having one or more features associated with the query term;
determining a similarity between the first feature vector and each second feature vector; and
aggregating the similarities between the candidate query term and the two or more query terms to generate an aggregated similarity indicative of a degree of similarity between the candidate query term and the two or more query terms;
ranking the one or more candidate query terms based, at least partially, on the aggregated similarity associated with each candidate query term; and
providing the one or more candidate query terms as query suggestions to the user based on the rankings of the candidate query terms.
2. The method of claim 1 , wherein the first search session corresponds to a period of time determined based on a point of time when the prefix of the query term is received from the user and a pre-determined time period.
3. The method of claim 1 , wherein the first search session corresponds to a period of time determined based on a predetermined number of query terms entered by the user before the user enters the prefix of the query term.
4. The method of claim 1 , wherein:
each of the first feature vectors has the one or more features with respect to a second search session; and
each of the second feature vectors has the one or more features with respect to the first search session.
5. The method of claim 4 , wherein the similarity between the first feature vector and each second feature vector is determined based on at least one of a cosine distance, a hamming distance, and a Euclidean distance between the first and second feature vectors.
6. The method of claim 4 , wherein the aggregated similarity is obtained based on a function, including one of a summation function, a weighted sum function, and an average function.
7. The method of claim 6 , wherein a weight in a weighted sum associated with a similarity between a candidate query term and one of the query terms from the first search session is determined based on a distance between the query term in the first search session and the prefix.
8. A system configured for providing query term suggestions, the system comprising:
storage;
a communication platform connected to a network; and
one or more processors programmed to execute one or more computer program instructions that, when executed, cause the one or more processors to:
receive, in a first search session, a prefix of a query term from a user;
obtain one or more candidate query terms based on the prefix;
obtain two or more query terms that have been previously entered by the user within the first search session;
determine, for each of the candidate query terms, a similarity between the candidate query term and the two or more query terms by:
obtaining, for the candidate query term, a first feature vector having one or more features associated with the candidate query term;
obtaining, for each of the two or more query terms, a second feature vector having one or more features associated with the query term;
determining a similarity between the first feature vector and each second feature vector; and
aggregating the similarities between the candidate query term and the two or more query terms to generate an aggregated similarity indicative of a degree of similarity between the candidate query term and the two or more query terms;
rank the one or more candidate query terms based, at least partially, on the aggregated similarity associated with each candidate query term; and
provide the one or more candidate query terms as query suggestions to the user based on the rankings of the candidate query terms.
9. The system of claim 8 , wherein the first search session corresponds to a period of time determined based on a point of time when the prefix of the query term is received from the user and a pre-determined time period.
10. The system of claim 8 , wherein the first search session corresponds to a period of time determined based on a predetermined number of query terms entered by the user before the user enters the prefix of the query term.
11. The system of claim 8 , wherein:
each of the first feature vectors has the one or more features with respect to a second search session; and
each of the second feature vectors has the one or more features with respect to the first search session.
12. The system of claim 11 , wherein the similarity between the first feature vector and each second feature vector is determined based on at least one of a cosine distance, a hamming distance, and a Euclidean distance between the first and second feature vectors.
13. The system of claim 11 , wherein the aggregated similarity is obtained based on a function, including one of a summation function, a weighted sum function, and an average function.
14. The system of claim 13 , wherein a weight in a weighted sum associated with a similarity between a candidate query term and one of the query terms from the first search session is determined based on a distance between the query term in the first search session and the prefix.
15. A machine-readable, non-transitory and tangible medium having data recorded thereon for providing search term suggestions, the medium, when read by the machine, causes the machine to perform the following:
receiving, in a first search session, a prefix of a query term from a user;
obtaining two or more query terms that have been previously entered by the user within the first search session;
obtaining one or more candidate query terms based on the prefix;
determining, for each of the candidate query terms, a similarity between the candidate query term and the two or more query terms by:
obtaining, for the candidate query term, a first feature vector having one or more features associated with the candidate query term;
obtaining, for each of the two or more query terms, a second feature vector having one or more features associated with the query term;
determining a similarity between the first feature vector and each second feature vector; and
aggregating the similarities between the candidate query term and the two or more query terms to generate an aggregated similarity indicative of a degree of similarity between the candidate query term and the two or more query terms;
ranking the one or more candidate query terms based, at least partially, on the aggregated similarity associated with each candidate query term; and
providing the one or more candidate query terms as query suggestions to the user based on the rankings of the candidate query terms.
16. The machine-readable, non-transitory and tangible medium of claim 15 , wherein the first search session corresponds to a period of time determined based on a point of time when the prefix of the query term is received from the user and a pre-determined time period.
17. The machine-readable, non-transitory and tangible medium of claim 15 , wherein the first search session corresponds to a period of time determined based on a predetermined number of query terms entered by the user before the user enters the prefix of the query term.
18. The machine-readable, non-transitory and tangible medium of claim 15 , wherein:
each of the first feature vectors has the one or more features with respect to a second search session;
each of the second feature vectors has the one or more features with respect to the first search.
19. The machine-readable, non-transitory and tangible medium of claim 18 , wherein the similarity between the first feature vector and each second feature vector is determined based on at least one of a cosine distance, a hamming distance, and a Euclidean distance between the first and second feature vectors.
20. The machine-readable, non-transitory and tangible medium of claim 18 , wherein the aggregated similarity is obtained based on a function, including one of a summation function, a weighted sum function, and an average function.