Query suggestion for E-commerce sites
First Claim
1. A method for providing query suggestions for a user comprising:
- using a computer processor and storage,receiving a query log comprising a number of user sessions on an e-commerce site, the sessions including a plurality of sets of queries that have been executed by users of the e-commerce site during the user sessions, some of the sets of queries including query transitions, followed by a purchase related event;
cleaning and normalizing the query log;
generating from the cleaned and normalized query log stationary scores and transition scores of at least some of the plurality of sets, the transition scores comprising ordered query pairs;
building a set of query suggestions from the ordered query pairs;
computing similarity scores of at least some of the set of query suggestions to determine whether individual ones of the at least some of the set of query suggestions meet a predetermined assurance level;
including as elements of the set query suggestions that meet the predetermined assurance level; and
mixing and ranking the set of query suggestions in accordance with a user behavior that is to be optimized, the ranking comprising using a first weighting with a popularity score and a second weighting with a purchase efficiency score.
1 Assignment
0 Petitions
Accused Products
Abstract
Providing query suggestions using a query log including a number of user sessions that comprise training data including a sequence of a plurality of sets of queries. Some of the sets of queries include query transitions followed by a purchase related event. The query log is cleaned and normalized. Query log stationary scores and transition scores of at least some of the plurality of sets is generated. A set of query suggestions is built and similarity scores are computed for at least some of the set of query suggestions to determine whether individual ones of the at least some of the set of query suggestions meet a predetermined assurance level. Those that meet the level are included as elements of the set of query suggestions that meet the predetermined assurance level. That set of query suggestions are mixed and ranked in accordance with a user behavior sought to be optimized.
35 Citations
23 Claims
-
1. A method for providing query suggestions for a user comprising:
-
using a computer processor and storage, receiving a query log comprising a number of user sessions on an e-commerce site, the sessions including a plurality of sets of queries that have been executed by users of the e-commerce site during the user sessions, some of the sets of queries including query transitions, followed by a purchase related event; cleaning and normalizing the query log; generating from the cleaned and normalized query log stationary scores and transition scores of at least some of the plurality of sets, the transition scores comprising ordered query pairs; building a set of query suggestions from the ordered query pairs; computing similarity scores of at least some of the set of query suggestions to determine whether individual ones of the at least some of the set of query suggestions meet a predetermined assurance level; including as elements of the set query suggestions that meet the predetermined assurance level; and mixing and ranking the set of query suggestions in accordance with a user behavior that is to be optimized, the ranking comprising using a first weighting with a popularity score and a second weighting with a purchase efficiency score. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. A computer-readable storage device having embedded therein a set of instructions which, when executed by one or more processors of a computer, causes the computer to execute operations comprising:
-
receiving a query log comprising a number of user sessions on an e-commerce site, the sessions comprising a plurality of sets of queries that have been executed by users of the e-commerce site during the user sessions, some of the sets of queries including query transitions, followed by a purchase related event; cleaning and normalizing the query log; generating from the cleaned and normalized query log stationary scores and transition scores of at least some of the plurality of sets, the transition scores comprising ordered query pairs; building a set of query suggestions from the ordered query pairs; computing similarity scores of at least some of the set of query suggestions to determine whether individual ones of the at least some of the set of query suggestions meet a predetermined assurance level; including as elements of the set query suggestions that meet the predetermined assurance level; and mixing and ranking the set of query suggestions in accordance with a user behavior that is to be optimized, the ranking comprising using a first weighting with a popularity score and a second weighting with a purchase efficiency score. - View Dependent Claims (11, 12, 13, 14, 15, 16, 17, 18)
-
-
19. A system for providing query suggestions for a user comprising:
-
at least one hardware processor configured to include; a query log module configured to receive a query log comprising a number of user sessions on an e-commerce site, the sessions comprising training data including a sequence of a plurality of sets of queries that have been executed by users of the e-commerce site during the user sessions, some of the sets of queries including query transitions, followed by a purchase related event; a query log cleaning and normalization module configured to clean and normalize the query log using a cleaning and normalizing module; a scoring module configured to generate from the cleaned and normalized query log stationary scores and transition scores of at least some of the plurality of sets, the transition scores comprising ordered query pairs; a query suggestion build module configured to build a set of query suggestions from the ordered query pairs; a similarity computation module configured to compute similarity scores of at least some of the set of query suggestions to determine whether individual ones of the at least some of the sets of query suggestions meet a predetermined assurance level, the similarity computation module further configured to include as elements the set of query suggestions that meet the predetermined assurance level; and a recommendation compilation module configured to mix and rank the set of query suggestions in accordance with a user behavior that is to be optimized, the ranking comprising using a first weighting with a popularity score and a second weighting with a purchase efficiency score.
-
-
20. A method of generating suggestions for search, the method comprising:
-
using a computer processor and storage, mining user query activity from user activity history logs of user sessions on an e-commerce site; analyzing, and building a probability graph from a user query activity history log of user queries that have been executed by users of the e-commerce site during the user query activity which includes at least one of searches, Buy It Now actions, bids, ask seller a question, watches, views, and offers, wherein at least some queries are seen in the user query activity history log as a node on the graph, edges connecting the at least some queries are based on follow counts of queries in user sessions, and popularity of queries and user behavior in terms of engagement are properties seen as edges of the graph; and pruning the graph, based on edge properties to obtain the best neighbors for every query which improve popularity of queries and user behavior in terms of engagement. - View Dependent Claims (21, 22)
-
-
23. A computer-readable storage device having embedded therein a set of instructions which, when executed by one or more processors of a computer, causes the computer to execute operations for generating suggestions for search, the operations comprising:
-
mining user query activity comprising queries that have been executed by users of the e-commerce site during the user sessions from user query activity history logs of usage of the e-commerce site; analyzing, and building a probability graph from a user query activity history log which includes at least one of searches, Buy It Now actions, bids, ask seller a question, watches, views, and offers, wherein at least some queries being seen in the user query activity history log as a node on the graph, edges connecting the at least some queries are based on follow counts of queries in user sessions, and popularity of queries and user behavior in terms of engagement are properties seen as edges of the graph; and pruning the graph, based on edge properties to obtain the best neighbors for every query which improve popularity of queries and user behavior in terms of engagement.
-
Specification