US2023177579A1PendingUtilityA1

System and method for computing features that apply to infrequent queries

Assignee: EBAY INCPriority: Dec 30, 2015Filed: Jan 27, 2023Published: Jun 8, 2023
Est. expiryDec 30, 2035(~9.4 yrs left)· nominal 20-yr term from priority
G06N 20/00G06N 7/01G06F 16/3334G06Q 30/0623
62
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

In various example embodiments, a system and method compute an inferred query feature score for a query that can be used provide items in response to the query. A query is received, and query terms are identified from the query. A query feature score associated with each query term from the query is determined. An inferred query feature score for the query is determined based on the query feature scores for the query terms from the query. One or more items are returned as search results in response to the query based at least in part on the inferred query feature score for the query.

Claims

exact text as granted — not AI-modified
What is claimed is: 
     
         1 . A computer-implemented method comprising:
 receiving a query;   identifying query terms from the query;   determining query feature scores for the query terms from the query;   computing an inferred query feature score for the query based on the query feature scores for the query terms from the query; and   providing one or more items as search results in response to the query based at least in part on the inferred query feature score for the query.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the query feature score associated with each query term from the query comprises a category-query affinity for a category. 
     
     
         3 . The computer-implemented method of  claim 2 , wherein the inferred query feature score for the query comprises a category demand for the category. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein each query term from the query comprises an n-gram from the query. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein determining the query feature scores for the query terms from the query comprises:
 computing the query feature scores for the query terms using historical search information for previous queries containing each query term;   storing the query feature scores for the query terms in a dictionary, the dictionary being indexed by query terms; and   retrieving the query feature scores for the query terms from the dictionary.   
     
     
         6 . The computer-implemented method of  claim 5 , the computer-implemented method further comprising:
 determining the dictionary does not include a query feature score for the query.   
     
     
         7 . The computer-implemented method of  claim 1 , wherein providing the one or more items as search results in response to the query based at least in part on the inferred query feature score for the query further comprises ranking the one or more items based on the inferred query feature score. 
     
     
         8 . One or more computer storage media storing computer-useable instructions that, when used by a computing device, cause the computing device to perform operations, the operations comprising:
 receiving a query;   identifying query terms from the query;   determining query feature scores associated with the query terms from the query;   computing an inferred query feature score for the query based on the query feature scores for the query terms from the query; and   providing one or more items as search results in response to the query based at least in part on the inferred query feature score for the query.   
     
     
         9 . The one or more computer storage media of  claim 8 , wherein the query feature score associated with each query term from the query comprises a category-query affinity for a category. 
     
     
         10 . The one or more computer storage media of  claim 9 , wherein the inferred query feature score for the query comprises a category demand for the category. 
     
     
         11 . The one or more computer storage media of  claim 8 , wherein each query term from the query comprises an n-gram from the query. 
     
     
         12 . The one or more computer storage media of  claim 8 , wherein determining the query feature scores for the query terms from the query comprises:
 computing the query feature scores for the query terms using historical search information for previous queries containing each query term;   storing the query feature scores for the query terms in a dictionary, the dictionary being indexed by query terms; and   retrieving the query feature scores for the query terms from the dictionary.   
     
     
         13 . The one or more computer storage media of  claim 12 , the operations further comprising:
 determining the dictionary does not include a query feature score for the query.   
     
     
         14 . The one or more computer storage media of  claim 8 , wherein providing the one or more items as search results in response to the query based at least in part on the inferred query feature score for the query further comprises ranking the one or more items based on the inferred query feature score. 
     
     
         15 . A computer system comprising:
 a processor; and   a computer storage medium storing computer-useable instructions that, when used by the processor, causes the computer system to perform operations comprising: 
 receiving a query; 
 identifying query terms from the query; 
 determining query feature scores associated with the query terms from the query; 
 computing an inferred query feature score for the query based on the query feature scores for the query terms from the query; and 
 providing one or more items as search results in response to the query based at least in part on the inferred query feature score for the query. 
   
     
     
         16 . The computer system of  claim 15 , wherein the query feature score associated with each query term from the query comprises a category-query affinity for a category. 
     
     
         17 . The computer system of  claim 16 , wherein the inferred query feature score for the query comprises a category demand for the category. 
     
     
         18 . The computer system of  claim 15 , wherein each query term from the query comprises an n-gram from the query. 
     
     
         19 . The computer system of  claim 15 , wherein determining the query feature scores for the query terms from the query comprises:
 computing the query feature scores for the query terms using historical search information for previous queries containing each query term;   storing the query feature scores for the query terms in a dictionary, the dictionary being indexed by query terms; and   retrieving the query feature scores for the query terms from the dictionary.   
     
     
         20 . The computer system of  claim 19 , wherein the operations further comprise:
 determining the dictionary does not include a query feature score for the query.

Join the waitlist — get patent alerts

Track US2023177579A1 — get alerts on status changes and closely related new filings.

We store only your email — no account needed. See our privacy policy.