US 8,943,067 B1 · Index server architecture using tiered and sharded phrase posting lists

Abstract

An information retrieval system uses phrases to index, retrieve, organize and describe documents. Phrases are extracted from the document collection. Documents are the indexed according to their included phrases, using phrase posting lists. The phrase posting lists are stored in an cluster of index servers. The phrase posting lists can be tiered into groups, and sharded into partitions. Phrases in a query are identified based on possible phrasifications. A query schedule based on the phrases is created from the phrases, and then optimized to reduce query processing and communication costs. The execution of the query schedule is managed to further reduce or eliminate query processing operations at various ones of the index servers.

Claims13

Dependent claims

A computer system comprising:

at least one processor;
a first tier in first memory;
a second tier in second memory, the second memory having lower processing performance than the first memory;
a third tier in third memory, the third memory having lower processing performance than the second memory;
and
memory storing instructions that, when executed by the at least one processor, cause the computer system to perform operations comprising:
determining a quantity of documents associated with a phrase in a phrase-based index,
assigning the phrase to the first tier when the quantity meets a first threshold,
assigning the phrase to the third tier when the quantity fails to meet a second threshold, and
assigning the phrase to the second tier when the quantity fails to meet the first threshold but meets the second threshold,
wherein the phrase is assigned to only one tier of the three tiers.

8 more elements

Dependencies are inferred from the claim text.

Facts

Application

13/842,731Filed 15 Mar 2013 · continuation

Priority

30 Mar 2007

Granted

27 Jan 2015

Term ends

Not estimatedThe source records don’t support an estimate.

Classification8 codes

G06F 16/2272
Indexing structures: management thereof
G06F 16/313
Indexing; Data structures therefor; Storage structures: selection or weighting of terms for indexing
G06F 16/93
Details of database functions independent of the retrieved data types: document management systems
G06F 16/951
Retrieval from the web: indexing; Web crawling techniques

Family

Application11/694,780Parent of this continuation · filed 30 Mar 2007

Application12/716,008Parent of this continuation · filed 2 Mar 2010

US 7,693,813 B1Parent of this continuation · filed 6 Apr 2010

US 8,090,723 B2Parent of this continuation · filed 24 Jun 2010

Application13/332,278Parent of this continuation · filed 20 Dec 2011

US 8,682,901 B1Parent of this continuation

US 2010/0161617 A1Published application

US 8,943,067 B1This patent

From the US filing history. Foreign family members aren’t listed.

Index server architecture using tiered and sharded phrase posting lists

Life of this patent

Index server architecture using tiered and sharded phrase posting lists

Life of this patent

Abstract

Claims13