公开(公告)号：US08682901B1

公开(公告)日：2014-03-25

申请号：US13332278

申请日：2011-12-20

申请人： Pei Cao ,  Nadav Eiron ,  Soham Mazumdar ,  Anna L. Patterson ,  Russell Power ,  Yonatan Zunger

发明人： Pei Cao ,  Nadav Eiron ,  Soham Mazumdar ,  Anna L. Patterson ,  Russell Power ,  Yonatan Zunger

IPC分类号： G01F7/00

CPC分类号： G06F17/30336 ,  G06F17/30011 ,  G06F17/30616 ,  G06F17/30864 ,  Y10S707/99931

摘要： 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.

摘要翻译： 信息检索系统使用短语来索引，检索，组织和描述文档。 短语从文档集中提取。 文件根据所包含的短语索引，使用短语发布列表。 短语发布列表存储在索引服务器的集群中。 短语列表可以分组成分组，并分成分区。 查询中的短语是根据可能的短语来确定的。 从短语中创建基于短语的查询调度，然后进行优化，以减少查询处理和通信成本。 管理查询调度的执行以进一步减少或消除索引服务器中的各个查询处理操作。

公开(公告)号：US08090723B2

公开(公告)日：2012-01-03

申请号：US12716008

申请日：2010-03-02

申请人： Pei Cao ,  Nadav Eiron ,  Soham Mazumdar ,  Anna L. Patterson ,  Russell Power ,  Yonatan Zunger

发明人： Pei Cao ,  Nadav Eiron ,  Soham Mazumdar ,  Anna L. Patterson ,  Russell Power ,  Yonatan Zunger

IPC分类号： G06F7/00

CPC分类号： G06F17/30336 ,  G06F17/30011 ,  G06F17/30616 ,  G06F17/30864 ,  Y10S707/99931

摘要： 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.

摘要翻译： 信息检索系统使用短语来索引，检索，组织和描述文档。 短语从文档集中提取。 文件根据所包含的短语索引，使用短语发布列表。 短语发布列表存储在索引服务器的集群中。 短语列表可以分组成分组，并分成分区。 查询中的短语是根据可能的短语来确定的。 从短语中创建基于短语的查询调度，然后进行优化，以减少查询处理和通信成本。 管理查询调度的执行以进一步减少或消除索引服务器中的各个查询处理操作。

公开(公告)号：US20100161617A1

公开(公告)日：2010-06-24

申请号：US12716008

申请日：2010-03-02

申请人： Pei Cao ,  Nadav Eiron ,  Soham Mazumdar ,  Anna L. Patterson ,  Russell Power ,  Yonatan Zunger

发明人： Pei Cao ,  Nadav Eiron ,  Soham Mazumdar ,  Anna L. Patterson ,  Russell Power ,  Yonatan Zunger

IPC分类号： G06F17/30

CPC分类号： G06F17/30336 ,  G06F17/30011 ,  G06F17/30616 ,  G06F17/30864 ,  Y10S707/99931

摘要： 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.

摘要翻译： 信息检索系统使用短语来索引，检索，组织和描述文档。 短语从文档集中提取。 文件根据所包含的短语索引，使用短语发布列表。 短语发布列表存储在索引服务器的集群中。 短语列表可以分组成分组，并分成分区。 查询中的短语是根据可能的短语来确定的。 从短语中创建基于短语的查询调度，然后进行优化，以减少查询处理和通信成本。 管理查询调度的执行以进一步减少或消除索引服务器中的各个查询处理操作。

公开(公告)号：US07693813B1

公开(公告)日：2010-04-06

申请号：US11694780

申请日：2007-03-30

申请人： Pei Cao ,  Nadav Eiron ,  Soham Mazumdar ,  Anna Patterson ,  Russell Power ,  Yonatan Zunger

发明人： Pei Cao ,  Nadav Eiron ,  Soham Mazumdar ,  Anna Patterson ,  Russell Power ,  Yonatan Zunger

IPC分类号： G06F17/30

CPC分类号： G06F17/30336 ,  G06F17/30011 ,  G06F17/30616 ,  G06F17/30864 ,  Y10S707/99931

摘要： 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.

摘要翻译： 信息检索系统使用短语来索引，检索，组织和描述文档。 短语从文档集中提取。 文件根据所包含的短语索引，使用短语发布列表。 短语发布列表存储在索引服务器的集群中。 短语列表可以分组成分组，并分成分区。 查询中的短语是根据可能的短语来确定的。 从短语中创建基于短语的查询调度，然后进行优化，以减少查询处理和通信成本。 管理查询调度的执行以进一步减少或消除索引服务器中的各个查询处理操作。

公开(公告)号：US08086594B1

公开(公告)日：2011-12-27

申请号：US11694797

申请日：2007-03-30

申请人： Pei Cao ,  Soham Mazumdar ,  Vaibhav Mehta ,  Yonatan Zunger

发明人： Pei Cao ,  Soham Mazumdar ,  Vaibhav Mehta ,  Yonatan Zunger

IPC分类号： G60F17/30

CPC分类号： G06F17/30616

摘要： 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.

摘要翻译： 信息检索系统使用短语来索引，检索，组织和描述文档。 短语从文档集中提取。 文件根据所包含的短语索引，使用短语发布列表。 短语发布列表存储在索引服务器的集群中。 短语列表可以分组成分组，并分成分区。 查询中的短语是根据可能的短语来确定的。 从短语中创建基于短语的查询调度，然后进行优化，以减少查询处理和通信成本。 管理查询调度的执行以进一步减少或消除索引服务器中的各个查询处理操作。

公开(公告)号：US07925655B1

公开(公告)日：2011-04-12

申请号：US11694802

申请日：2007-03-30

申请人： Russell Power ,  Soham Mazumdar ,  Yonatan Zunger

发明人： Russell Power ,  Soham Mazumdar ,  Yonatan Zunger

IPC分类号： G06F17/30

CPC分类号： G06F17/30675

摘要： 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.

摘要翻译： 信息检索系统使用短语来索引，检索，组织和描述文档。 短语从文档集中提取。 文件根据所包含的短语索引，使用短语发布列表。 短语发布列表存储在索引服务器的集群中。 短语列表可以分组成分组，并分成分区。 查询中的短语是根据可能的短语来确定的。 从短语中创建基于短语的查询调度，然后进行优化，以减少查询处理和通信成本。 管理查询调度的执行以进一步减少或消除索引服务器中的各个查询处理操作。

公开(公告)号：US09355169B1

公开(公告)日：2016-05-31

申请号：US13615541

申请日：2012-09-13

申请人： Soham Mazumdar ,  Viktor Przebinda ,  Yonatan Zunger

发明人： Soham Mazumdar ,  Viktor Przebinda ,  Yonatan Zunger

IPC分类号： G06F17/30

CPC分类号： G06F17/30616 ,  G06F17/30864

摘要： 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.

公开(公告)号：US08402033B1

公开(公告)日：2013-03-19

申请号：US13274238

申请日：2011-10-14

申请人： Soham Mazumdar ,  Viktor Przebinda ,  Yonatan Zunger

发明人： Soham Mazumdar ,  Viktor Przebinda ,  Yonatan Zunger

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30616 ,  G06F17/30864

摘要： 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.

摘要翻译： 信息检索系统使用短语来索引，检索，组织和描述文档。 短语从文档集中提取。 文件根据所包含的短语索引，使用短语发布列表。 短语发布列表存储在索引服务器的集群中。 短语列表可以分组成分组，并分成分区。 查询中的短语是根据可能的短语来确定的。 从短语中创建基于短语的查询调度，然后进行优化，以减少查询处理和通信成本。 管理查询调度的执行以进一步减少或消除索引服务器中的各个查询处理操作。

公开(公告)号：US08166045B1

公开(公告)日：2012-04-24

申请号：US11694792

申请日：2007-03-30

申请人： Soham Mazumdar ,  Viktor Przebinda ,  Yonatan Zunger

发明人： Soham Mazumdar ,  Viktor Przebinda ,  Yonatan Zunger

IPC分类号： G06F7/00 ,  G06F17/30

CPC分类号： G06F17/30616 ,  G06F17/30864

摘要： 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.

摘要翻译： 信息检索系统使用短语来索引，检索，组织和描述文档。 短语从文档集中提取。 然后根据所包含的短语，使用短语发布列表将文档编入索引。 短语发布列表存储在索引服务器的集群中。 短语列表可以分组成分组，并分成分区。 查询中的短语是根据可能的短语来确定的。 从短语中创建基于短语的查询调度，然后进行优化，以减少查询处理和通信成本。 管理查询调度的执行以进一步减少或消除索引服务器中的各个查询处理操作。

公开(公告)号：US08600975B1

公开(公告)日：2013-12-03

申请号：US13442317

申请日：2012-04-09

申请人： Pei Cao ,  Soham Mazumdar

发明人： Pei Cao ,  Soham Mazumdar

IPC分类号： G06F17/30

CPC分类号： G06F17/30616 ,  G06F17/2775

摘要： 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.

摘要翻译： 信息检索系统使用短语来索引，检索，组织和描述文档。 短语从文档集中提取。 文件根据所包含的短语索引，使用短语发布列表。 短语发布列表存储在索引服务器的集群中。 短语列表可以分组成分组，并分成分区。 查询中的短语是根据可能的短语来确定的。 从短语中创建基于短语的查询调度，然后进行优化，以减少查询处理和通信成本。 管理查询调度的执行以进一步减少或消除索引服务器中的各个查询处理操作。