Microsoft Technology Licensing, LLC

Tapas Kumar Nayak

Nimish S Khanolkar

Feng Tian

Stefan Isbein Larimore

Denis Churin

Amit Dilip Ghosh

Jingwei Lu

Vineet Garhewal

Sundaram Narayanan

Methods, systems, and computer program products are described herein for updating big data tables using snapshot isolation. The tables may store data (e.g., as data objects) collected from different users. The tables are stored in a first data store. The data's metadata is stored in a second data store. The metadata comprises version numbers for the objects that correspond to a consistent version thereof. When an update process for the table is initiated, a coordinator locks the metadata, and. the objects are updated. If the update to the objects is successful, the coordinator commits the updates and obtains the new version numbers of the objects. If all the commits are successful, the coordinator atomically updates the metadata with the new version numbers and releases the lock. However, if a commit to an object is unsuccessful, a subsequent process rolls back the committed objects to the version numbers specified by the metadata.

Techniques for updating big data tables using snapshot isolation

The present invention relates to an integrated full-text search architecture that integrates full text search with database server applications in a tight manner so that it becomes part of the server in all aspects including storage, metadata, query processing, back/up restore and resource management. This provides improved performance with respect to queries as well as improved manageability. Furthermore, the subject architecture is open and schema directed unlike other conventional full-text search architectures. Accordingly, the full-text search architecture enables expert users (e.g., search providers) to define their own index structures as well as ranking algorithms.

Integrated full text search system and method

Detailed herein is a technology which, among other things, allows a search engine to utilize a user-defined relevance function. In one approach to the technology, a method of applying a user-defined relevance function is described. In this approach, a complex search query is decomposed into a simple operator. The simple operator is associated with the user-defined relevance function. A document which matches the search query is retrieved, and a rank is calculated for the document, using the user-defined relevance function.

User-defined relevance ranking for search

Special lists can be used to perform fast ranked searching of documents containing key terms. The special lists are distinguished from basic inverted indices because they contain a ranking of only a predetermined number of documents that may be identified in the index. During a search, search engines can utilize the special lists to perform fast ranked searching without having to redundantly search through the entire corpus or index of documents available to the search engine. Rather, the search engine can search only the documents listed in the special list, thereby saving the time and resources required to perform the search. The search engine can also be configured to search a combination of the special lists and the index to provide users selective control over the balance between the accuracy and speed of the search.

Fast ranked full-text searching

A full-text search index system and method is generated by creating instances of a database index from an in-memory inverted list of keywords associated with a text identifier and the occurrences of the keyword in the text. Instances of the index are placed in a priority queue. A merge scheduling process determines when a merge should be initiated, selects instances of the index to be merged and selects a type of merge to perform. Instances of an index are assigned a temporal indicator (timestamp). A set of instances is selected to be merged. The set of instances is validated and merged.

Performant and scalable merge strategy for text indexing

The subject invention pertains to database reverse query matching. A text document can be received and analyzed to determine which, if any, queries the document matches. To enable such functionality, a number of intermediate structures such as tables are generated in accordance with designated queries. In particular, a canonical table can be generated that specifies the expressions or phrases as well as match rules. Furthermore, a Boolean table can be generated that specifies the Boolean relationship of expressions in canonical table. A match component or methodology can match text phrases to query phrases identified by the canonical table. An evaluation component or related methodology can subsequently utilize the Boolean table to determine if the preliminary phrase matches match the query logic.

Database reverse query matching

A full-text search index system and method is generated by creating instances of a database index from an in-memory inverted list of keywords associated with a text identifier and the occurrences of the keyword in the text. Instances of the index are placed in a priority queue. A merge scheduling process determines when a merge should be initiated, selects instances of the index to be merged and selects a type of merge to perform.

Growing community of inventors

Redmond, WA, United States of America

Tapas Kumar Nayak