Identification of query patterns and related total statistics among search queries

摘要

In various embodiments, the features described herein contribute to preserving the confidentiality of the information when processing a search query and can provide n-gram categorization as private or private in a relatively low cost manner. Multiple query patterns may be generated based on a plurality of non-private n grams found in the search log of a private search query. Aggregate search activity statistics (“ASAS”) associated with each query pattern may be determined in the search log. The ASAS associated with each query pattern may indicate post-search activity associated with a plurality of private search queries in the search log that match the query pattern. In response to determining that the ASAS meets the performance criteria for a given query pattern,