Microsoft Technology Licensing, LLC

Frederic H Behr, Jr

Kuansan Wang

Xiaolong Li

Zijian Zheng

Jiangbo Miao

Ahmed Hassan Awadallah

Imed Zitouni

Randall Kern

Robert C Wang

Yu Fan Chen

Toby H Walker

Michael D Hintze

Kimberly J Howell

Described herein are technologies pertaining to determining which search engine results page (SERP), from a plurality of SERPs, is preferable to a user. A query is received, and multiple SERPS are retrieved based upon the query, wherein the multiple SERPs are generated independently from one another. Values of features of the query and the multiple SERPs are obtained, and a determination as to which of the SERPs from the multiple SERPs is preferable to the user is made based upon the values of the features. The SERP determined to be preferable over other SERPs in the multiple SERPs is presented to the user.

Identifying preferable results pages from numerous results pages

A statistical language model (SLM) may be iteratively refined by considering N-gram counts in new data, and blending the information contained in the new data with the existing SLM. A first group of documents is evaluated to determine the probabilities associated with the different N-grams observed in the documents. An SLM is constructed based on these probabilities. A second group of documents is then evaluated to determine the probabilities associated with each N-gram in that second group. The existing SLM is then evaluated to determine how well it explains the probabilities in the second group of documents, and a weighting parameter is calculated from that evaluation. Using the weighting parameter, a new SLM is then constructed as a weighted average of the existing SLM and the new probabilities.

Adaptive construction of a statistical language model

The ranking quality of a ranked list may be evaluated. In an example embodiment, a method is implemented by a system to access log data, ascertain which entries of a ranked list are skipped, and determine a ranking quality metric from the skipped entries. More specifically, log data that reflects user interactions with a ranked list having multiple entries is accessed. The user interactions include at least indications of which of the multiple entries are selected entries. It is ascertained which entries of the multiple entries of the ranked list are skipped entries based on the selected entries. The ranking quality metric for the ranked list is determined responsive to the skipped entries.

Evaluating the ranking quality of a ranked list

Assigning session identifications to log entries and generating anonymous log entries are provided. In order to balance users' privacy concerns with the need for analysis of the log entries to provide high quality search results, non-user-specific data fields, such as a user's location (e.g., city, state, and latitude/longitude) and connection speed, are inserted into the log entries, and user-specific data fields, such as the IP address and cookie identifications, are deleted from the log entries. In addition or alternatively, prior to anonymization of the log entries, session identifications are assigned to identified groups of log entries. The groups are identified based on factors such as the user's identification, the IP address, the time of search, and differences between the search terms used in the search queries.

Generating anonymous log entries

Growing community of inventors

Kirkland, WA, United States of America

Frederic H Behr, Jr