Amazon Technologies, Inc.

Microsoft Technology Licensing, LLC

Ron Kohavi

Benjamin W S Redman

Ronald M Whitman

Eric R Vadon

Gautam K Jayaraman

Brent Russell Smith

Kushal Chakrabarti

Jeffrey Alan Holden

Jeremy Charles York

Lawrence Gordon Tesler

Daniel Bruce Lloyd

Llewellyn James Mason

Ya Xu

Noor-E-Gagan Singh

Sarvesh Nagpal

Toby H Walker

Brian Frasca

Systems, methods, and computer-readable storage media are provided for determining whether a user is a human agent or a non-human agent. A user is initially classified as a human or non-human agent based on user request properties. Sensor data is received from the user device and used to determine whether the user is to be reclassified as a human agent or non-human agent. Based on the sensor data, the user is then reclassified as a human agent or non-human agent. A service is adapted based on the classification.

Automatic detection of human and non-human activity

Enhancements of the user experience are provided when a user returns to a previously viewed page, such as a previously viewed page of search results. When a user returns to a previously viewed page, additional context information from a user's actions since the initial view of a page can be used to modify the previously viewed page and/or obtain a new version of the previously viewed page. In situations where the previously viewed page corresponds to a page of responsive results from a search engine, the modified and/or new version of the search engine results page can include an expanded or reduced group of results, different types of results, different rankings for existing results, or a combination thereof.

Changing results after back button use or duplicate request

A system and method are disclosed for automatically detecting associations between particular sets of search criteria, such as particular search strings, and particular items. Actions of users of an interactive system, such as a web site, are monitored over time to generate event histories reflective of searches, item selection actions, and possibly other types of user actions. An analysis component collectively analyzes the event histories to automatically identify and quantify associations between specific search strings (or other types of search criteria) and specific items.

Detection of behavior-based associations between search strings and items

Computing services that unwanted entities may wish to access for improper, and potentially illegal, use can be more effectively protected by using Active HIP systems and methodologies. An Active HIP involves dynamically swapping one random HIP challenge, e.g., but not limited to, image, for a second random HIP challenge, e.g., but not limited to, image. An Active HIP can also, or otherwise, involve stitching together, or otherwise collecting and including, within Active HIP software, i.e., a HIP web page, to be executed by a computing device of a user seeking access to a HIP-protected computing service x number of software executables randomly selected from a pool of y number of software executables. The x number of software executables, when run, generates a random Active HIP key. If the generated Active HIP key accompanies a correct user response to the valid HIP challenge the system and/or methodology can assume with a degree of certainty that the current user is a legitimate human user and allow the current user access to the requested computing service.

Active hip

The controversiality of an offering in a computer implemented system is computed based on user satisfaction feedback. A controversiality index can be provided to indicate the extent to which the offering is controversial.

Method and system for determining whether an offering is controversial based on user feedback

A continuous website trial allows ongoing observation of user interactions with website for an indefinite period of time that is not ascertainable at initiation of the trial. Users are randomly assigned to either a control group or one or more test groups. The control and test groups are served different sets of web pages, even though they access the same website. During the trial, the web pages for the control group are held constant over time, while the web pages for the test group(s) undergo multiple modifications at separate occasions over time. As the web pages for the test group(s) are modified, statistical data collection continues to learn how user behavior changes as a result of the modifications. The statistical data obtained from the users of the various groups may be compared and contrasted and used to gain a better understanding of customer experience with the website.

Continuous usability trial for a website

A system and method are disclosed for automatically detecting associations between particular sets of search criteria, such as particular search strings, and particular items. Actions of users of an interactive system, such as a web site, are monitored over time to generate event histories reflective of searches, item selection actions, and possibly other types of user actions. An analysis component collectively analyzes the event histories to automatically identify and quantify associations between specific search strings (or other types of search criteria) and specific items. As part of this process, a decay function reduces the weight given to a post-search item selection event based on intervening events that occur between the search event and the item selection event.

An automated method and system for providing an item comparison includes identifying a first item and a set of one or more other items for comparison with the first item, prioritizing attributes of the first item and the other items, and providing the item comparison with prioritized attributes to a user. Identifying comparable items may involve a multiple step process in which a candidate set of items is first selected for possible comparison with the first item, and thereafter selecting one or more items from the candidate set for comparison. Prioritizing the attributes of the items may include measuring like attributes of the items against each other and arranging the attributes to appear in an order according to the degree the like attributes distinguish the items from each other. A modified item comparison may be prepared and provided in accordance with user feedback.

Method and system for automated comparison of items

Strategies are described for generating recommendations. The strategies generate a set of original recommendations based on a source of information. The strategies then transform the set of original recommendations into a set of similarity-spaced recommendations based on 'repulsion force' analysis applied to the set of original recommendations. In a first implementation, the set of spaced recommendations represent a diverse sampling of items in the set of original recommendations. In a second implementation, the set of spaced recommendations represent a sampling of items in the set of original recommendations which omits or excludes recommendations assessed as obvious. A third implementation can combine the first and second implementations.

Growing community of inventors

Issaquah, WA, United States of America

Ron Kohavi