Google Inc.

Ailive, Inc.

Michael David McNally

Xiaoyuan Tu

Brian Keith Cabral

Wei Yen

John Funge

Ian Wright

Daniel Dobson

Nigel Duffy

Ron Musick

Krishna Asur Bharat

Ming Lei

Nathan Stoll

Justin Lawyer

Scott Barta

William D Strathearn

Anurag Gupta

Vinay Rao

Fei Xiao

Ioan Marius Pungaru

Bill Davis

This specification describes technologies relating to detecting anomalous user accounts. A computer implemented method is disclosed which evaluates an unknown status user account. The method described compares features associated with a plurality of known anomalous user accounts stored in a database to features present in the unknown account. A correlation value corresponding to the probability of a specific feature occurring in a particular anomalous user account is calculated and a dependence value corresponding to the degree of dependence between the given feature and at least one other feature is also calculated. A subset of features in the unknown account is generated comprising those features that possess a correlation value less than a threshold value and a dependence value below a maximum correlation value. A risk score for the unknown account is calculated by selecting those features from the subset that maximizes the correlation value. The unknown account is then reviewed by an account reviewer if the risk score exceeds a threshold value.

Detection of anomalous instances through dynamic feature selection analysis

Methods, computer program products and systems are described for online-content management. Online content from multiple contributors is received at one or more first computers for public online display. An authentication score is determined for a contributor of the multiple contributors. The contributor's name and a representation of the contributor's authentication score is published online for display on one or more second computers in association with the online content received from the contributor.

Reputation scoring of an author

Authentication of a contributor of online content

A collaborative editing model for online content is described. A set of suggested edits to a version of the online content is received from multiple users. Each suggested edit in the set relates to the same version. The set of suggested edits is provided to an authorized editor, who is visually notified of differences between the version of the content and the suggested edits and conflicts existing between two or more suggested edits. Input is received from the editor resolving conflicts and accepting or rejecting suggested edits in the set. The first version of the content is modified accordingly to generate a second version of the content. Suggested edits from the set that were not accepted nor rejected and are not in conflict with the second version are carried over and can remain pending with respect to the second version.

Online content collaboration model

Providing dynamic learning for software agents in a simulation is described. The software agents with learners are capable of learning from examples. When a non-player character queries the learner, it can provide a next action similar to a player character. A game designer provides program code, from which compile-time steps determine a set of raw features. The code may identify a function (like computing distances). At compile-time steps, determining these raw features in response to a scripting language, so the designer can specify which code should be referenced. A set of derived features, responsive to the raw features, may be relatively simple, more complex, or determined in response to a learner. The set of such raw and derived features form a context for a learner. Learners might be responsive to (more basic) learners, to results of state machines, to calculated derived features, or to raw features. The learner includes a machine learning technique.

Query controlled behavior models as components of intelligent agents

A system including at least specialized elements that are restricted to a particular domain of data analysis or processing and configurable data that permits the specialized elements to be tailored to a particular application. The configurable data expands applicability of the specialized elements to plural applications within the particular domain. The specialized elements can be provided by a supplier to a developer without the supplier having detailed knowledge of structures and internal operations used by the particular application. The particular application can be generated by the developer without the developer having detailed knowledge of internal operations used by the specialized elements.

Non-disruptive embedding of specialized elements

Providing dynamic learning for software agents in a simulation. Software agents with learners are capable of learning from examples. When a non-player character queries the learner, it can provide a next action similar to the player character. The game designer provides program code, from which compile-time steps determine a set of raw features. The code might identify a function (like computing distances). At compile-time steps, determining these raw features in response to a scripting language, so the designer can specify which code should be referenced. A set of derived features, responsive to the raw features, might be relatively simple, more complex, or determined in response to a learner. The set of such raw and derived features form a context for a learner. Learners might be responsive to (more basic) learners, to results of state machines, to calculated derived features, or to raw features. The learner includes a machine learning technique.

Real time context learning by software agents

A system including at least (1) specialized elements that are restricted to a particular domain of data analysis or processing and (2) configurable data that permits the specialized elements to be tailored to a particular application. The configurable data expands applicability of the specialized elements to plural applications within the particular domain. The specialized elements can be provided by a supplier to a developer without the supplier having detailed knowledge of structures and internal operations used by the particular application. The particular application can be generated by the developer without the developer having detailed knowledge of internal operations used by the specialized elements.

Growing community of inventors

San Jose, CA, United States of America

Michael David McNally