Abstract: Red-eye detection based on red region detection with eye confirmation initially identifies pixels that correspond to the color of red-eye within an image. A determination is then made as to whether these identified pixels and surrounding areas are part of an eye or not part of an eye. Those identified pixels that are determined to be part of an eye are the detected red-eye regions.

Abstract: A method and system for providing business context corresponding to unstructured documents is provided. A business context correlation system analyzes the contents of a user's unstructured document, identifies the business context of the unstructured document from the analyzed contents, and presents the business context along with the unstructured document to the user. The business context includes the relevant contextual objects and documents associated with one or more business applications. Providing a view of the business context along with the unstructured document allows the user more fully understand and act on the displayed document.

Abstract: Disclosed herein are systems methods and devices related to region detection of an image. Detected regions include pixels of a particular one or more colors without requiring faces within the image to be previously detected. Region detection may include receiving information that a flash was used to capture the image or that return light was detected in the image.

Abstract: A method and system for identifying a configuration parameter of a “sick” computer system that is at fault for causing an undesired behavior based on analysis of configuration parameters from other computer systems is provided. In one embodiment, a troubleshooting system collects “suspect” values for “suspect” configuration parameters used by a “sick” application when the undesired behavior was exhibited by the sick computer system. The troubleshooting system then compares the suspect values to sample values of the suspect configuration parameters retrieved from sample computer systems. The troubleshooting system uses that comparison to identify one or more suspect configuration parameters that are likely at fault for causing the application to exhibit the undesired behavior.

Abstract: A system that facilitates detecting a targeted topic in a document is described herein. The system includes a receiver component that receives a document. The system additionally includes a topic model component trained using a plurality of training documents including the topic and a plurality of training documents that do not include the topic. The topic model component analyzes the document and automatically determines which portions of the document include the topic and which portions of the document do not include the topic.

Abstract: What is disclosed is acquiring information regarding a web page, without having to commit to downloading that page. In one embodiment, after a current web page is downloaded from one source, and information regarding web pages linked to by links in the current web page are downloaded from a second source, when a user hovers a cursor over a link on a current web page, an informational region is displayed by the link that includes the information from the second source. The informational region may include, for example, a text box that apparently floats by the link. The information in the region can include, for example, keywords in the meta tags of the web page; paragraph headings of the web page; links on the web page to other pages; etc.

Abstract: A system and method for generating a list is provided. The system includes a seed item input subsystem, an item identifying subsystem, a descriptive metadata similarity determining subsystem and a list generating subsystem that builds a list based, at least in part, on similarity processing performed on seed item descriptive metadata and user item descriptive metadata and user selected thresholds applied to such similarity processing. The method includes inexact matching between identifying metadata associated with new user items and identifying metadata stored in a reference metadata database. The method further includes subjecting candidate user items to similarity processing, where the degree to which the candidate user items are similar to the seed item is determined, and placing user items in a list of items based on user selected preferences for (dis)similarity between items in the list and the seed item.

Abstract: A malicious behavior detection/prevention system, such as an intrusion detection system, is provided that uses active learning to classify entries into multiple classes. A single entry can correspond to either the occurrence of one or more events or the non-occurrence of one or more events. During a training phase, entries are automatically classified into one of multiple classes. After classifying the entry, a generated model for the determined class is utilized to determine how well an entry corresponds to the model. Ambiguous classifications along with entries that do not fit the model well for the determined class are selected for labeling by a human analyst The selected entries are presented to a human analyst for labeling. These labels are used to further train the classifier and the models. During an evaluation phase, entries are automatically classified using the trained classifier and a policy associated with determined class is applied.

Abstract: The subject invention provides systems and methods that facilitate obfuscating a spam filtering system to hinder reverse engineering of the spam filters and/or to mitigate spammers from finding a message that consistently gets through the spam filters almost every time. The system includes a randomization component that randomizes a message score before the message is classified as spam or non-spam so as to obscure the functionality of the spam filter. Randomizing the message score can be accomplished in part by adding a random number or pseudo-random number to the message score before it is classified as spam or non-spam. The number added thereto can vary depending on at least one of several types of input such as time, user, message content, hash of message content, and hash of particularly important features of the message, for example. Alternatively, multiple spam filters can be deployed rather than a single best spam filter.

Abstract: Diagnosis of one or more root causes of symptoms is performed by using stochastic gradient descent to find the optimal parameters of a variational distribution. This methodology, called variational gradient descent, permits fast diagnosis for a large number (greater than 1,000) or very large number (greater than 1,000,000) of symptom observations. A real-time application of the root cause diagnosis can determine currently occurring intermittent root causes. Diagnosis can be performed in a number of scenarios, such as medical disease detection or computer/network failure.

Abstract: The subject invention provides a unique system and method that facilitates an interactive game-powered search engine that serve the purposes of both users who may be looking for information as well as game participants who may desire to earn some reward or level of enjoyment by playing the game. More specifically, the system and method provides feedback to a user based on the user's input string or a string derived therefrom. The feedback can be a response or answer to the user's input in the form of text, an image, audio or sound, video, and/or a URL that is provided by one or more game participants when there is some degree of consistency or agreement between the responses or when individual players have demonstrated good reliability in their responses.

Abstract: Architecture for completing search queries by using artificial intelligence based schemes to infer search intentions of users. Partial queries are completed dynamically in real time. Additionally, search aliasing can also be employed. Custom tuning can be performed based on at least query inputs in the form of text, graffiti, images, handwriting, voice, audio, and video signals. Natural language processing occurs, along with handwriting recognition and slang recognition. The system includes a classifier that receives a partial query as input, accesses a query database based on contents of the query input, and infers an intended search goal from query information stored on the query database. A query formulation engine receives search information associated with the intended search goal and generates a completed formal query for execution.

Abstract: Architecture for completing search queries by using artificial intelligence based schemes to infer search intentions of users. Partial queries are completed dynamically in real time. Additionally, search aliasing can also be employed. Custom tuning can be performed based on at least query inputs in the form of text, graffiti, images, handwriting, voice, audio, and video signals. Natural language processing occurs, along with handwriting recognition and slang recognition. The system includes a classifier that receives a partial query as input, accesses a query database based on contents of the query input, and infers an intended search goal from query information stored on the query database. A query formulation engine receives search information associated with the intended search goal and generates a completed formal query for execution.

Abstract: Architecture for completing search queries by using artificial intelligence based schemes to infer search intentions of users. Partial queries are completed dynamically in real time. Additionally, search aliasing can also be employed. Custom tuning can be performed based on at least query inputs in the form of text, graffiti, images, handwriting, voice, audio, and video signals. Natural language processing occurs, along with handwriting recognition and slang recognition. The system includes a classifier that receives a partial query as input, accesses a query database based on contents of the query input, and infers an intended search goal from query information stored on the query database. A query formulation engine receives search information associated with the intended search goal and generates a completed formal query for execution.

Abstract: Providing for browsing a summary of content formed of keywords that can scale to a user-defined level of detail is disclosed herein. Components of a system can include a summarization component that extracts keywords related to the content and associates the keywords with portions thereof, and a zooming component that displays a number of keywords based on a keyword/keyphrase relevance rank and a zoom factor. Additionally, a speech to text component can translate speech associated with the content into text, wherein the keywords are extracted from the translated text. Consequently, the claimed subject matter can present a variable hierarchy of keywords to form a scalable summary of such recorded content.

Abstract: An incoming electronic communication is broken down into message portions. Features of the message portions are extracted and the message portions are converted into sparse feature vectors. The probabilities of the message portions being of interest of the user are calculated and the message portions are converted back into text. Message portions with a relatively high probability of being of interest to a user are presented to the user as a summary.

Abstract: Systems and methods are disclosed that facilitate producing probabilistic outputs also referred to as posterior probabilities. The probabilistic outputs include an estimate of classification strength. The present invention intercepts non-probabilistic classifier output and applies a set of kernel models based on a softmax function to derive the desired probabilistic outputs. Such probabilistic outputs can be employed with handwriting recognition where the probability of a handwriting sample classification is combined with language models to make better classification decisions.

Abstract: Prior to searching a multidimensional feature space populated with data objects, each dimension in the feature space is divided into a number of intervals. When a query is received, a single interval that is overlapped by the query is selected from each dimension. A reduced set of data objects is then selected that includes only those data objects that overlap the selected intervals. This reduced set of data objects, rather than the entire set of data objects in the feature space, is then used to determine matches for the query.

Abstract: The present invention relates to a system and methodology to facilitate automatic management and pruning of audio files residing in a database. Audio fingerprinting is a powerful tool for identifying streaming or file-based audio, using a database of fingerprints. Duplicate detection identifies duplicate audio clips in a set, even if the clips differ in compression quality or duration. The present invention can be provided as a self-contained application that it does not require an external database of fingerprints. Also, a user interface provides various options for managing and pruning the audio files.

Abstract: A strategy is described for identifying anomalies in time-series data. The strategy involves dividing the time-series data into a plurality of collected data segments and then using a modeling technique to fit local models to the collected data segments, Large deviations of the time-series data from the local models are indicative of anomalies In one approach, the modeling technique can use an absolute value (L1) measure of error value for all of the collected data segments. In another approach, the modeling technique can use the L1 measure for only those portions of the time-series data that are projected to be anomalous. The modeling technique can use a squared-term (L2) measure of error value for normal portions of the time-series data. In another approach, the modeling technique can use an iterative expectation-maximization strategy in applying the L1 and L2 measures.