Abstract: A multi-modal search system (and corresponding methodology) that employs wildcards is provided. Wildcards can be employed in the search query either initiated by the user or inferred by the system. These wildcards can represent uncertainty conveyed by a user in a multi-modal search query input. In examples, the words “something” or “whatchamacallit” can be used to convey uncertainty and partial knowledge about portions of the query and to dynamically trigger wildcard generation.

Abstract: A human interactive puzzle (HIP) authorization architecture where keyed and animated puzzles are executed by HIP players which are distinct and obfuscated to the point where breaking a single player is a relatively costly operation. A key is created in response to a request for a service, a HIP player is created based on the key, and a small installation executable is created that expands during installation to produce a computationally expensive data structure on the client relative to verification of the solution at the server. Thus, copying of the player or relay of the puzzle to a third system requires more time than allowed to receive the solution at the server.

Abstract: Human Interaction Proofs (“HIPs”, sometimes referred to as “captchas”), may be generated automatically. An captcha specification language may be defined, which allows a captcha scheme to be defined in terms of how symbols are to be chosen and drawn, and how those symbols are obscured. The language may provide mechanisms to specify the various ways in which to obscure symbols. New captcha schemes may be generated from existing specifications, by using genetic algorithms that combine features from existing captcha schemes that have been successful. Moreover, the likelihood that a captcha scheme has been broken by attackers may be estimated by collecting data on the time that it takes existing captcha schemes to be broken, and using regression to estimate the time to breakage as a function of either the captcha's features or its measured quality.

Abstract: In one embodiment, a physical world tracking mechanism may monitor the efficacy of an advertisement with an offline conversion component. A data storage device 306 may store a commercial location 110 described in the advertisement and associate a conversion action with the advertisement. A processor 304 may register the conversion action at the commercial location 110 executed by a handheld computing device 104 of a user.

Abstract: Various embodiments provide techniques for inventory management. In one or more embodiments, a probabilistic model is constructed to represent an inventory of ad impressions available from a service provider. The probabilistic model can be based on a traffic model that describes historic interaction of clients with the service provider using various attributes that define the ad impressions. The probabilistic model provides a distribution of the attributes and relates the attributes one to another based on dependencies. When an order from an advertiser for ad impressions is booked by the service provider, the probabilistic model is updated to reflect an expected probabilistic decrease in the inventory of ad impressions. The updated probabilistic model can then be employed to determine whether the inventory of ad impressions is sufficient to book subsequent orders for ad impressions.

Abstract: Various embodiments provide techniques for advertisement inventory. In at least some embodiments, a scaled number of impressions can be matched to orders that have scaled impression goals. Impressions can be randomly selected from an offline traffic model and allocated to orders according to a matching algorithm until a number of impression defined by a scale factor is reached. This can occur by sampling the traffic model directly using the scale factor and/or by creating a scaled data set to which the matching algorithm can be applied. The matching algorithm can be configured to identify an order that is farthest away from being complete and then match the randomly selected impression to the identified order. If the scaled orders in the data set can be fulfilled using the scaled number of impressions, a conclusion is made that the original set of orders can be fulfilled using the original impressions.

Abstract: The subject disclosure pertains to anonymous network interaction. More specifically, mechanisms are provided to ensure anonymity with respect network interaction such that third parties are unable to determine the source and/or intent of communications. Accordingly, entities may anonymize all outgoing and/or incoming data packets so as to mitigate outside entities from learning about information being sought and/or provided. For example, a user or corporation may employ an anonymizer with respect to web searching so that outside entities are not able to determine what information is attempted to be accessed and by whom.

Abstract: Described is automated learning of failure recovery policies based upon existing information regarding previous policies and actions. A learning mechanism automatically constructs a new policy for controlling a recovery process, based upon collected observable interactions of an existing policy with the process. In one aspect, the learning mechanism builds a partially observable Markov decision process (POMDP) model, and computes the new policy base upon the learned model. The new policy may perform automatic fault recovery, e.g., on a machine in a datacenter corresponding to the controlled process.

Abstract: Described is a technology for measuring the similarity between two objects (e.g., documents), via a framework that learns the term-weighting function from training data, e.g., labeled pairs of objects, to develop a learned model. A learning procedure tunes the model parameters by minimizing a defined loss function of the similarity score. Also described is using the learning procedure and learned model to detect near duplicate documents.

Abstract: Described is automated learning of failure recovery policies based upon existing information regarding previous policies and actions. A learning mechanism automatically constructs a new policy for controlling a recovery process, based upon collected observable interactions of an existing policy with the process. In one aspect, the learning mechanism builds a partially observable Markov decision process (POMDP) model, and computes the new policy base upon the learned model. The new policy may perform automatic fault recovery, e.g., on a machine in a datacenter corresponding to the controlled process.

Abstract: A system is described for allowing a user, operating a trusted device, to remotely log into a server via a potentially untrustworthy client. The system operates by establishing a first secure connection between the client and the server. The system then establishes a second secure connection between the device and the server through the client. The user then remotely logs into the server over the second secure connection using the device. The second secure connection is tunneled within the first secure connection, preventing the untrustworthy client from discovering personal information associated with the user. According to one feature, prior to forming the second secure connection, the user can establish a pairing relationship with the client by reading an address of the client using any kind of reading mechanism. According to another feature, the device can receive marketing information in the course of a transaction.

Abstract: The subject disclosure pertains to anonymous network interaction. More specifically, mechanisms are provided to ensure anonymity with respect network interaction such that third parties are unable to determine the source and/or intent of communications. Accordingly, entities can anonymize all outgoing and/or incoming data packets so as to mitigate outside entities from learning about information being sought and/or provided. For example, a user or corporation can employ an anonymizer with respect to web searching so that outside entities are not able to determine what information is attempted to be accessed and by whom.

Abstract: Systems and methods for determining the value of bids placed by content providers for placement positions on a page, e.g., a web page, rendered according to a given context, for instance, the search results listing for a particular query initiated on a search engine web site, are provided. Additionally, systems and methods are provided for determining placement of content items, e.g., advertisements and/or images, on a rendered page relative to other content items on the page based upon bid value.

Abstract: A system that can analyze a multi-dimensional input thereafter establishing a search query based upon extracted features from the input. In a particular example, an image can be used as an input to a search mechanism. Pattern recognition and image analysis can be applied to the image thereafter establishing a search query that corresponds to features extracted from the image input. The system can also facilitate indexing multi-dimensional searchable items thereby making them available to be retrieved as results to a search query. More particularly, the system can employ text analysis, pattern and/or speech recognition mechanisms to extract features from searchable items. These extracted features can be employed to index the searchable items.

Abstract: This patent application pertains to computing scenarios that allow users to more readily accomplish desired tasks. One implementation includes at least one dictionary of potential auto-suggestions that can be generated in relation to user-input. The implementation also includes a text framework configured to weight at least some of the potential auto-suggestions based upon one or more parameters. This implementation further includes a task engine configured to associate tasks with at least some of the potential auto-suggestions.

Abstract: Decision trees populated with classifier models are leveraged to provide enhanced spam detection utilizing separate email classifiers for each feature of an email. This provides a higher probability of spam detection through tailoring of each classifier model to facilitate in more accurately determining spam on a feature-by-feature basis. Classifiers can be constructed based on linear models such as, for example, logistic-regression models and/or support vector machines (SVM) and the like. The classifiers can also be constructed based on decision trees. “Compound features” based on internal and/or external nodes of a decision tree can be utilized to provide linear classifier models as well. Smoothing of the spam detection results can be achieved by utilizing classifier models from other nodes within the decision tree if training data is sparse. This forms a base model for branches of a decision tree that may not have received substantial training data.

Abstract: A system that can analyze a multi-dimensional input thereafter establishing a search query based upon extracted features from the input. In a particular example, an image can be used as an input to a search mechanism. Pattern recognition and image analysis can be applied to the image thereafter establishing a search query that corresponds to features extracted from the image input. The system can also facilitate indexing multi-dimensional searchable items thereby making them available to be retrieved as results to a search query. More particularly, the system can employ text analysis, pattern and/or speech recognition mechanisms to extract features from searchable items. These extracted features can be employed to index the searchable items.

Abstract: Content management architecture for a portable wireless device. Caching and fetching techniques are provided to improve content handling for portable devices such as cellular telephones and portable computers. A search component automatically performs searches as a background process, and potentially desired content is received and cached by a content storing component to be available in the future when and if needed, mitigating latency associated with slow download speeds, refresh rates, and other system and/or network impediments. Content from background search results can be trickled into the device as part of the background process so as not to burden system resources for other processes. As part of memory management, aged and/or low priority or low interest content can be selectively removed or archived to increase available cache or memory space, as well as to maintain relevant content within the device. A presentation component facilitates presentation of the pre-stored content.

Abstract: A mobile device may present advertisements to users. However, advertisements may be ineffective or dangerous if presented when the attention of the user is unavailable (e.g., while operating a vehicle at a busy intersection.) It may also be desirable to select a sequence of advertisements that interrelate, or that relate the route of the user to an advertised product or service. Therefore, potential routes may be identified (e.g., based on user history or nearby locations of interest), and for potential routes, advertisement opportunities may be identified where the user may have an at least partial attention availability (e.g., traffic signals and fuel stops.) Advertisements may be selected for presentation at the advertisement opportunities of respective potential routes. Additionally, advertisement opportunities may be offered to advertisers in an auction model, and advertisers may specify conditions of advertisements (e.g.

Abstract: A “Constrained Predictive Interface” uses predictive constraints to improve accuracy in user interfaces such as soft keyboards, pen interfaces, multi-touch interfaces, 3D gesture interfaces, EMG based interfaces, etc. In various embodiments, the Constrained Predictive Interface allows users to take any desired action at any time by taking into account a likelihood of possible user actions in different contexts to determine intended user actions. For example, to enable a virtual keyboard interface, various embodiments of the Constrained Predictive Interface provide key “sweet spots” as predictive constraints that allow the user to select particular keys regardless of any probability associated with the selected or neighboring keys. In further embodiments, the Constrained Predictive Interface provides hit target resizing via various piecewise constant touch models in combination with various predictive constraints.