Abstract: Devices and techniques are generally described for generating confidence scores for boosting-based tree machine learning models. In various examples, a first record comprising a plurality of input variables may be received. In another example, a boosting-based tree machine learning model may generate, for the first record, a base model score. In various examples, the base model score may be generated based on the plurality of input variables and the base model score may represent a likelihood that the first record is associated with a first class. In some examples, a score confidence machine learning model may generate a confidence score for the first record. The confidence score may indicate a confidence in the base model score. In various examples, the first record may be processed based at least in part on the confidence score.

Abstract: At an artificial intelligence-based service, an indication of a similarity group of items of a data stream is obtained. A subset of the stream items is to be included in an ordered collection and presented via an interface which allows one or more types of interactions. Using a first data set which includes interaction records of items in the similarity group, one or more machine learning models are trained to predict a relevance metric associated with a particular type of interaction. A predicted value of the relevance metric is obtained from a trained version of a model and stored.

Abstract: Methods, systems, and computer readable media for packet monitoring in a virtual environment are disclosed. According to one method executed at a virtual tap element residing in between a first virtual machine and a second virtual machine in a virtual network environment, the method includes obtaining cryptographic key information from either the first virtual machine or the second virtual machine and detecting an encrypted packet flow being communicated in the virtual network environment between the first virtual machine and the second virtual machine via the virtual tap element. The method further includes decrypting the encrypted packet flow using the cryptographic key information, generating a decrypted packet flow set comprising at least a portion of the decrypted packet flow, and sending the decrypted packet flow set to a packet analyzer.

Abstract: The arrangement and selection of digital content to present to a user can be based at least in part upon the relevance of content, e.g., the probabilities of the user selecting to view more information and/or otherwise engaging with instances of the content. Features of items associated with content presented to a user can be determined, as well as the user's response to items with those features. This data is used to determine the probability of the user viewing and/or otherwise engaging an item having specific values for at least some of those features. The probabilities are combined with abandonment scores associated with a feed position of an interface to ensure that content displayed is optimized for engagement. The items can be ranked based on this engagement determination, in order to select which item content to display and the appropriate arrangement of that content.

Abstract: The effect of position bias on content performance can be determined in part using artificial intelligence and computer learning. Performance data can include the frequency with which an action, such as a purchase, occurs in response to an instance of content being displayed. The content can be associated with a node at a lowest level of an offering hierarchy, and performance data from the various levels can be rolled up to higher level nodes to obtain sufficient data to for accurate position bias determinations. A bias model can be trained using the data from the various levels, where the training determines weightings for the bias determinations of each level. Once the position bias for an offer is determined, a normalized performance value can be obtained that does not include the effects of the bias. The normalized values can be used to select and place content based on actual performance.

Abstract: Methods, systems, and computer readable media for packet monitoring in a virtual environment are disclosed. According to one method executed at a virtual tap element residing in between a first virtual machine and a second virtual machine in a virtual network environment, the method includes obtaining cryptographic key information from either the first virtual machine or the second virtual machine and detecting an encrypted packet flow being communicated in the virtual network environment between the first virtual machine and the second virtual machine via the virtual tap element. The method further includes decrypting the encrypted packet flow using the cryptographic key information, generating a decrypted packet flow set comprising at least a portion of the decrypted packet flow, and sending the decrypted packet flow set to a packet analyzer.

Abstract: Systems and methods are disclosed to provide on demand packet traffic monitoring for packet communications within virtual packet processing environments. Virtual TAPs (test access ports) within virtualization layers for VM (virtual machine) host hardware systems are controlled by external controllers to configure watch filters for VM platforms operating within the virtualization layer based upon trigger events determined within packet flow data and/or based upon other external trigger events. The virtual TAP controller then periodically receives watch filter packet data updates from the virtual TAP and further controls the virtual TAP to configure more detailed focus filters for the VM platforms based upon watch filter trigger events. The virtual TAP controller can further communicate one or more VM action commands (e.g., stop VM, stop application, etc.) to the virtual TAP for application to the VM platforms based upon trigger events associated with this more detailed focus filter data.

Abstract: Methods, systems, and computer readable media for packet monitoring in a virtual environment are disclosed. According to one method, the method occurs at a virtual tap controller implemented using at least one processor. The method includes sending, to a virtual tap in a virtual environment implemented using at least one computing platform, at least one summarization rule for generating summary packet information about packet traffic associated with the virtual environment. The method also includes receiving, from the virtual tap, the summary packet information generated using the at least one summarization rule. The method further includes generating, using the summary packet information, at least one processing rule for copying or forwarding packet data associated with the virtual environment and sending, to the virtual tap, the at least one processing rule.

Abstract: Methods, systems, and computer readable media for emulating virtualization resources are disclosed. According to one method, the method occurs at a computing platform. The method includes receiving a message associated with a device under test (DUT) and in response to receiving the message, performing an action associated with at least one of an emulated hypervisor and an emulated virtual machine (VM).

Abstract: Methods, systems, and computer readable media for packet monitoring in a virtual environment are disclosed. According to one method, the method occurs at a virtual tap controller implemented using at least one processor. The method includes sending, to a virtual tap in a virtual environment implemented using at least one computing platform, at least one summarization rule for generating summary packet information about packet traffic associated with the virtual environment. The method also includes receiving, from the virtual tap, the summary packet information generated using the at least one summarization rule. The method further includes generating, using the summary packet information, at least one processing rule for copying or forwarding packet data associated with the virtual environment and sending, to the virtual tap, the at least one processing rule.

Abstract: Systems and methods are disclosed to provide on demand packet traffic monitoring for packet communications within virtual packet processing environments. Virtual TAPs (test access ports) within virtualization layers for VM (virtual machine) host hardware systems are controlled by external controllers to configure watch filters for VM platforms operating within the virtualization layer based upon trigger events determined within packet flow data and/or based upon other external trigger events. The virtual TAP controller then periodically receives watch filter packet data updates from the virtual TAP and further controls the virtual TAP to configure more detailed focus filters for the VM platforms based upon watch filter trigger events. The virtual TAP controller can further communicate one or more VM action commands (e.g., stop VM, stop application, etc.) to the virtual TAP for application to the VM platforms based upon trigger events associated with this more detailed focus filter data.

Abstract: There are disclosed methods and apparatus for displaying and viewing control plane statistical data for a network. The method comprises configuring a network configuration, wherein the network configuration comprises a network topology, a device group, and a device, generating a test to test the network under test, and requesting to display and view a statistical data based on a network configuration parameter.

Abstract: An illustrative mobile device includes a data storage configured to at least temporarily store visual information and at least one processor that is configured to determine whether to request visual information processing from a network with which the mobile device may communicate. The processor is configured to determine a mobile device condition and a network condition. The processor determines a type of feature from the visual information to use for classification based on the determined mobile device and network conditions. The processor is configured to classify the visual information based on the determined type of feature and determine a confidence indicator based on the classification. The processor determines whether to request visual information processing from the network based on the determined confidence indicator.

Abstract: Methods, systems, and computer readable media for emulating virtualization resources are disclosed. According to one method, the method occurs at a computing platform. The method includes receiving a message associated with a device under test (DUT) and in response to receiving the message, performing an action associated with at least one of an emulated hypervisor and an emulated virtual machine (VM).

Abstract: There are disclosed methods and apparatus for displaying and viewing control plane statistical data for a network. The method comprises configuring a network configuration, wherein the network configuration comprises a network topology, a device group, and a device, generating a test to test the network under test, and requesting to display and view a statistical data based on a network configuration parameter.

Abstract: An illustrative mobile device includes a data storage configured to at least temporarily store visual information and at least one processor that is configured to determine whether to request visual information processing from a network with which the mobile device may communicate. The processor is configured to determine a mobile device condition and a network condition. The processor determines a type of feature from the visual information to use for classification based on the determined mobile device and network conditions. The processor is configured to classify the visual information based on the determined type of feature and determine a confidence indicator based on the classification. The processor determines whether to request visual information processing from the network based on the determined confidence indicator.

Abstract: A system and method for caching and pre-fetching content is disclosed. This invention relates to mobile devices and, more particularly but not exclusively, to delivering content to a mobile device. Existing systems employ different mechanisms for delivering content such as multimedia and the like to users of mobile device. Mechanisms such as broadcast services, delivery from the interne, Wi-Fi hotspots, Bluetooth kiosks etc face problems of offering innovative services to users due to insufficient network capacity, high end costs to consumers. The disclosed system delivers contents such as multimedia, data and the like by pre-fetching and caching techniques. The contents preferred by a user is identified and pre-fetched to access points located in vicinity of the user. The user can access the contents from the access points via a short range communication means such as Bluetooth, Infrared and so on.