Abstract: Exemplary embodiments relate to a system for recovering a conversation between a user and the system when the system is unable to properly respond to a user's input. The system may process the user input and determine an error condition exists. The system may query one or more storage systems to identify candidate text data based on their semantic similarity to the user input. The storage systems may store data related to past frequently entered inputs and/or user-generated inputs. Alternative text data is selected from the candidate text data, and presented to the user for confirmation.

Abstract: Devices and techniques are generally described for evaluation of text data using large n-grams. In various examples, a first vector may be generated for first text data, wherein each element of the vector comprises a value indicating whether the first text data includes a respective n-gram included in a corpus of text data. First label data indicating that a user associated with the first text data has connected to a first computer-implemented service more than a threshold number of times during a past time period may be determined. A first machine learning model may be trained based at least in part on the first vector and the first label data. The first machine learning model may be used to determine a first probability associated with a first n-gram of the first vector. In some examples, at least a first user associated with the first n-gram may be determined.

Abstract: Technologies directed to correcting terrestrial interference using narrowband adaptive filtering and beamforming technology are described. One method includes receiving a first and second radio frequency (RF) signal. The method includes generating first digital samples corresponding to the first RF signal using a first sample rate and generating second digital samples corresponding to the first RF signal using a second sample rate that is lower than the first sample rate. The method further includes generating third digital samples corresponding to the second RF signal using the second sample rate. The method further includes determining parameters associated with a filtering process using the second digital samples and the third digital samples. The method further includes generating fourth digital samples using the parameters of the filtering process. The method further includes removing a first portion from the first RF signal using the first digital samples and the fourth digital samples.

Abstract: An audio/video (A/V) device may include or accommodate a viewer through a barrier. For example, an A/V device may include a first component for installation on an exterior surface of a door, a second component for installation on an interior surface of the door, a viewer that extends through an opening in the door, and a flexible connector that electrically couples the first component and the second component. The A/V device may enable use of an existing hole in the door as part of a door viewer, while also providing the functionality of an A/V device. For example, the A/V device may be configured to receive an input using a button on the first component, generate image data using a camera on the first component, and send the image data to a network device.

Abstract: Techniques for determining the input threshold voltage level of an integrated circuit device may include configuring a voltage drive level and a load current for a tester channel of automated test equipment (ATE) connected to an input pin of an integrated circuit device, and executing a test pattern. The test pattern may include test vectors for generating a set of voltage ramps at the input pin by the tester channel using the load current and the voltage drive level. The set of voltage ramps can be characterized by different lengths and different amplitudes. The test pattern may also include test vectors for checking output values on an output pin of the integrated circuit device after each voltage ramp of the set of voltage ramps. The input threshold voltage level of the input pin can be determined based on results of executing the test pattern.

Abstract: With the advent of virtualization technologies, networks and routing for those networks can now be simulated using commodity hardware. For example, virtualization technologies can be adapted to allow a single physical computing machine to be shared among multiple virtual networks by providing one or more virtual machines simulated in software by the single physical computing machine, with each virtual machine acting as a distinct logical computing system. In addition, as routing can be accomplished through software, additional network setup flexibility can be provided to the virtual network in comparison with hardware-based routing. In some implementations, virtual network setup can be abstracted through the use of resource placement templates, allowing users to create virtual networks compliant with a customer's networking policies without necessarily having knowledge of what those policies are.

Abstract: Disclosed herein is a tag viewer that can be implemented to overlay content on a web page, such as a web page of a web-based console associated with a service of a service provider network. The tag viewer may determine which page elements of a web page are tagged based on data, such as a data structure, associated with the web page, and may overlay content on the web page, the content including: (i) one or more containers presented around one or more tagged page elements, and (ii) one or more annotations presented in association with the tagged page element(s). Individual annotations that are overlaid on the web page may include a tag type and/or a tag value corresponding to the analytics tag associated with the tagged page element.

Abstract: Methods, systems, and computer-readable media for automated threat modeling using application relationships are disclosed. A graph is determined that includes of nodes and edges. At least a portion of the nodes represent software components, and at least a portion of the edges represent relationships between software components. An event is received, and a sub-graph associated with the event is determined. The event is indicative of a change to one or more of the nodes or edges in the graph. Threat modeling is performed on the sub-graph using one or more analyzers. The one or more analyzers determine whether the sub-graph is in compliance with one or more policies.

Abstract: Bitmaps for managing computing resources are described. Example bitmaps described in this application use less memory space by varying the sizes of the nodes in the bitmap's tree structure, and/or by limiting the number of nodes in the bitmap's leaf layer. Other example bitmaps described in this application reduce the time needed to traverse the bitmap by tailoring the search direction according to the bitmap's configuration.

Abstract: The motion of objects within a scene may be detected and tracked using digital (e.g., visual and depth) cameras aligned with fields of view that overlap at least in part. Objects may be identified within visual images captured from the scene using a tracking algorithm and correlated to point clouds or other depth models generated based on depth images captured from the scene. Once visual aspects (e.g., colors or other features) of objects are correlated to the point clouds, shapes and/or positions of the objects may be determined and used to further train the tracking algorithms to recognize the objects in subsequently captured frames. Moreover, a Kalman filter or other motion modeling technique may be used to enhance the prediction of a location of an object within subsequently captured frames.

Abstract: Techniques for dynamic profile data ingestion are described. The system may process profile data associated with one device, such as a mobile device, to associate it with another device, such as a vehicle. For example, when a connection is made between the first device and the second device, the profile data associated with the first device may be associated with the second device, in a manner using a remote system. The remote system may temporarily associate the profile data with the second device, enabling the system to interpret a command using the profile data.

Abstract: Systems and methods for multilingual keyword generation for low-resource language passages are disclosed. For example, high-resource language passages describing items in a catalog or other such passages may include numerous keywords for classifying and searching for the item while a low-resource language description of the item may not include the same rich keyword environment due to lower usage and traffic in the low-resource language. The systems and methods herein provide for leveraging the high-resource language through a multilingual natural language processing algorithm to identify similar passages across language barriers and identify keywords in the high-resource language for input into a decoder to generate keywords in the low-resource language.

Abstract: A plurality of metrics records, including some records indicating metrics for which anomaly analysis has been performed, is obtained. Using a training data set which includes the metrics records, a machine learning model is trained to predict an anomaly analysis relevance score for an input record which indicates a metric name. Collection of a particular metric of an application is initiated based at least in part on an anomaly analysis relevance score obtained for the particular metric using a trained version of the model.

Abstract: Systems and methods are provided for generating custom garment patterns for producing clothing sized to fit any newly input human body representation. A set of reference sample bodies may be selected for which custom designed garment patterns are then obtained. Once reference patterns are obtained, a custom garment pattern for a particular new body may be automatically created by blending two or more of the reference patterns. For example, the neighboring reference bodies to the new body may be identified within a low-dimensional embedding space, and interpolation of garment parameters for the previously designed garment patterns for these reference bodies may be performed to produce a custom garment pattern.

Abstract: In various implementations, provided are systems and methods for reducing neural network processing. A compiler may generate instructions from source code for a neural network having a repeatable set of operations. The instructions may include a plurality of blocks. The compiler may add an overwrite instruction to the plurality of blocks that, when executed by one or more execution engines, triggers an overwrite action. The overwrite action causes the instructions of subsequent blocks to be overwritten with NOP instructions. The overwrite action is triggered only when a condition is satisfied.

Abstract: A speech-processing system may provide access to multiple virtual assistants via one or more voice-controlled devices. Each assistant may leverage language processing and language generation features of the speech-processing system, while handling different commands and/or providing access to different back applications. Each assistant may be associated with its own voice and/or speech style, and thus be perceived as having a particular “personality.” Different assistants may be available for use with a particular voice-controlled device based on time, location, the particular user, etc. In some situations, language processing may be improved by leveraging data such as intent data, grammars, lexicons, entities, etc., associated with assistants available for use with the particular voice-controlled device.

Abstract: A security device has user-configurable motion detection settings. The security device includes at least one camera configured to capture sequential frames of image data within a field of view; at least one processor; memory communicatively coupled with the processor(s); a location setting, stored in the memory, defining whether or not the security device is located at a common access area; and machine readable instructions stored in the memory. The machine readable instructions are executable by the processor(s) to determine the image data indicates motion; and determine that the motion indicates lingering presence at the common access area. In certain embodiments, the machine readable instructions are executable by the processor(s) to determine, from the image data, that the average ambient light over a daily period varies less than a light variation threshold, and configure the location setting to indicate that the security device is located at the common access area.

Abstract: Systems and methods are provided herein for generating optimized video segments. A derivative video segment (e.g., a scene) can be identified from derivative video content (e.g., a movie trailer). The segment may be used a query to search video content (e.g., the movie) for the segment. Once found, an optimized video segment may be generated from the video content. The optimized video segment may have a different start time and/or end time than those corresponding to the original segment. Once optimized, the video segment may be presented to a user or stored for subsequent content recommendations.

Abstract: Systems and methods are disclosed to implement a data storage system that manages data retention for partitioned datasets. A received data retention policy specifies to selectively delete data from a dataset based on a set of data retention attributes. If the data retention attributes are part of the dataset's partition key, a first type of data deletion job is configured to selectively delete entire partitions of the dataset. Otherwise, the system will generate a retention attribute index for the dataset, which will be used by a second type of data deletion job to selectively delete individual records within the partitions. In embodiments, the retention attribute index is implemented as Bloom filters that track retention attribute values in each partition. Advantageously, the disclosed system is able to automatically configure deletion jobs for any dataset schema that avoids full scans of the dataset partitions.