Abstract: In some embodiments, a room-scale data storage library includes shelf robots and movable shelves on a floor of the room-scale data storage library. The shelf robots move the movable shelves between storage locations on the floor of the room-scale data storage library and drive bays comprising drives and mechanisms to move the data storage devices between the movable shelves and the drives. In such a system, different type of components, such as movable shelves, data storage devices, drives, drive bay robots, etc. may be independently scaled up or down, to include more such components, providing flexibility to fully utilize the components of the room-scale data storage library.

Abstract: A cryptographic key management service receives a request, associated with a principal, to use a cryptographic key to perform a cryptographic operation. In response to the request, the service determines whether a rate limit specific to the principal is associated with the cryptographic key. If the rate limit is associated with the cryptographic key, the service generates a response to the request that conforms to the rate limit. The service provides the response in response to the request.

Abstract: Edge devices of a network collect data. An edge device may determine whether to process the data using a local data processing model or to send the data to a tier device. The tier device may receive the data from the edge device and determine whether to process the data using a higher tier data processing model of the tier device. If the tier device determines to process the data, then the tier device processes the data using the higher tier data processing model, generates a result based on the processing, and sends the result to an endpoint (e.g., back to the edge device, to another tier device, or to a control device). If the tier device determines not to process the data, then the tier device may send the data on to another tier device for processing by another higher tier model.

Abstract: Features are disclosed for managing multiple heterogeneously owned data stores (e.g., data sets, data lakes) and provisioning a framework for data consumers and data publishers. A computing device can obtain a plurality of data catalogs associated with the data stores. For example, the computing device may update a hybrid data catalog with information from the plurality of data catalogs. The computing device can further provide a portion of the plurality of data catalogs to a data consumer. The computing device may provide the portion of the plurality of data catalogs based on permissions provided by the data publisher. In response, the computing device can receive a request to access a data store associated with the plurality of data catalogs. The computing device can transmit the request to a corresponding data publisher and, based on a response by the data publisher, may modify the distinct access controls for the data store.

Abstract: Prior to an update of an operating system of a computing device, a configuration operation is performed with respect to a particular processor of the computing device, such that the particular processor is indicated to the operating system as being in an offline state while an application runs at the particular processor. The operating system is then updated. The update comprises a time interval in which the operating system is unavailable and the application performs one or more computations at the particular processor. After the update, the application is restarted.

Abstract: A data source configured to provide a representation of an environment of one or more agents is identified. Using a data set obtained from the data source, a neural network-based reinforcement learning model with one or more attention layers is trained. Importance indicators generated by the attention layers are used to identify actions to be initiated by an agent. A trained version of the model is stored.

Abstract: Systems, methods, and computer-readable media are disclosed for language-agnostic subtitle drift detection and correction. A method may include determining subtitles and/or captions from media content (e.g., videos), the subtitles and/or captions corresponding to dialog in the media content. The subtitles may be broken up into segments which may be analyzed to determine a likelihood of drift (e.g., a likelihood that the subtitles are out of synchronization with the dialog in the media content) for each segment. For segments with a high likelihood of drift, the subtitles may be incrementally adjusted to determine an adjustment that eliminates and/or reduces the amount of drift, and the drift in the segment may be corrected based on the drift amount detected. A linear regression model and/or human blocks determined by human operators may be used to otherwise optimize drift correction.

Abstract: Techniques are described for maintaining in-order execution when a dependency exists between write transactions. In some embodiments, a write re-order buffer (WROB) is configured to assign the same group ID to an incoming write transaction upon determining that the incoming write transaction is dependent on a pending write transaction. The WROB forwards the incoming write transaction to an interconnect fabric for routing to a completer device. The interconnect fabric enforces in-order execution when write transactions share the same group ID. The WROB can maintain a transaction log of pending write transactions and also track the statuses of responses for such transactions. Transaction responses can include responses sent from a completer to confirm that a transaction has actually been completed. Additionally, the WROB can send a response indicating completion back to the requester of the transaction. In some embodiments, the WROB is configured to send an early response to the requester.

Abstract: Systems and methods are described to enable delivery of streaming content while inhibiting or preventing removal, blocking, or skipping of portions within that streaming content. A content delivery system can generate a manifest indicating content portions that form the streaming content. Each content portion can be identified in the manifest using a concealed identifier, which conceals the actual identifier of the content portion from the client to inhibit or prevent the client from automatically removing or modifying the content portion. On receiving a request for a content portion, the content delivery system can convert the concealed identifier into the actual identifier, and return the appropriate content portion to the client. In some instances, the specific identifiers included within a concealed manifest may be modified or adapted based on monitoring information of the client device, to ensure clients view given portions of streaming content.

Abstract: Methods and apparatus for coordinating inter-region operations in provider networks. An inter-region coordinator (IRC) operates asynchronously to the control planes of regional networks to coordinate inter-region operations. The IRC in a region may include one or more IRC servers. To perform inter-region operations, the servers may implement a local-remote-local method in which a server invokes an API in the local region to get work, sends the work to a control plane of a remote region, receives a response from the remote region, and informs the control plane in the local region of the status of the work.

Abstract: According to an embodiment, a method includes estimating, based at least in part on a first location of a bounding box for a foot in a first frame of a sequence of frames and a second location of the bounding box in a second frame of the sequence of frames, a smoothing transformation that characterizes a movement of the foot in the sequence of frames and smoothing, based at least in part on the smoothing transformation, a movement of a structure of the foot from a first location of the structure in the first frame to a second location of the structure in the second frame. The method also includes superimposing a model of a shoe onto the foot in the sequence of frames based at least in part on the smoothed movement.

Abstract: User information may be used to create a training exercise representing simulated package delivery. The user information can include metrics corresponding to physical package delivery. The user information may be used as part of a predictive model to determine the content of the training exercise, including the type and number of tasks comprising the exercise. Once created, the training exercise can be presented to a user as a graphical simulation. The presentation can occur in response to one or more triggering conditions.

Abstract: This disclosure is directed to facilitating voice and video communication between users independent of a location or a device. A communication request can specify users, who may be identified and located in their respective environments. For example, users can be identified and located using facial recognition imaging techniques and/or by monitoring a radio frequency (RF) signal associated with a device that is carried or worn by a user. After determining a location of a user, individual devices can be configured as a functionally grouped device to allow the users to communicate. For example, capabilities of a television, microphone, speaker, and imaging device can be combined to allow a video communication between users. Further, as a user moves around his or her environment, the location of the user can be tracked and additional functionally grouped devices can be provided for seamless communication.

Abstract: Systems and methods are disclosed for systems-in-packages that have multiple shielding components. In one embodiment, a system-in-package may include a substrate, an integrated circuit package disposed on the substrate, a system-on-a-chip disposed on the substrate, and a molding compound disposed over the integrated circuit package and the system-on-a-chip. The system-in-package may include a first electromagnetic interference shielding component disposed about the molding compound, and a second electromagnetic interference shielding component that at least partially forms an outer surface of the system-in-package. The second electromagnetic interference shielding component may have a patterned structure formed thereon.

Abstract: This disclosure describes, in part, techniques for improving the integration of voice-interaction experiences to mobile devices, and improving user experience when interacting with mobile devices that provide voice-interaction experiences. A remote system may detect an event that indicates that a mobile device is to perform an action. The remote system may determine the mobile device is not connected to the remote system, and send a push-notification message to prompt the mobile device to establish a network connection with the remote system. The mobile device may send device-context data to the remote system that indicates a role of a periphery device connected to the mobile device. Depending on the role of the periphery device and the action to be performed by the mobile device, the remote system may send a command to the mobile device using the open network connection to cause the mobile device to perform the action.

Abstract: Features are disclosed for automatically identifying a speaker. Artifacts of automatic speech recognition (“ASR”) and/or other automatically determined information may be processed against individual user profiles or models. Scores may be determined reflecting the likelihood that individual users made an utterance. The scores can be based on, e.g., individual components of Gaussian mixture models (“GMMs”) that score best for frames of audio data of an utterance. A user associated with the highest likelihood score for a particular utterance can be identified as the speaker of the utterance. Information regarding the identified user can be provided to components of a spoken language processing system, separate applications, etc.

Abstract: A counting device bears a visually distinct pattern or marking, and is coupled to a pusher or other movable system of a shelf in a manner that causes the counting device to rotate in response to changes in position of the pusher. When items are placed on a shelf, or removed from the shelf, causing the pusher to move, the pattern on the counting device rotates at an angle defined by an extent of the movement of the pusher. Images captured of the counting device at various times may be processed to determine orientations of the pattern at such times. Where a change in an orientation of a pattern is detected, a number of items added to or removed from a shelf may be calculated based on the change in orientation and an event involving the number of items may be determined to have occurred.

Abstract: A system comprising one or more computing devices implements a vehicle information extraction service. The vehicle information extraction service enables customers to optimize an amount of relevant vehicle sensor information extracted from vehicles by reducing instances of collection of redundant data. The vehicle information extraction service additionally, or alternatively, enables customers to maintain a model of a fleet of vehicles and determine number of the vehicles of the fleet in a certain partition to calculate a data reduction factor that will filter out sensor data. The vehicle information extraction service communicates the reduction factor to the vehicles in the geographical region using a vehicle scheme to indicate to the vehicles the probability with which the vehicle is to transmit a particular type of sensor data.

Abstract: An identification system includes one or more infrared light sources and a camera that acquires images of a user's palm. For example, at a first time, one or more first images may be acquired by the camera using infrared light with a first polarization that represent external characteristics of the user's palm. At a second time, one or more second images may be acquired using infrared light with a second polarization that represent internal characteristics of the user's palm. These images are processed to determine a first set of feature vectors and a second set of feature vectors. A current signature may be determined using the first set of feature vectors and the second set of feature vectors. In addition, a user may be identified based on a comparison of the current signature and previously stored reference signatures that are associated with candidate user identifiers.

Abstract: Systems, methods, and computer-readable media are disclosed for systems and methods for automated identification and mapping of objects in video content. Example methods may include determining a first set of frames in video content, determining, using one or more object recognition algorithms, a first object present in the first set of frames, determining that a first product corresponding to the first object is present in a product catalog comprising a set of product images, associating a first product identifier of the first product with a video identifier of the video content, and causing presentation of a set of product identifiers associated with the video identifier.

Abstract: Evaluation rooms (or fitting rooms) at a clothing store include replenishment closets that are accessible to customers and associates of the clothing store, albeit not at the same time. Doors of evaluation rooms include access control systems with interlocks that govern operation of the respective doors. Before an associate opens a first door between an exterior of an evaluation room and a closet to place an item therein, a second door between an interior of the evaluation room and the closet is locked. After the associate places the item in the closet, the first door is closed and locked, and the second door is unlocked, enabling the customer to open the second door and retrieve the item. Feedback indicating that items are being staged in a closet, or that items are staged therein and the closet is accessible to a customer, is provided to the customer within the evaluation room.

Abstract: Devices and techniques are generally described for process optimization using reinforcement learning. In various examples, first input data is received and a first process for processing the first input data is determined. In some examples, a second process for processing the first input data is determined. A first machine learning model is used to generate a first prediction for processing the first input data by the first process. The first process and/or the second process are controlled based at least in part on the first prediction.

Abstract: In various examples, audio received from a source device is shared from a first wireless earbud to one or more other wireless earbuds. For example, source-device settings are shared by the first wireless earbud with the one or more other wireless earbuds to facilitate synchronization and passive receipt of data transmitted by the source device. Once the wireless earbuds are synchronized, they may check in with one another in a coordinated manner to share packets that were missed when passively listening to the source device.

Abstract: Systems and methods related to redundant battery management systems (BMS) may include an on-battery BMS, and one or more off-battery, off-vehicle, and/or remote BMS. The one or more remote BMS may receive data associated with parameters of a battery, and may process the received data using various models, algorithms, or estimators to determine a battery state. The battery state determined by the remote BMS may then be used to corroborate or support a battery state determined by the on-battery BMS, thereby ensuring safe, reliable, and efficient operations of systems, machines, or devices utilizing batteries as power sources.

Abstract: A system that implements a data storage service may store data on behalf of storage service clients. The system may maintain data in multiple replicas of various partitions that are stored on respective computing nodes in the system. The system may employ a single master failover protocol, usable when a replica attempts to become the master replica for a replica group of which it is a member. Attempting to become the master replica may include acquiring a lock associated with the replica group, and gathering state information from the other replicas in the group. The state information may indicate whether another replica supports the attempt (in which case it is included in a failover quorum) or stores more recent data or metadata than the replica attempting to become the master (in which case synchronization may be required). If the failover quorum includes enough replicas, the replica may become the master.

Abstract: Recognizing unknown data objects may be implemented for data objects stored in a data store. Data objects that are identified as unknown may be accessed to retrieve a portion of the data object. Different representations of the data object may be generated for recognizing different data schemas. An analysis of the representations may be performed to identify a data schema for the unknown data object. The data schema may be stored in a metadata store for the unknown data object.

Abstract: Methods, systems, and computer-readable media for tracing service interactions without global transaction identifiers are disclosed. A service monitoring system receives an event message from a first service in a service-oriented system. The event message comprises one or more elements of data from a body of a service request from an upstream service. The first service initiates a sub-task associated with the service request. The service monitoring system receives one or more additional event messages from one or more additional services. The additional event message(s) comprise one or more additional elements of data from one or more additional service requests associated with one or more additional sub-tasks. The service monitoring system determines, based (at least in part) on the element(s) of data in the event message and the additional element(s) of data in the additional event message(s), that the sub-task and the additional sub-task(s) are associated with a higher-level task.

Abstract: Disclosed are various embodiments for asynchronously generating consistent snapshots in a distributed system. In one embodiment, a snapshotting agent receives a respective local snapshot for individual processes in a distributed system. The respective local snapshot for a corresponding process includes a corresponding vector clock that comprises respective values indicating respective state changes in the corresponding process and other processes. The snapshotting agent determines whether a collection of the respective local snapshots for the individual processes represents a global consistent snapshot for the distributed system based at least in part on a comparison of the respective values of the corresponding vector clocks.

Abstract: Systems and methods to implement customer contact service with real-time supervisor assistance. A supervisor may oversee multiple agents in a customer contact service. A service of a computing resource service provider may monitor a plurality of audio connections at a service of a computing resource service provider, generate transcripts for the plurality of audio data, analyze the transcripts using a set of natural language processing (NLP) techniques to generate metadata, tag the transcripts with categories based at least in prat on the metadata, generate information for at least a portion of the plurality of connections based on the transcripts, metadata, and categories, and provide the information to a supervisor of the agents.

Abstract: A computing service may include a user interface and an associated programming interface which is invoked by interaction with the user interface. An automation service may receive information indicative of a series of interactions with the user interface that result in an invocation of the programming interface. The automation service may generate code comprising instructions for invoking the programming interface, the instructions based on the invocation caused by interaction with the user interface. The generated code may be shared. When executed, the generated code may reproduce the effects of the interaction with the user interface.

Abstract: Techniques for enrolling a user in a system's user recognition functionality without requiring the user speak particular speech are described. The system may determine characteristics unique to a user input. The system may generate an implicit voice profile from user inputs having similar characteristics. After an implicit voice profile is generated, the system may receive a user input having speech characteristics similar to that of the implicit voice profile. The system may ask the user if the user wants the system to associate the implicit voice profile with a particular user identifier. If the user responds affirmatively, the system may request an identifier of a user profile (e.g., a user name). In response to receiving the user's name, the system may identify a user profile associated with the name and associate the implicit voice profile with the user profile, thereby converting the implicit voice profile into an explicit voice profile.

Abstract: System and methods are provided for sharding at the content level and routing content requests. Each point of presence (PoP) can initially identify the PoP that should serve content by using hashing. A PoP can encode a domain name with the identified PoP in metadata and redirect the client computing device. A client computing device transmits a DNS query for the encoded domain name. A DNS server receives the encoded domain name and decrypts and decodes the domain name label. The DNS server uses the decrypted and decoded metadata to make a further routing decision. The DNS server sends, to the client computing device, a DNS reply with the Internet Protocol (IP) address of the selected PoP. The client computing device requests content from the PoP identified by the provided IP address.

Abstract: An apparatus includes a liquid crystal layer comprising a first region and a second region. The first region comprises a first plurality of liquid crystal molecules in a first state and the second region comprises a second plurality of liquid crystal molecules in a second state different from the first state. The apparatus also includes a camera positioned to receive light propagating through the second region, a first driver circuit configured to apply a first set of voltages to a first set of electrodes in the first region, and a second driver circuit configured to apply a second set of voltages to a second set of electrodes in the second region.

Abstract: Disclosed are various embodiments that provide demand-based allocation of ephemeral radio-based network resources. In one embodiment, a determination is made that an unmanned vehicle has unallocated computing capacity along a travel path. At least a portion of the unallocated computing capacity is provisioned for use by a customer for a time period as the unmanned vehicle progresses on the travel path.

Abstract: A system can be utilized to determine media clips for media content based on a comparison between subtitles of the media content and information associated with a third-party system. The comparisons can be utilized to identify subtitles based on the comparison and determine the media clips based on portions of the media content associated with the identified subtitles. A smoothing algorithm can be applied to the media clips to modify start times and end times of the media clips. The system can cause the media clips or the corresponding media content to be output by an external device.

Abstract: This disclosure proposes systems and methods for speech processing and sharing permitted entity information across speech processing systems. A first system can receive first audio data representing a first utterance. The first system can receive a first dialog identifier associated with a previous utterance. The first system can determine that the first audio data references a first entity. In some cases, the first system may not be able to resolve the first entity based on information in the first audio data. The first system can send, to a second system different from the first system, a first request for information about the first entity. The first request includes the first dialog identifier. The first system can receive first data responsive to the first request from the second system. The first system can process the first data and the first audio data to determine second data responsive to the first utterance, and output a first response representing the second data.

Abstract: Technologies directed to channel state information (CSI) sending in the 2.4 GHz band are described. A method includes receiving first CSI data representing channel properties of a first wireless channel used by first and wireless devices that operates in the 2.4 GHz band. The method receives second and third CSI data corresponding to second and third wireless channels. The method determines an inference probability of a motion or a non-motion condition in the geographical region based on an average probability of CSI samples from the first, second, and third CSI data.

Abstract: Systems, methods, and computer-readable media are disclosed for roll-formed containers for shipping. In one embodiment, an example container for an item may include a rectangular sheet of formable material, the rectangular sheet having a first crease line, a second crease line separated from the second crease line by a distance, a first crease pattern disposed adjacent to the first crease line, and a second crease pattern disposed adjacent to the second crease line. The container may include a sealant disposed about three sides of the rectangular sheet.

Abstract: Representations of sets of descriptors of reference objects are stored in a repository, with individual descriptors including information about entities identified in the reference objects. In response to a request to extract content from a particular data object, a reference object which satisfies a similarity criterion with respect to the particular data object is identified from the repository using the descriptors. A structural comparison of the particular data object and the reference object is performed to determine an entity related to another entity identified in the particular data object.

Abstract: This disclosure is directed to item-identifying carts that may be utilized by users to automatically identify items that the users place in their carts. In addition, these carts may automatically determine the outcome of respective events that occur with respect to these identified items. For example, the carts may be configured to identify one or more items that are placed into or removed from the cart, and thereafter determine one or more actions taken with respect to the identified items and a quantity of the items involved. For example, after identifying a first item and a second item either placed into or removed from the cart, the cart may determine that the user added two instances of the first item and removed one instance of the second item. In response to making this determination, the cart may update a virtual cart of a user operating the physical cart.

Abstract: Techniques for selecting and providing highly targeted, interactive advertisements in a personalized manner. These advertisements may be audio-only advertisements, video-only advertisements, or advertisements that include both audio and video. As described below, advertisements may be selected and/or generated for a particular user based on an array of factors, including the user's interactions with multiple different client devices (e.g., a tablet computing device, a voice-controlled device, a television etc.), as well as additional behavior of the user. In some instances, the client devices may include a voice-controlled device that the user interacts with via voice commands and that provides audible content for output to the user.

Abstract: Devices, systems, and methods are provided for encapsulating machine learning in a clean room to generate a goal-based output. A method may include identifying, by a device operating within a clean room, an agreement between multiple parties to share data for use in machine learning to generate a goal-based output; retrieving the data; selecting the machine learning model based on a goal indicated by the agreement; generating, using the data as inputs to the selected machine learning model, a first set of probabilities indicative that a respective user may perform an action; generating, using the selected machine learning model and the first set of probabilities, a second set of probabilities indicative that a respective user may perform the action; generating the goal-based output based on the second set of probabilities; and sending the goal-based output from the clean room to a destination location.

Abstract: Techniques for routing a user command to a speechlet and resolving conflicts between potential speechlets are described. A system determines an intent of an input command. The system also receives context information associated with the input command. The system determines speechlets (e.g., speechlets and/or skills) that may execute with respect to the input command given the intent and the context data. The system then determines whether conditions of routing rules, associated with the speechlets, are satisfied given the context data. If the conditions of only one routing rule are satisfied, the system causes the speechlet associated with the routing rule to execute with respect to the input command. If the conditions of more than one routing rule are satisfied, the system may determine a speechlet to execute with respect to the input command based on the speechlets' priorities in a list of speechlets and/or based on potential output data provided by the speechlets.

Abstract: Systems and techniques for performing a scan-free reading of a structured identifier are provided. One technique involves obtaining a first set of images of an object within a scanning volume of an environment. The object is passed through the scanning volume without an explicit presentation of the structured identifier to an optical scanner within the environment. For each image of a plurality of the first set of images, an indication of a first region of interest of the structured identifier on the object within the image is obtained, based in part on a second set of images of the object having a lower quality than the first set of images. The first region of interest of the structured identifier is extracted from a first image of the plurality of the first set of images. The structured identifier within the first region of interest within the first image is decoded.

Abstract: A hybrid beamforming device utilizes analog beamformers (ABF) and digital beamformers (DBF) to produce a desired radio frequency radiation pattern having one or more lobes pointing in particular directions. A set of directions, such as each pointing toward a different candidate area of the sky, are processed to determine a coarse direction. ABF beam coefficients are determined based on the coarse direction. DBF beam coefficients are determined based on the directions in the set of directions, providing more precise directionality in the pattern. The ABF beam coefficients may be sent to the ABFs at a first cadence, such as every second. The DBF beam coefficients may be sent to the DBFs at a second cadence that is faster than the first cadence, such as every millisecond. This facilitates rapid scanning of different precision directions, such as of different portions of the sky to receive a broadcast transmission from a satellite.

Abstract: Devices, systems, and methods are provided for dynamic and context-based presentation of content using streaming media applications. A method may include receiving, by a first device, a user request to search for media titles based on user context data received by a first streaming media application; identifying, from a catalog of media titles and streaming media applications, the media titles based on the user context data; identifying an advertisement campaign associated with a second streaming media application; selecting, based on the advertisement campaign and the user context data, a first media title; selecting, based on the user context data, a second media title; generating first user interface data indicative of the first media title and second user interface data indicative of the second media title; and causing presentation of the first user interface data and the second user interface data using a user interface of the first streaming media application.