Abstract: Systems and methods for optimizing a transportation plan for a transportation network are described. In an example, a computer system determines a forecasted demand for transporting items between a source node and a destination node of a transportation network and a set of constraints associated with a handling node of the transportation network. The computer system generates a transportation plan that comprises a network path including the handling node and a type of item handling at the handling node. In a first stage of optimization, an optimization model of the computer system selects the network path from network paths. In a second stage of optimization, the optimization model selects the type of item handling from types of item handling available at the handling node. The optimization model uses the network paths and the types of item handling as variables.

Abstract: Voice-controlled devices that include one or more speakers for outputting audio. In some instances, the device includes at least one speaker within a cylindrical housing, with the speaker aimed or pointed away from a microphone coupled to the housing. For instance, if the microphone resides at or near the top of the cylindrical housing, then the speaker may point downwards along the longitudinal axis of the housing and away from the microphone. By pointing the speaker away from the microphone, the microphone will receive less sound from the speaker than if the speaker were pointed toward the microphone). Because the voice-controlled device may perform speech recognition on audio signals generated by the microphone, less sound from the speaker represented in the audio signal may result in more accurate speech recognition, and/or a lesser need to perform acoustic echo cancelation (AEC) on the generated audio signals.

Abstract: Disclosed are systems and methods to deliver location restricted content to devices that do not have a location component, such as a Global Positioning System component. A location aware device may send to a content delivery service, location information determined by a location component of the location aware device and receive, from the content delivery service, an encrypted access token. The location aware device may then send the access token to a non-location aware device that is on a same local area network as the location aware device. The non-location aware device may provide the access token to the content delivery service along with a request for location restricted content. The content delivery service may use the access token provided by the non-location aware device to verify that the non-location aware device is within a defined area for which the requested location restricted content is allowed for presentation.

Abstract: Techniques for training a visual neural network are described. In particular, the training of the visual neural network may be performed using one or more contrastive learning loss functions including one or more of a visual-to-visual contrastive learning function using the visual neural network on positive and negative video clips according to a first loss function, a secondary-to-secondary contrastive learning a secondary neural network on secondary positive and negative information generated from the positive and negative video clips, and a secondary-to-visual contrastive learning according to a third loss function using the visual neural network on positive and negative video clips and using the secondary neural network secondary positive and negative information generated from the positive and negative video clips.

Abstract: Techniques for generating geographical units that can be used to generate delivery routes are described herein. Geospatial vector data and barrier geospatial vector data for a geographical area may be obtained. Seed points for one or more portions of the geographical area may be determined based at least in part on historical delivery volume for the geographical area. A plurality of polygons that represent the geographical area may be determined based at least in part on an algorithm that uses the seed points, the geospatial vector data, and the barrier geospatial vector data. Coordinates for a geographical unit of a plurality of geographical units that divide the geographical area may be determined based at least in part on the plurality of polygons and a polygon-to-polygon barrier aware drive time matrix that identifies a calculated cost for traveling from one polygon to another polygon using barriers identified in the barrier geospatial vector data.

Abstract: Methods, systems, and computer-readable media for global column indexing in a graph database are disclosed. A plurality of data elements of a graph database are stored. The triples comprise identifiers, column names, and values. The column names are globally scoped in the graph database and are associated with data types. Indices corresponding to the column names are created. A particular one of the indices comprises one or more of the values associated with the corresponding column name. A query is performed on the graph database using one or more of the indices corresponding to one of more of the column names associated with the query.

Abstract: An apparatus includes a memory and a hardware processor. The hardware processor determines one or more of a weight of an item, a packaging type of the item, a packaging material of the item, a barcode of the item, a rigidity of the item, or a physical response of the item to being lifted and determines a visual appearance of the item and a shape or size of the item. The hardware processor also compares, using a machine learning model, the determined characteristics of the item to a manifest for the container. The manifest identifies a plurality of items in the container. The hardware processor determines, using the machine learning model, an identity of the item based on comparing the determined characteristics of the item to the manifest.

Abstract: Techniques are generally described for machine learning exampled-based annotation of image data. In some examples, a first machine learning model may receive a query image comprising a first depiction of an object-of-interest. In some examples, the first machine learning model may receive a target image representing a scene in which a second depiction of the object-of-interest is visually represented. In various examples, the first machine learning model may generate annotated output image data that identifies a location of the second depiction of the object-of-interest within the target image. In some examples, an object detection model may be trained based at least in part on the annotated output image data.

Abstract: Techniques for using suppression filters for presenting content of a network documents are described. In an example, a computer system receives, from a device associated with an account identifier, a request for an online network document. The computer system determines that a first category identifier of a first item category is associated with a suppression filter. The computer system determines that the account identifier is associated with an online item interaction having an interaction time associated with an item that belongs to the first item category. The computer system determines, based on a comparison of the interaction time and the suppression time, that a presentation of the first content in the online network document is prohibited. The computer system sends, to the device in response to the request, network document data that indicates second content about a third item that belongs to a second item category.

Abstract: Disclosed are systems and methods for detecting defects during the handling and processing of items at a material handling facility. Embodiments of the present disclosure can be implemented at material handling to detect quality defects during processing of items in connection with fulfillment operations that may be designed to receive, store, sort, pick, pack, and ship items. Embodiments of the present disclosure provides a plurality of sensors and a trained machine learning model configured to provide real-time acquisition and analysis of item information to facilitate detection and mitigation of processing quality defects.

Abstract: Systems, methods, and computer-readable media are disclosed for using machine learning to generate automated custom media experiences. Example methods may include determining a first user identifier of a first user present in an environment, determining a first set of media preferences of the first user using media presented in association with the first user identifier, and determining a second user identifier of a second user present in the environment. Methods may include determining a second set of media preferences of the second user using media presented in association with the second user identifier, generating, using a first machine learning model, a first playlist of media using the first set of media preferences and the second set of media preferences for presentation to the first user and the second user, the first playlist comprising first media and second media, and causing audible presentation of the first media.

Abstract: Systems and techniques are generally described for detecting evasive terms in item listings. In some examples, a list of keywords associated with a first category of specified items may be received. In some examples, text data associated with a first item may be received. A first plurality of tokens representing a corrected version of the text data may be generated using spell correction techniques. In some cases, first flag data indicating that the text data constitutes evasive text may be generated based at least in part on the generation of the first plurality of tokens. The first flag data and a numerical representation of the first plurality of tokens may be input into a binary classifier trained to generate label data indicating whether text data associated with a given item is evasive or non-evasive. The binary classifier may generate label data indicating that the text data associated with the first item is evasive.

Abstract: A computer system and associated methods are disclosed for mitigating side-channel attacks using a shared cache. The computer system includes a host having a main memory and a shared cache. The host executes a virtual machine manager (VMM) that determines respective security keys for a plurality of co-located virtual machines (VMs). A cache controller for the shared cache includes a scrambling function that scrambles addresses of memory accesses performed by threads of the VMs according to the respective security keys. Different cache tiers may implement different scrambling functions optimized to the architecture of each cache tier. Security keys may be periodically updated to further reduce predictability of shared cache to memory address mappings.

Abstract: Devices and techniques are generally described for generating per-topic review summarization. In some examples, a plurality of text descriptions of a first item may be received. In at least some examples, a list of categories may be determined. In some examples, at least one machine learned model may generate a first summary of the plurality of text descriptions. In some examples, the first summary may be relevant to a first category of the list of categories. In further examples, the at least one machine learned model may generate a second summary of the plurality of text descriptions. The second summary may be relevant to a second category of the list of categories. In various cases, first output data that includes the first summary and the second summary may be generated.

Abstract: Systems and methods are provided for management of data access latency in a distributed storage system by dynamically replicating data objects experiencing a high request volume. When a storage node is unable to meet a data access latency target (e.g., due to one or more data objects hosted by the storage node being the subject of a large quantity of requests), the storage node may initiate a process by which a second storage node is employed to reduce the request processing load. The second storage node may cache a copy of the requested data object, and may service at least a portion of requests for the data object using the cached copy.

Abstract: A data service implements a configurable data compressor/decompressor using a recipe generated for a particular data set type and using compression operators of a common registry (e.g., pantry) that are referenced by the recipe, wherein the recipe indicates at which nodes of a compression graph respective ones of the compression operators of the registry are to be implemented. The configurable data compressor/decompressor provides a customizable framework for compressing data sets of different types (e.g., belonging to different data domains) using a common compressor/decompressor implemented using a common set of compression operators.

Abstract: Systems and methods are provided for implementing a multi-service file system for a hosted computing instance via a locally-addressable secure compute layer. Software within the instance can submit file operations to the secure compute layer, which the secure compute layer can translate into calls to one or more network-accessible storage services. To provide a multi-service file system, the secure compute layer can obtain mapping data mapping file system objects within the virtualized file system to different network-accessible storage services. On receiving a file operation, the secure compute layer can determine one or more network-accessible storage services corresponding to the file operation, and submit appropriate calls to the one or more network-accessible storage services.

Abstract: Systems and methods are described herein for implementing a hybrid codec to compress and decompress image data using both lossy and lossless compression. In one example encoding process, it may be determined whether a first block of pixels of a frame of image data contains an edge. A type of compression by which to encode the first block may be selected based on that determination. The first block may be compressed using the selected type of compression. At least one second value associated with the first block of pixels may be set to indicate at least oof the compressed value or the type of compression used to compress the first block.

Abstract: Disclosed are various embodiments for inferring brand similarities using graph neural networks and selection prediction. In one embodiment, a brand-to-brand graph is generated indicating similarities between a set of brands according to at least one of: click-through data or conversion data. Using a first graph neural network (GNN) tower, the brand-to-brand graph is analyzed to determine brand similarities among a first brand identified from a search query and a first set of other brands. Using a second GNN tower, the brand-to-brand graph is analyzed to determine brand similarities among a second brand and a second set of other brands. A level of similarity between the first brand and the second brand is determined based at least in part on an output of the first GNN tower and an output of the second GNN tower.

Abstract: Techniques for building, validating, and utilizing custom database software in a shared management environment are described. A database customization service allows users to provide database installation files as part of a configuration to generate a custom database engine version. The creation of custom database engine versions may be governed by policy, and the database customization service may provide recommendations for creating custom database engine versions according to various criteria. The custom database engine version can be built, and its functionality and correctness verified. Users may launch database instances using these custom database engine versions that can be managed under a shared management scheme where both users and the database customization service can perform host-level management.

Abstract: Various embodiments of systems and methods for providing virtualized (e.g., serverless) broker clusters for a data streaming service are disclosed. A data streaming service uses a front-end proxy layer and a back-end broker layer to provide virtualized broker clusters, for example in a Kafka-based streaming service. Resources included in a virtualized broker cluster are monitored and automatically scaled-up, scaled-down, or re-balanced in a way that is transparent to data producing and/or data consuming clients of the data streaming service.

Abstract: A latch mechanism for a sidewalk delivery robot or container includes a plunger that extends to engage a latch body on a lid to lock the lid closed, a cable for pulling the plunger out of engagement with the lid to free the lid for opening, and a temporary catch mechanism for holding the plunger in the retracted position during an initial phase of the opening process. The catch, and therefore the plunger, is released when a forward-extending release arm of the catch is engaged by the latch body during the opening process to pivot the catch. A slot hinge mechanism includes a spring piston to guard against finger pinching and a slider that is attached to the piston of the latch mechanism by the cable. Actuation of the hinge mechanism retracts the piston to its retracted position.

Abstract: Methods, systems, and computer-readable media for auto-tuning permissions using a learning mode are disclosed. A plurality of access requests to a plurality of services and resources by an application are determined during execution of the application in a learning mode in a pre-production environment. The plurality of services and resources are hosted in a multi-tenant provider network. A subset of the services and resources that were used by the application during the learning mode are determined. An access control policy is generated that permits access to the subset of the services and resources used by the application during the learning mode. The access control policy is attached to a role associated with the application to permit access to the subset of the services and resources in a production environment.

Abstract: Techniques for performing speech processing using multi-modal widget information are described. A system may receive input data corresponding to a user input. The system may also receive widget context data corresponding to one or more multi-modal widgets active at a device. The system may use the widget context data to perform natural language understanding (NLU) processing with respect to the user input, and for selecting a skill component for responding to the user input. The system may send a widget identifier to the skill component when invoking the skill to respond to the user input.

Abstract: Systems and methods for sender profile and/or recipient profile disambiguation and/or confirmation are disclosed. In instances where a sender profile is not indicated by a user sending a communication from a communal device, heuristic data may be utilized to infer the sender profile. Similar heuristic data may also be used when selection of the sender profile is associated with a low confidence level. Heuristic data may also be used to infer the recipient profile when the user does not indicate the recipient profile or when selection of the recipient profile is associated with a low confidence. Various confirmations may result from the sender and recipient profile disambiguation.

Abstract: An object-based data storage service receives a request to store a data object in a first location corresponding to a first data storage tier. The request may specify a parameter to enable transitioning of the data object to another data storage tier. In response to the request, the object-based data storage service stores the data object in the first location and monitors access of the data object to determine usage data associated with the data object. The object-based data storage service processes the usage data to determine that the data object is to be transitioned to a second data storage tier. As a result of this determination, the object-based data storage service transitions the data object to a second location corresponding to the second data storage tier.

Abstract: Remote Triggered Black Holes (RTBHs) can be precisely placed on networks that are not directly physically connected to a target of an attack. A network source of a potential attack can be determined. A path between the network source and the target can be identified, and a determination can be made as to which networks along that path subscribe to an attack mitigation service. From multiple identified subscriber networks, a subscriber network can be identified that is determined to be appropriate for placement of a black hole to mitigate the attack. Once selected, the identified network can receive attack information and acknowledge placement of the black hole. The subscriber network can then begin discarding traffic for the attack target. A subscriber-owned list of network prefixes can be reviewed before allowing RTBH injection for a corresponding address space.

Abstract: Availability zone and region recovery are described. For an availability zone (AZ), a recovery availability zone (rAZ) may be identified based on available computing capacity of the recovery availability zone and geographic proximity of the availability zone relative to the recovery availability zone. In an instance in which the availability zone is impacted in which at least one of hardware and software of the availability zone is not fully operational, a virtual private cloud (VPC) is generated that establishes a peered connection between the availability zone and the recovery availability zone. A service is executed in the recovery availability zone, permitting any other services executing in the availability zone to invoke the service and become partially or fully operational.

Abstract: Methods and systems for improved quality of a streaming session using multiple simultaneous streams. For the multiple simultaneous streams an audio/video device (A/V device) records and generates a high-resolution stream and a low-resolution stream for simultaneous transmission to a server. The server selects one of the two streams for retransmission to a destination client device. The server also monitors the streaming session and estimates a total available bandwidth between the server and the A/V device and assigns a confidence value to the bandwidth estimation. The server periodically transmits the bandwidth estimate and confidence value to the A/V device to improve the efficiency of the streams being generated by the A/V device. The A/V device can use the received bandwidth estimate and confidence value to adapt the resolution of each of the streams to efficiently use the total available bandwidth between the A/V device and the server.

Abstract: Techniques for change data capture (CDC) log augmentation are described. In some examples, a user configures CDC log augmentation by indicating which data should be included in a CDC log, and the database, when generating a CDC log associated with this configuration, can obtain the associated data and augment the CDC log by inserting this data into it. The augmented data can include one or more fields from a record in a separate database table, where the record can be identified based on the changed record represented by the CDC log.

Abstract: An optical transceiver includes a built-in optical switch to switch between diverse fiber paths in switches in a datacenter or in switches between two datacenters. The built-in optical switch can be used to switch between racks in a datacenter to increase capacity for any rack that requests it. A controller, which receives a signal from a server computer in one of the racks, can be external to the optical transceiver or within the optical transceiver. In either case, the server computer can be provided with additional bandwidth when needed. For connections between datacenters, the built-in optical switch allows for optical line protection, but without the need for a splitter circuit, which incurs a significant power loss and requires a more expensive transceiver. Consequently, the built-in optical switch within an optical transceiver can be used in a variety of contexts to increase efficiency and reduce overall costs for network devices.

Abstract: Techniques for performing machine learning inference calls in database query processing are described. A method for performing machine learning inference calls in database query processing may include generating a query plan to optimize a query for batch processing of data stored in a database service, the query plan including a batch mode operator to execute a function reference and an execution context associated with the batch mode operator, executing the query plan to invoke a function associated with the function reference, wherein the function sends a batch of requests, generated using the execution context, to a remote service and obtains a plurality of responses from the remote service, and generating a query response based on the plurality of responses.

Abstract: Systems and methods are described controlling ingestion of data items within a data stream by executions of a serverless function on a serverless compute system. A poller device can act as an intermediary between the data stream and the serverless function, iteratively retrieving data items from the data stream and passing them in invocations of the serverless function. To allow for fine-grained control of ingestion without requiring implementation of complex logic at the poller device, the poller device can enable the serverless function to pass instructions controlling subsequent operation of the poller device. Each execution of the serverless function may determine whether subsequent operation of the poller device should be altered, and if so, instruct the poller device accordingly. The poller device can then modify its operation pursuant to the instructions, enabling highly granular control of streaming data ingestion without inhibiting existing benefits of serverless computing.

Abstract: The present disclosure generally relates to a system of a delivery device for combining sensor data from various types of sensors to generate a map that enables the delivery device to navigate from a first location to a second location to deliver an item to the second location. The system obtains data from RGB, LIDAR, and depth sensors and combines this sensor data according to various algorithms to detect objects in an environment of the delivery device, generate point cloud and pose information associated with the detected objects, and generates object boundary data for the detected objects. The system further identifies object states for the detected object and generates the map for the environment based on the detected object, the generated object proposal data, the labeled point cloud data, and the object states. The generated map may be provided to other systems to navigate the delivery device.

Abstract: A clock disciplining scheme uses a pulse per second (PPS) signal that is distributed throughout a network to coordinate timing. In determining the time, jitter can occur due to latency between detection of the PPS signal and a software interrupt generated there from. This jitter affects the accuracy of the clock disciplining process. To eliminate the jitter, extra hardware is used to capture when the PPS signal occurred relative to a hardware clock counter associated with the clock disciplining software. In one embodiment, the extra hardware can be a sampling logic, which captures a state of a hardware clock counter upon PPS detection. In another embodiment, the extra hardware can initiate a counter that calculates a delay by the clock disciplining software in reading the hardware clock counter. The disciplining software can then subtract the calculated delay from a hardware clock counter to obtain the original PPS signal.

Abstract: A technique for merging, via lattice surgery, a color code and a surface code, and subsequentially decoding one or more rounds of stabilizer measurements of the merged code is disclosed. Such a technique can be applied to bottom-up fault-tolerant magic state preparation protocol such that an encoded magic state can be teleported from a color code to a surface code. Decoding the stabilizer measurements of the merged code requires a decoding algorithm specific to the merged code in which error correction involving qubits at the border between the surface and color code portions of the merged code is performed. Error correction involving qubits within the surface code portion and within color code portion, respectively, may additionally be performed. In some cases, the magic state is prepared in a color code via a technique for encoding a Clifford circuit design problem as an SMT decision problem.

Abstract: Aspects of the present disclosure relate to the sharing of synchronization information corresponding to content among devices in a communication network. An originating device collects synchronization information related to the presentation of content to a user via the originating device. The synchronization information is defined according to reference points related to the presentation of the content to the user via the originating device, including a current state of the presentation of the content and/or additional information obtained during the presentation of the content. Based on detection of a synchronization event, the originating device transmits the collected synchronization information, resulting in the receipt of the synchronization information by one or more receiving devices. Thereafter, the presentation of the content to the user on one of the receiving devices can incorporate the synchronization information collected and transmitted by the originating device.

Abstract: Data is encoded to be incrementally authenticable. A plaintext is used to generate a ciphertext that comprises a plurality of authentication tags. Proper subsets of the authentication tags are usable to authenticate respective portions of plaintexts obtained from the ciphertext. Portions of the plaintext can be obtained and authenticated without decrypting the complete ciphertext.

Abstract: Described are systems and methods for monitoring, detecting, and/or protecting various systems of an aerial vehicle, such as an unmanned aerial vehicle (UAV). Embodiments of the present disclosure can provide a multi-tiered system to provide monitoring, detection, and/or initiation of protection protocols in response to detected faults in connection with the electronics associated with UAV systems, such as the motor drive and/or control systems that may drive the propulsion systems of the UAV.

Abstract: Apparatus and methods are disclosed herein for remote, direct memory access (RDMA) technology that enables direct memory access from one host computer memory to another host computer memory over a physical or virtual computer network according to a number of different RDMA protocols. In one example, a method includes receiving remote direct memory access (RDMA) packets via a network adapter, deriving a protocol index identifying an RDMA protocol used to encode data for an RDMA transaction associated with the RDMA packets, applying the protocol index to a generate RDMA commands from header information in at least one of the received RDMA packets, and performing an RDMA operation using the RDMA commands.

Abstract: Learning iterations, individual ones of which include a respective bucket group selection phase and a class boundary refinement phase, are performed using a source data set whose records are divided into buckets. In the bucket group selection phase of an iteration, a bucket is selected for annotation based on output obtained from a classification model trained in the class boundary refinement phase of an earlier iteration. In the class boundary refinement phase, records of buckets annotated as positive-match buckets for a target class in the bucket group selection phase are selected for inclusion in a training set for a new version of the model using a model enhancement criterion. The trained version of the model is stored.

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: Systems and methods for configuring a virtual machine provided by a remote computing system based on the availability of one or more remote computing resources and respective corresponding prices of the one or more remote computing resources are disclosed. Users are presented with an interface that allows for selection of individual remote computing resources to be included in a custom-configured virtual machine. Also, a customized corresponding price is determined for the custom-configured virtual machine based on user selections and current availability of the selected remote computing resources to be included in the custom-configured virtual machine.

Abstract: A materialization configuration request is received via a programmatic interface from a client of a journal-based multi-data-store database. The request indicates a partitioning rule to be used to select, for respective writes indicated in committed transaction entries of a journal, the materialization node at which the writes are to be stored. A control plane component of the database verifies that a set of materialization nodes corresponding to the partitioning rule has been established, and initiates the propagation of writes from the journal to the materialization nodes by respective write appliers.

Abstract: An acoustic event detection system may employ one or more recurrent neural networks (RNNs) to extract features from audio data, and use the extracted features to determine the presence of an acoustic event. The system may use self-attention to emphasize features extracted from portions of audio data that may include features more useful for detecting acoustic events. The system may perform self-attention in an iterative manner to reduce the amount of memory used to store hidden states of the RNN while processing successive portions of the audio data. The system may process the portions of the audio data using the RNN to generate a hidden state for each portion. The system may calculate an interim embedding for each hidden state. An interim embedding calculated for the last hidden state may be normalized to determine a final embedding representing features extracted from the input data by the RNN.

Abstract: Disclosed are various embodiments for implementing passenger profiles for autonomous vehicles. A passenger of the autonomous vehicle is identified. A passenger profile corresponding to the passenger and comprising a passenger preference is identified. The passenger preference is identified. A configuration setting of the autonomous vehicle corresponding to autonomous operation of the autonomous vehicle is then adjusted based at least in part on the passenger preference.