Abstract: Systems and methods for presence ground truth approximation and utilization are disclosed. For example, a system detects the presence of a predefined subject, such as a person associated with a given user profile, and/or determines that authentication criteria for performing an action in association with the user profile has been satisfied. A period of time to associate data is determined, and data of one or more data types is labeled as being associated with the speaker identification event. That data may be formatted and input into one or more models to train those models to more accurately detect presence and/or determine whether authentication of a user profile should succeed.

Abstract: Product spaces for containers of non-discretized items are defined by sets of points in three-dimensional space. When a customer breaches or contacts a product space established for a container of the non-discretized items, video feeds representing the product space are displayed to an associate in a web page or another user interface. By interacting with the user interface, the associate may view the video feeds and make a determination as to whether the customer received any of the non-discretized items from the container, and to confirm an identity of the customer accordingly.

Abstract: Devices, systems, and methods are provided for generating and selecting video clips for inclusion in video sequences based on still frame images. A method may include encoding first embeddings for a first video including first images of an item at a first scene, the first embeddings indicative of features of the first scene; encoding second embeddings for a second video including second images of the item at a second scene, the second embeddings indicative of features of the second scene; encoding third embeddings for the first video, the third embeddings indicative of features of a first type of camera shot used for the first images; encoding fourth embeddings for the second video, the fourth embeddings indicative of features of a second type of camera shot used for the second images; and generating, based on the first, second, third, and fourth embeddings, a video sequence for the item.

Abstract: A speech interface device is configured to detect an interrupt event and process a voice command without detecting a wakeword. The device includes on-device interrupt architecture configured to detect when device-directed speech is present and send audio data to a remote system for speech processing. This architecture includes an interrupt detector that detects an interrupt event (e.g., device-directed speech) with low latency, enabling the device to quickly lower a volume of output audio and/or perform other actions in response to a potential voice command. In addition, the architecture includes a device directed classifier that processes an entire utterance and corresponding semantic information and detects device-directed speech with high accuracy. Using the device directed classifier, the device may reject the interrupt event and increase a volume of the output audio or may accept the interrupt event, causing the output audio to end and performing speech processing on the audio data.

Abstract: Technologies are disclosed for interacting with a virtual assistant to request updates associated with one or more events and/or perform actions. According to some examples, a user may use their voice to interact with a virtual assistant to receive updates relating to events occurring during a certain period of time. For example, a user may request an update associated with one or more events occurring that day. The system may access data sources (e.g., calendar services, email services, etc.) to obtain data associated with the events, tag the events according to one or more conditions indicated by the data, and/or rank the events according to the tags. In addition, to resolve conditions associated with the events, the virtual assistant may also include options in the update to perform certain actions and/or to provide response data. The virtual assistant may generate the update and audibly provide the update to the user.

Abstract: One or more indications may be received of a decision to deny an attempted access of a computing resource by an identity. A plurality of relevant policies may be determined whose permissions are evaluated as inputs to the decision to deny. One or more denial-related policies of the relevant policies may be determined that are associated with at least one of explicitly denying or implicitly denying the attempted access. One or more denial indications may be provided of the one or more denial-related policies. The one or more denial indications may include at least one explicit deny indication of at least one of the one or more denial-related policies that explicitly denies the attempted access. The one or more denial indications may also include at least one implicit deny indication of at least one of the one or more denial-related policies that implicitly denies the attempted access.

Abstract: Techniques for performing automated device activation and managing access to a workspace are described herein. While operating in an activated state, a user device (e.g., a wearable device) may be configured to modify movements of various mobile components (e.g., mobile drive units, robotic arms, etc.) of the workspace by emitting signals that cause the mobile components to stop or reduce speed when in proximity of the user device. An access controller device (ACD) may be used to restrict and/or allow access to the workspace and to perform operations for activating a user device that is attempting access. The ACD may receive light emissions from the user device that may be used to initiate a process for activating the user device. When the ACD receives an indication that the user device is operating in the activated state, the ACD may execute operations for enabling access to the workspace.

Abstract: Methods and apparatus for partitioned private interconnects to provider networks are described. At least a portion of available bandwidth of a private physical interconnect between a provider network and a connectivity intermediary's network is designated as the bandwidth limit of an interconnect partition set up on behalf of a customer at the request of the intermediary. The intermediary's network comprises one or more devices to which at least one of the customer's devices is connected. Access to one or more resources of the provider network via the interconnect is enabled. Traffic monitoring results associated with the interconnect are used to enforce the designated bandwidth limit of the partition.

Abstract: In networks, some communication links may be provided as part of a network underlay to reach outer networks/regions. Technologies are disclosed for monitoring/analyzing targeted networks using probe packets sent from outside of the targeted networks. The probe packets are configured to include an outer IP packet encapsulating an inner UDP packet, where the inner UDP packet indicates a source of the probe (e.g., an agent) as both the source and destination address. Time to Live (TTL) values for the inner and outer packets are controlled to propagate the packet through the network using the underlay to access the outer network/regions.

Abstract: A device management service may enforce compliance of remote devices with device specifications by disabling or enabling use of client certificates by applications installed on the devices. The device management service receives configuration data from an agent installed on the remote device. If the device management service determines that the device is no longer compliant with specifications for the device, then the device management service may prevent subsequent use of client certificate(s) by applications on the device to establish certificate-based connections. For example, the device management service may disable or revoke a client certificate or may instruct the device to disable or remove the client certificate. If the device becomes compliant at a subsequent time, then the device management service may enable the client certificate or cause a new client certificate to be sent to the device.

Abstract: Systems and methods for usage-based device naming and grouping are disclosed. For example, trigger events that indicate when a device should be renamed, added to a device group, and/or added to a routine may be determined. Usage data representing usage of the device may be received and utilized to determine if a trigger event occurs. When a trigger event occurs, a recommendation for renaming, grouping, etc. may be determined and sent to a user device. Upon acceptance of the recommendation, the device may be renamed, grouped, and/or added to a routine.

Abstract: This disclosure describes techniques for identifying users that are enrolled for use of a user-recognition system and updating enrollment data of these users over time. To enroll in the user-recognition system, the user may initially scan his or her palm. The resulting image data may later be used when the user requests to be identified by the system by again scanning his or her palm. However, because the characteristics of user palms may change over the time, the user-recognition system may continue to build more and more data for use in recognizing the user, in addition to removing older data that may no longer accurately represent current characteristics of respective user palms.

Abstract: Threats can be determined from anomalous events based on artificial intelligence (AI) models. For example, a computer system stores, based on an output of a first AI model, first information indicating that a first event cluster of the first event clusters is associated with a threat classification and that a second event cluster of the first event clusters is associated with a non-threat classification. The computer system receives a first dataset representing first events and generate a first input to the first AI model based on the first dataset. The computer system determines, based on the first input to the first AI model, second event clusters and that a third event cluster of the second event clusters has no correspondence in the first event clusters and is associated with an unknown classification. The computer system generates second information indicating that the third event cluster is associated with the unknown classification.

Abstract: An address decoder for a system is disclosed that can be used for different source nodes in the system. Each address decoder can be configured to perform a plurality of decode methods that can be customized for each source node. A first decode method can be used to determine a target node from a plurality of target nodes based on a destination address of the transaction. A second decode method can be used to assign a dedicated target node as the target node irrespective of the destination address of the transaction. The second decode method can be used to route the transaction to the dedicated target node for testing and verification operations.

Abstract: A portion of a radio-based application (RBA) is executed at a first runtime environment (RTE) launched at a server. The first RTE includes a software program for processing messages between a pair of layers of the RBA. In response to determining that the portion of the RBA is to be executed at a second RTE, at least a subset of state information pertaining to the inter-layer messages is transferred to the second RTE without pausing the RBA. After the state information is transferred, the portion of the RBA is run at the second RTE.

Abstract: Methods, systems, and computer-readable media for implementing rule-based triggering in a provider network are disclosed. When conditions are met for one or more triggers, one or more rules that comprise the one or more triggers are determined. The conditions are determined in a provider network comprising a plurality of resources. One or more actions are determined in the one or more rules that comprise the one or more triggers. The one or more actions are performed, comprising modifying one or more of the resources in the provider network.

Abstract: Described are systems and methods for determining an agent that performed an event within a materials handling facility. A series of overhead images that include representations of the event location and one or more agents are processed to determine a motion or movement of the agent over a period of time. For example, a motion model representative of a motion of the agent over a period of time is generated from the images. A distance between the motion model and the event location is also determined. An association between the agent and the event may be determined based on the motion model and the distance between the motion model and the event location.

Abstract: Techniques are described for providing managed computer networks, such as for managed virtual computer networks overlaid on one or more other underlying computer networks. In some situations, the techniques include facilitating replication of a primary computing node that is actively participating in a managed computer network, such as by maintaining one or more other computing nodes in the managed computer network as replicas, and using such replica computing nodes in various manners. For example, a particular managed virtual computer network may span multiple broadcast domains of an underlying computer network, and a particular primary computing node and a corresponding remote replica computing node of the managed virtual computer network may be implemented in distinct broadcast domains of the underlying computer network, with the replica computing node being used to transparently replace the primary computing node in the virtual computer network if the primary computing node becomes unavailable.

Abstract: Systems, methods, and computer-readable media are disclosed for determining obstacle data based on sensor data such as greyscale data and depth data. Based on the obstacle data navigation data may be determined and used by an autonomous vehicle to navigate an environment such as a warehouse or storage facility. The obstacle data may be determined by determining three-dimensional representations of the greyscale data and the depth data and segmented and combining or fusing the three-dimensional representations of the greyscale data and the depth data. The system used to determine the obstacle data may be trained to avoid false obstructions and omitted obstructions.

Abstract: A modified measured boot approach is utilized for establishing a secure communication link between two devices. Each device may execute a respective boot process until the device reaches the stage responsible for establishing the communication link with the other device. Each device may exchange its respective self-signed certificate and extend its certificate chain with the self-signed certificate received from the other device. A secure link can be established using the public key of the other device as a based key for a key exchange protocol.

Abstract: This disclosure describes techniques and systems for encoding instructions in audio data that, when output on a speaker of a first device in an environment, cause a second device to output content in the environment. In some instances, the audio data has a frequency that is inaudible to users in the environment. Thus, the first device is able to cause the second device to output the content without users in the environment hearing the instructions. In some instances, the first device also outputs content, and the content output by the second device is played at an offset relative to a position of the content output by the first device.

Abstract: A method of optimizing a delivery route for a delivery vehicle driver and a delivery assistant includes: identifying a delivery route for a delivery vehicle; determining, for each of the packages to be delivered using the delivery route, a first delivery time for a delivery vehicle driver of the delivery vehicle to deliver the respective package without the delivery assistant, a second delivery time for a delivery assistant of the delivery vehicle to deliver the respective package without the delivery vehicle driver, and a third delivery time for both the delivery assistant and the delivery vehicle driver to deliver the respective package; determining minimum times needed by the delivery vehicle driver and the delivery assistant to deliver the packages using the delivery route; and determining that a minimum of the estimated total delivery times corresponds to a first subset and a second subset of the packages.

Abstract: This disclosure describes techniques for increasing the baseline performance of a burstable instance to an increased performance level for a limited time period. For example, a user may schedule a time period which the burstable instance has access to 100% of a CPU, instead of competing with other burstable instances even during periods of bursting as in prior techniques. In some cases, the user uses credits to reserve the time periods at which the increased performance level is requested. After receiving the reservation, a resource system selects computing resources to host the burstable instance such that the burstable instance, can operate at the requested increased performance level. After the time period has ended, the burstable instance may return to the baseline performance level.

Abstract: An aerial vehicle or another system having moving components may be configured with a capacitive sensing system for detecting body parts of humans or other animals within proximity. The capacitive sensing system includes conductive components provided in association with surfaces of housings within which motors rotate propellers or other objects. The capacitors are coupled to circuits including transistors, resistors, capacitors or other features that are configured to determine levels of capacitance on the conductive components during operations of the aerial vehicle or other system. When a body part approaches a conductive component, and disrupts a level of capacitance on a capacitor coupled to the conductive component, a change in the level of capacitance on the capacitor is detected. Where the change exceeds a predetermined threshold, predetermined actions such as stopping or otherwise altering operations of the motors may be performed.

Abstract: Proxy-based scaling may be performed for databases. A proxy may be implemented for a database that can establish a connection between the proxy and a database engine to perform a database queries received from a client at the proxy. A scaling event may be detected for the database responsive to which the proxy may establish a connection with a new database engine which may, in some embodiments, have different capabilities or resources that address the features or criteria that triggered the scaling event. Session state may be copied from the database engine to the new database engine so that the new database engine may be able to provide access to the database on behalf of requests received from the client through the proxy.

Abstract: Systems and methods for activity-based device recommendations are disclosed. For example, historical usage data associated with a device may indicate that the device is likely to be associated with a given state at a given time. When the device is not in the anticipated state, a recommendation to transition the device state, for example, may be sent. Additionally, a determination of the activity state associated with the device, such as an active state, an asleep state, and/or an away state may be utilized to determine the recommendation to surface, to determine whether to send a recommendation, and when and/or how to send the recommendation.

Abstract: An aerial vehicle is programmed or configured to respond to reports of events or conditions within spaces of a facility. The aerial vehicle travels to a location of a reported event or condition and captures data using onboard sensors. The aerial vehicle independently determines whether the reported event or condition is occurring, or is otherwise properly addressed by resources that are available at the location, using images or other data captured by the onboard sensors. Alternatively, the aerial vehicle transmits a request for additional resources to be provided at the location, where necessary. A map of the location generated based on images or other data captured by the onboard sensors may be utilized for any purpose, such as to make one or more recommendations of products that are appropriate for use at the facility.

Abstract: Techniques for routing data, in a system including multiple assistants, are described. A user device may store configuration data for a virtual assistant, where the configuration data includes a virtual assistant identifier, one or more resource identifiers, and optionally a virtual assistant name. A resource identifier may correspond to a component or device(s) of the virtual assistant. When the user device receives event data associated with a virtual assistant identifier, the user device may use stored configuration data to determine a resource identifier(s) associated with the virtual assistant identifier, associated with the event data. The user device may thereafter send the event data to the component and/or device(s) corresponding to the determined resource identifier(s).

Abstract: Techniques for providing a contextual voice user interface that enables a user to query a speech processing system with respect to the decisions made to answer the user's command are described. The speech processing system may store speech processing pipeline data used to process a command. At some point after the system outputs content deemed responsive to the command, a user may speak an utterance corresponding to an inquiry with respect to the processing performed to respond to the command. For example, the user may state “why did you tell me that?” In response thereto, the speech processing system may determine the stored speech processing pipeline data used to respond to the command, and may generate output audio data that describes the data and computing decisions involved in determining the content deemed responsive to the command.

Abstract: A system receives a first indication associated with a first device picking up a package and transmits a first instruction to the first device to travel to a location associated with transferring the package to a second device. The system may transmit a second instruction to the second device to travel to the location to receive the package from the first device. The system receives a second indication associated with the package being transferred from the first device to the second device at the location. One or more third devices may meet at the location to transfer packages to the second device. In some instances, the location may be determined based at least in part on a current location of the first device and/or a current location of the second device.

Abstract: At a machine learning service, a determination is made that an analysis to detect whether at least a portion of contents of one or more observation records of a first data set are duplicated in a second set of observation records is to be performed. A duplication metric is obtained, indicative of a non-zero probability that one or more observation records of the second set are duplicates of respective observation records of the first set. In response to determining that the duplication metric meets a threshold criterion, one or more responsive actions are initiated, such as the transmission of a notification to a client of the service.

Abstract: Techniques for dividing a geographical area into districts are described herein. Geospatial vector data, barrier geospatial vector data, road infrastructure data, and historical delivery demand data for a geographical area may be obtained. A plurality of clusters from a stratified sampling of data points for the delivery demand data and barrier penalties from a barrier-aware road graph are generated. A first set of polygons for the plurality of clusters may be generated using a concave hull algorithm. A second set of polygons may be generated using a barrier constrained network Voronoi algorithm that uses the barrier-aware road graph and the first set of polygons as seeds. The second set of polygons may be modified using a bounded Voronoi algorithm that uses a raster cost allocation based on barrier penalties. Coordinates for each polygon of the modified second set of polygons are determined that divide the geographical area.

Abstract: Described is a system and method for presenting event information to a user and, if necessary, obtaining confirmation of different aspects (user, item, action) of the event. In some implementations, an event includes a user, an action, and an item. For example, an event may include a user picking an item from an inventory location, a user placing an item into a tote associated with the user, etc. If the aspects of the event cannot be determined with a high enough degree of confidence, a user interface may be generated and sent to the user requesting confirmation of one or more of the aspects of the event.

Abstract: Techniques for outputting supplemental content are described. A system may receive input data corresponding to a user input, and determine and present output data responsive to the user input. After causing the output data to be presented, the system may determine supplemental content is to be presented. Based on this, the system may determine first presentation data representing first supplemental content is to be visually presented, and second presentation data representing second supplemental content is to be audibly presented. The system may use a machine learning model to determine the first supplemental content is to be presented instead of the second supplemental content. The system may thereafter cause a device to use the first presentation data to visually present the first supplemental content.

Abstract: An apparatus for diverting and/or folding articles includes an infeed conveyor, an outfeed conveyor, and a diverter. The diverter is a non-contact, fluid emitting diverter, configured to emit a fluid jet to exhibit the diverting force on the impact zone of the article at a side of the article facing away from the outfeed entry. An angle of the average direction of the diverting force of the fluid jet with the outfeed path at the outfeed entry is in the range of 5° to 85°.

Abstract: Systems and methods to reduce aerodynamic drag and/or affect flight characteristics of an aerial vehicle may include adjustable fairings associated with one or more components of the aerial vehicle. The adjustable fairings may be coupled to and at least partially surround a motor, propulsion mechanism, motor arm, strut, or other component of an aerial vehicle. In addition, the adjustable fairings may be passively movable between two or more positions responsive to airflow around the fairings, and/or the adjustable fairings may be actively moved between two more positions to affect flight characteristics. Further, the adjustable fairings may include actuatable elements to alter a portion of an outer surface of the fairings to thereby affect flight characteristics. In this manner, adjustable fairings associated with various components of an aerial vehicle may reduce aerodynamic drag and/or may improve control and safety of an aerial vehicle.

Abstract: The present disclosure generally relates to systems and methods for searching media content. In some implementation examples, a search system receives an input query, generates a query embedding of the input query, and generates a bias mitigation transformation associated with a sensitive attribute. Based on the query embedding and the bias mitigation transformation, the search system generates a transformed query embedding that suppresses at least a portion of the query embedding related to the sensitive attribute. Using the transformed query embedding, the search system executes a similarity search in a media embedding model to identify one or more media embeddings that are similar to the transformed query embedding and transmits the one or more media embeddings.

Abstract: Robotic end effectors may include a suction cup, one or more grasping fingers, and one or more flexible nails to securely and reliably engage, grasp, and cage items. The grasping fingers may move between open and closed positions to grasp items. In addition, the flexible nails may be coupled to ends of the grasping fingers to facilitate caging of items by the fingers and nails. For example, the flexible nails may bend, flex, or slide under, around, or relative to items and thereby enable grasping and caging of portions of items by the fingers and nails. The nails may be formed of various materials, with various layers or thicknesses of materials, and/or with variable flexibility or friction properties. Further, the nails may be transitioned or actuated between multiple configurations, including a sliding configuration and a grasping configuration.

Abstract: Systems, methods, and computer-readable media are disclosed for systems and methods for automated video summary generation using textual quotes. Example methods may include determining first text representing a phrase spoken in video content, determining that the first text is present in first subtitle data of first video content, determining a first timestamp and a second timestamp associated with the first text in the first subtitle data, determining a first video segment of the first video content corresponding to the first timestamp and the second timestamp, and generating a first video summary for the first video content, the first video summary comprising the first video segment.

Abstract: Autonomous mobile robots for transporting carts are described. An example robotic cart transport system includes a cart for transport and a robotic transport. The robotic transport includes a transport cab and a load handler. The transport cab includes a drive system and a sensor array positioned over the transport cab. The load handler includes a load base supported by a directable caster wheel, a lift table positioned over the load base, a lift abutment anchor, and a lift drive. The robotic transport can autonomously position the load handler under a cart, and the lift drive can raise the lift table up and off of the top surface of the load base, to a lifted position seated against the lift abutment anchor. The lift table will contact and lift the cart in this motion, and the cart can be transported to a new location by the robotic transport.

Abstract: Techniques are described for managing execution of programs. In some situations, program execution is managed for multiple users using excess program execution capacity of one or more computing systems. In some such situations, excess or otherwise unused program execution capacity may be made available to execute programs on a temporary basis, such that the programs executing using the excess program execution capacity may be terminated at any time if other preferred use for the excess program execution capacity arises. The excess program execution capacity may in some situations be provided in conjunction with other dedicated program execution capacity that is allocated to particular users, such as to use unused dedicated capacity of some users as excess capacity for other users. In some situations, the techniques are used in conjunction with a fee-based program execution service that executes multiple programs on behalf of multiple users of the service.

Abstract: Embedding an insecure application within a host application is performed. Modern applications may incorporate smaller applications into a common interface with some applications requiring more privilege than others. A host application may be configured to load an application into a sandboxed frame to create separate security zones by isolating the originating domains of the respective applications. Security authorization for the sandboxed application may be obtained by the host application as part of initialization. Then, operations to be performed by the sandboxed application that require origination from the host domain may be requested by the application to the host using a Remote Procedure Call (RPC) mechanism. The host may then perform the requested operations on behalf of the application and return the results via RPC. In this manner, the embedded application may employ greater application privileges without increasing security vulnerabilities of the host.

Abstract: A computer system and associated methods are disclosed for mitigating side-channel attacks using memory page remapping. The computer system includes a main memory and a shared cache, the shared cache implementing cache set associativity determined by a portion of memory addresses of the main memory. Multiple physical memory pages are reserved for mapping to a virtual memory page, the physical memory pages differing in the respective portions of their memory addresses determining cache set associativity. Accesses to the virtual memory page result in a mapping of one of the reserved physical memory pages to the virtual memory page, with remapping events causing different ones of the physical memory pages to become mapped. This remapping results in varying cache set associativity of elements stored in the virtual memory page over time.

Abstract: Described are systems and methods for deduplicating shared dependencies for micro-frontend applications. Embodiments of the present disclosure can provide hosting of shared dependencies on a networked resource, such as a content delivery network (CDN), and import statements of the shared dependencies can be replaced with calls to a network identifier specifying a network location where the shared dependencies are hosted. Accordingly, the shared dependencies can be natively imported from the network location and shared among the micro-frontend bundles.

Abstract: Techniques for updating a chatbot definition are described. In some examples, this updating includes receiving an edit to intent characteristics for a stage of a plurality of stages in a chatbot flow, identifying a stage to modify based on at least the received edit, identifying, for the stage, a default update rule based on the chatbot definition, and updating the stage in the chatbot definition by inferring a next step according to one or more rules for the stage including the identified default update rule.

Abstract: A determination is made as to whether a value of a first parameter of a first application is to be obtained using a natural language interaction. Based on received input, a first service of a plurality of services is identified. The first service is to be used to perform a first task associated with the first parameter. Portions of the first application to determine the value of the first parameter and to invoke the first service are generated.

Abstract: Parameters of a pool of computing resources to be utilized for machine learning tasks from a set of entities are stored, including a category of the computing resources, and a post-task-completion retention period during which, after completion of a task, at least a portion of data stored at the resource is not to be deleted. A compute instance of the pool is assigned to a task requested from the set of entities after determining that one or more configuration settings of the instance satisfy a preference indicated in the request for the task, and that the retention period of the instance relative to a completion of an earlier task on the instance has not expired. A result of the task is stored.

Abstract: In response to determining that continuous data protection is to be enabled for a particular table of a database service, a service component verifies that automated transmission of change records of the table to a log-structured journal has been configured. A given change record comprises a before-image and an after-image associated with a committed database write, and is assigned a unique sequence number. In response to a determination to restore the table as of a specified point in time, a restore record set is identified from the journal with respect to a selected snapshot of the table. The restore record set includes change records which are not represented in the snapshot and are to be represented in the restored table. A restore result table is created using the selected snapshot and the restore record set.

Abstract: Techniques for presenting content by a voice-controlled device are described. In an example, the voice-controlled device is operatively coupled to a presentation device and supports dual mode functionalities. In a first mode, the voice-controlled device sends content for presentation at the presentation device. In a second mode, the voice-controlled device presents the content at a presentation interface of the voice-controlled device. Based on speech input from a user indicating an issue with a content presentation in the first mode, the voice-controlled device switches to the second mode and presents a message at the presentation interface indicating that subsequent content presentations would be presented at this interface. The voice-controlled device remains in the second mode until receiving additional speech input necessitating a switch to the first mode.