Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.

Abstract: A method, computer program product, and computing system for increasing communication session downtime. A first computing device of a plurality of computing devices transmits a handshake signal to a second computing device of the plurality of computing devices at a predetermined time interval and the second device receives the handshake signals. A communication session between the first computing device and the second computing device is ended when the second computing device does not receive a number X of expected consecutive handshake signals from the first computing device. Prior to a reboot of the first computing device, the number X of expected consecutive handshake signals is increased to a number Y of expected consecutive handshake signals, such that the communication session between the first computing device and the second computing device will be caused to end when the second device does not receive the number Y of expected consecutive handshake signals from the first computing device.

Abstract: A system for establishing network reliability for a computer network includes a plurality of initiating nodes to transmit a plurality of packets across the network and a plurality of receiving nodes to receive the plurality of packets via the network. A portion of the plurality of packets transmitted from the initiating nodes are appended with identifiers that correspond to characteristics of entities using the network. The plurality of receiving nodes transmit acknowledgement receipts associated with packets appended with the identifiers to a network monitoring system that monitors quality of service associated with the characteristics.

Abstract: A computerized method determines erasure coding (EC) formats for data extents in storage systems. Traffic history data of a data extent to be stored in the storage system is obtained. Estimated future traffic data is generated using a traffic estimation model, wherein the traffic history data is provided to the model as input. A current storage system constraint is calculated using the obtained traffic history data, and a constraint adjustment value is determined using a proportional, integral, derivative (PID) controller based on the current storage system constraint. An EC format for the data extent is determined using the estimated future traffic data and the determined constraint adjustment value and the data extent is stored in the storage system using the determined EC format. Use of the model and the PID controller balances optimized storage use with efficient data traffic handling.

Abstract: Systems and methods for processing a distributed transaction are provided. A distributed execution statement including a plurality of tasks for executing a query and a table to be modified by the executed query is received. A first task is transmitted to a first backend node and a second task is transmitted to a second backend node. A first confirmation that the first task is executed and a second confirmation that the second task is executed are received. Executing the first task includes making a first modification to the table and a first identification of the first modification, and executing the second task includes making a second modification to the table and a second identification of the second modification. Based at least on each of the first task and the second task being completed, committing the first modification and the second modification to the table.

Abstract: Operations of a workload are assigned to physical resources of a physical device array. The workload includes a graph of operations to be performed on a physical device array. The graph of operations is partitioned into subgraphs. Partitioning includes at least minimizing the quantity of subgraphs and maximizing resource utilization per subgraph. A logical mapping of the subgraph to logical processing engine (PE) units is generated using features of the subgraph and tiling factors of the logical PE units. The logical mapping is assigned to physical PE units of the physical device array at least by minimizing network traffic across the physical PE units. The operations of the subgraph are performed using the physical PE units to which the logical mapping is assigned. This process enhances the computational efficiency of the array when executing the workload.

Abstract: Images captured by a camera moving in an environment are received, and for each of a plurality of points in one of the images, outputs are computed using a neural network. The outputs comprise: a trajectory depicting the point in each of the plurality of images, as well as, for each trajectory, a prediction of visibility of the trajectory in each of the images and a prediction of whether the trajectory depicts a static or moving surface in the environment. The neural network receives the images and points as input and computes the outputs, wherein the outputs comprise for each of the trajectories, confidence data. The outputs are sent to a downstream process selected from any of: visual odometry, structure from motion, human body tracking, video editing, vehicle tracking.

Abstract: Example solutions for augmenting text inputs for analyzing clinical documents include: identifying a clinical named entity within text content of a clinical input document; adding an anchor tag to the text content, the anchor tag including an entity ID and a clinical attribute associated with the clinical named entity, thereby generating an enhanced input document; and submitting a first query prompt and the enhanced input document to a generative artificial intelligence (GAI) model, the first query prompt including task text and anchoring markup text, the task text includes instructions of a task to be performed by the GAI model on the enhanced input document, the anchoring markup text includes a template of the anchor tag and instruction to add a reference anchor tag to output generated by the GAI model, where the reference anchor tag is to include the entity ID and the clinical attribute of the anchor tag.

Abstract: In various examples there is a knowledge base construction and/or maintenance system for use with a probabilistic knowledge base. The system has a probabilistic generative model comprising a process for generating text or other formatted data from the knowledge base. The system has an inference component configured to generate inference results, by carrying out inference using inference algorithms, run on the probabilistic generative model, in either a forward direction whereby text or other formatted data is generated, or a reverse direction whereby text or other formatted data is observed and at least one unobserved variable of the probabilistic generative model is inferred. The inference component is configured to update the knowledge base using at least some of the inference results.

Abstract: A stream tool is disclosed that allows a user to seamlessly connect with the different data streams, regardless of the streams' transmission platforms or communication protocols, in order to visually see a representation of the type of data that the data streams are transmitting. A user may specify a particular data stream and provide corresponding connection details. A collection of abstracted software functions enable interaction with the different stream platforms and protocols. Using these abstracted functions, a stream-processing service accesses a requested data stream and samples its data events for either sample timeframe or up to a threshold number of data events. The sampled data events are parsed and visually presented to the user in an easy-to-understand format. The user may then inspect the data stream's data for use in developing robust applications that may integrate and use such data.

Abstract: A computerized method provides secure and controlled access provisions for data exploration in managed compute datasets. A workspace on a compute cluster is created for a user with permissions to the workspace. The compute cluster that includes a code analyzer is provisioned within a cloud computing infrastructure. The code analyzer is configured to: receive a data query from a task executing on the compute cluster; identify a query operation included in the data query; compare the query operation to a list of prohibited query operations for the workspace to which the user has the permissions; and terminate the data query without execution when the query operation is in the list of prohibited query operations for the workspace to which the user has the permissions.

Abstract: Embodiments of the disclosure provide application management capabilities to enterprises. A computing device of a user, associated with the enterprise, receives an enrollment token signed with a certificate. The enrollment token includes an enterprise identifier associated with the enterprise. The computing device receives a package containing one or more applications. The package also includes an enterprise identifier. Installation and execution of one or more applications from the received package is accepted or rejected based on a comparison of the enterprise identifier from the enrollment token with the enterprise identifier from the received package or application. A web service provides validation services by monitoring the installation and execution of applications on the computing devices associated with the enterprise.

Abstract: A computerized method trains and uses a multimodal fusion transformer (MFT) model for content moderation. Language modality data and vision modality data associated with a multimodal media source is received. Language embeddings are generated from the language modality data and vision embeddings are generated from the vision modality data. Both kinds of embeddings are generated using operations and/or processes that are specific to the associated modalities. The language embeddings and vision embeddings are combined into combined embeddings and the MFT model is used with those combined embeddings to generate a language semantic output token, a vision semantic output token, and a combined semantic output token. Contrastive loss data is generated using the three semantic output tokens and the MFT model is adjusted using that contrastive loss data. After the MFT model is trained sufficiently, it is configured to perform content moderation operations using semantic output tokens.

Abstract: To avoid inconsistencies caused by clock skew across data storage tiers, a point-in-time restore service creates a restore account, restores a partition of the database to its state at the designated point-in-time, including data from that time. A restored value is read from the data and a list is retrieved of segments written to a disaggregated storage tier by the existing partition. The disaggregated storage tier includes a first segment with a first value and a second segment with a second value, the values indicating their creation order. A first comparison is made between the restored value and the first value, and a second comparison is made between the restored value and the second value. Based on these comparisons, the first segment but not the second segment is copied to the restore account.

Abstract: Example solutions for providing route aggregation as a service (RaaS) are disclosed. A RaaS server receives original routing tables from routers in a wide area network (WAN), aggregates the routes by identifying common prefixes, and returns more compact aggregated routing tables to the routers. The routers use the aggregated routing tables to efficiently route data traffic in the WAN. Multiple resiliency approaches are disclosed, in order to prevent the routers from flushing the aggregated routes in the event that the RaaS server experiences an outage and the border gateway protocol (BGP session between each router and the RaaS server is lost. Example resiliency measures includes the use of a long lived stale time (LLST), reaching a length of perhaps weeks, during which the routers continue to use the aggregated routing tables, and the use of mirroring the aggregated routing tables in other RaaS.

Abstract: Natural language to database query translation optimization is disclosed. Due to the flexibility of natural language and database query languages, translations may differ in form, yet still be valid. A natural language query is translated to a first database query in a database query language using a query translator. A first and second database query result are generated by performing a first and second database query on a database. The second database query differs from the first database query in form (e.g., order of the query parameters), but is functionally similar to the first database query, such that an ideal query translation would produce equivalent database query results (e.g., same retrieved information, even if in a different order). If the first database query result matches the second database query result, training reinforcement is provided, but if not, a training adjustment is provided for the query translator.

Abstract: Aspects of the disclosure identify a pattern of features associated with a computing component indicating an increased probability that the component incurs an uncorrectable error. Historical component data, component features, server data, and server services are utilized to identify the patterns that correlate to an increased probability that the component incurs an uncorrectable error. For example, this data is used as input into a machine learning platform. Proactive and/or mitigating actions that reduce the probability of an uncorrectable error or its negative effects are presented and/or implemented to minimize or eliminate disruption in cloud computing services.

Abstract: In various examples there is a computer-implemented method performed by a rendering device. A depth image is rendered from a 3D model according to a predicted pose. The depth image is divided into a plurality of tiles. An error map is computed comprising, for each tile of the plurality of tiles, a planar deviation error value that represents a geometric complexity of the tile and comprises an extent to which a geometry of the tile deviates from a plane. The error map, or information derived from the error map, is sent to a display device.

Abstract: Systems and methods for inferring the favorite authors and collaborators of a user are provided. The method includes storing an enterprise authorship database, identifies a document accessed by a user identifier (UID), identifying contributors to the identified document, generating a contribution score for each contributor of the identified contributors, based on each generated contribution score, determining one or more authors of the identified document, creating an authorship record by associating UIDs of the determined one or more authors with the identified document, and updating the enterprise authorship database with the created authorship record, wherein the authorship record is used to identify a relationship between the UID and the determined one or more authors and generate a recommendation for the UID based on the identified relationship.

Abstract: The disclosure herein describes enabling menuless operations using spatially aware tags with virtual geo-fenced boundaries. A tag manager implemented on a processor obtains movement data associated with an ultrawide band (UWB) enabled initiator device within a selected geo-fenced zone. The movement data is generated by one or more UWB enabled responder(s) within the selected geo-fenced zone. The movement data includes data describing 3D movements of the initiator device within the selected geo-fenced zone. A tag manager identifies a sequence of 3D movements of the initiator device using the movement data. The tag manager maps the sequence of 3D movements to zone-specific and/or user-specific action(s) using a menuless operations mapping table. The tag manager triggers a target computing device within the selected geo-fenced zone to perform the matched action(s). The target computing device can include an internet of things (IoT) device, a computing device, or the initiator device itself.