Abstract: A device may include a memory and a processor configured to obtain cell data representative of one or more attributes associated with a state of a cell of a mobile communication network, wherein radio resources of the cell are managed based on a radio resource management model, determine, for the radio resource management model, an update timescale based on the cell data, and communicate timescale information representative of the determined update timescale to the radio resource management model, wherein the timescale information is configured to cause the radio resource management model to update model parameters to manage the radio resources of the cell based on the determined update timescale.

Abstract: Systems for fusing arthroscopic video data are described. A system comprises an arthroscopic assembly, an inertial measurement unit (IMU) mounted on the arthroscopic assembly, a processor, and a processor-readable storage medium. An arthroscopic surgical plan, images from the arthroscopic assembly, and measurements from the IMU may be obtained. The images and the measurements may be combined to form a data combination. The data combination may be filtered to form a fused data set. The fused data set may control a device. A map of an arthroscopic surgical site may be created based on the fused data set, and a position of the arthroscopic assembly with respect to the arthroscopic surgical site may be calculated. The arthroscopic surgical plan may be updated based on at least one of the map of the arthroscopic surgical site and the position of the arthroscopic assembly.

Abstract: Systems and methods for using machine learning to dynamically assess contract parameters are disclosed. According to certain aspects, an electronic device may train a machine learning model using real-world pricing and contract data, access parameters associated with a potential contract for an entity, and analyzing, using the machine learning model, the accessed parameters. Based on the analysis, the machine learning model may output a set of potential terms for the potential contract. Data indicative of this output may be availed to the entity to be used in negotiating and executing the contract, among other uses.

Abstract: Systems and methods for using machine learning to dynamically assess contract parameters are disclosed. According to certain aspects, an electronic device may train a machine learning model using real-world pricing and contract data, access parameters associated with a potential contract for an entity, and analyzing, using the machine learning model, the accessed parameters. Based on the analysis, the machine learning model may output a set of potential terms for the potential contract. Data indicative of this output may be availed to the entity to be used in negotiating and executing the contract, among other uses.

Abstract: Various disclosed embodiments can resolve output inaccuracies produced by many machine learning models. Embodiments use content order as input to machine learning model systems so that they can process documents according to the position or rank of instances in a document or image. In this way, the model is less likely to misclassify or incorrectly detect instances or the ordering between predicted instances. The content order in various embodiments can be used as an additional signal to classify or make predictions.

Abstract: Various disclosed embodiments can resolve output inaccuracies produced by many machine learning models. Embodiments use content order as input to machine learning model systems so that they can process documents according to the position or rank of instances in a document or image. In this way, the model is less likely to misclassify or incorrectly detect instances or the ordering between predicted instances. The content order in various embodiments can be used as an additional signal to classify or make predictions.

Abstract: Systems and methods in a node in an Ethernet network include, responsive to enabling burst monitoring between the node and a peer node in the Ethernet network, obtaining rate and burst size information from the peer node; configuring a counter at a traffic disaggregation point based on the rate and the burst size information, wherein the counter is based on a dual token bucket that is used to count out-of-profile frames in excess of a Committed Information Rate (CIR); and detecting a burst based on the out-of-profile frames during a monitored time interval.

Abstract: Systems and methods in a node in an Ethernet network include, responsive to enabling burst monitoring between the node and a peer node in the Ethernet network, obtaining rate and burst size information from the peer node; configuring a counter at a traffic disaggregation point based on the rate and the burst size information, wherein the counter is based on a dual token bucket that is used to count out-of-profile frames in excess of a Committed Information Rate (CIR); and detecting a burst based on the out-of-profile frames during a monitored time interval.

Abstract: A packet switch includes an ingress port; queue admission control circuitry connected to the ingress port; one or more egress queues configured to manage packet buffers; and an egress port connected to the packet buffers, wherein the packet buffers are managed such that already queued lower priority packets are discarded from the packet buffers when it is required to drop higher priority packets that should otherwise be accepted in the packet buffers. The queue admission control circuitry can be configured to determine if a packet should be dropped or not, and the queue admission control circuitry communicates to buffer reallocation circuitry that is configured to discard one or more lower priority packets to support enqueuing the higher priority packet.

Abstract: Various disclosed embodiments can resolve output inaccuracies produced by many machine learning models. Embodiments use content order as input to machine learning model systems so that they can process documents according to the position or rank of instances in a document or image. In this way, the model is less likely to misclassify or incorrectly detect instances or the ordering between predicted instances. The content order in various embodiments can be used as an additional signal to classify or make predictions.

Abstract: A packet queueing system includes an ingress port configured to receive packets; queueing logic communicatively coupled to one or more egress queues for transmission via an egress port, wherein the queueing logic is configured to maintain an Acceptable Burst Size (ABS) token bucket which is set to enable absorption of microbursts, and implement a congestion avoidance algorithm to one of randomly drop packets and queue packets, wherein the congestion avoidance algorithm only performs the randomly drop packets responsive to the ABS token bucket being empty.

Abstract: Techniques described herein implement heading identification and classification for a digital document in a digital medium environment. A document analysis system is leveraged to extract structural features from a digital document, identify heading candidates from among the structural features, validate the headings candidates, and classify validated headings into different headings types. The classified headings are then utilized to generate a sectioned version of the digital document (“sectioned document”) that is divided into different sections based on the headings. Further, a document directory is generated that includes the headings and that enables navigation to different sections of the sectioned document.

Abstract: Techniques described herein implement heading identification and classification for a digital document in a digital medium environment. A document analysis system is leveraged to extract structural features from a digital document, identify heading candidates from among the structural features, validate the headings candidates, and classify validated headings into different headings types. The classified headings are then utilized to generate a sectioned version of the digital document (“sectioned document”) that is divided into different sections based on the headings. Further, a document directory is generated that includes the headings and that enables navigation to different sections of the sectioned document.

Abstract: A packet switch includes an ingress port; queue admission control circuitry connected to the ingress port; one or more egress queues configured to manage packet buffers; and an egress port connected to the packet buffers, wherein the packet buffers are managed such that already queued lower priority packets are discarded from the packet buffers when it is required to drop higher priority packets that should otherwise be accepted in the packet buffers. The queue admission control circuitry can be configured to determine if a packet should be dropped or not, and the queue admission control circuitry communicates to buffer reallocation circuitry that is configured to discard one or more lower priority packets to support enqueuing the higher priority packet.

Abstract: System and methods of ingress packet metering include receiving a plurality of flows combined to form an envelope with a specific bandwidth, wherein the envelope is defined such that unused bandwidth from higher rank flows is usable by lower rank flows; admitting packets from the plurality of flows based on committed tokens and excess tokens; determining unused tokens in a time interval; and distributing the unused tokens based on configured weights of the plurality of flows within the envelope. The unused tokens can be provided from a lower rank flow to a higher rank flow. The unused tokens can be determined utilizing Two Rate Three Color Marker (trTCM) metering. The receiving can be at a User-Network Interface (UNI), a Network-Network Interface (NNI), or an External NNI (ENNI) port in a node.

Abstract: A packet queueing system includes an ingress port configured to receive packets; queueing logic communicatively coupled to one or more egress queues for transmission via an egress port, wherein the queueing logic is configured to maintain an Acceptable Burst Size (ABS) token bucket which is set to enable absorption of microbursts, and implement a congestion avoidance algorithm to one of randomly drop packets and queue packets, wherein the congestion avoidance algorithm only performs the randomly drop packets responsive to the ABS token bucket being empty.

Abstract: A computer implemented method and an apparatus for facilitating voice user interface (VUI) design are provided. The method comprises identifying a plurality of user intentions from user interaction data. The method further comprises associating each user intention with at least one feature from among a plurality of features. One or more features from among the plurality of features are extracted from natural language utterances associated with the user interaction data. Further, the method comprises computing a plurality of distance metrics corresponding to pairs of user intentions from among the plurality of user intentions. A distance metric is computed for each pair of user intentions from among the pairs of user intentions. Furthermore, the method comprises generating a plurality of clusters based on the plurality of distance metrics. Each cluster comprises a set of user intentions. The method further comprises provisioning a VUI design recommendation based on the plurality of clusters.

Abstract: System and methods of ingress packet metering include receiving a plurality of flows combined to form an envelope with a specific bandwidth, wherein the envelope is defined such that unused bandwidth from higher rank flows is usable by lower rank flows; admitting packets from the plurality of flows based on committed tokens and excess tokens; determining unused tokens in a time interval; and distributing the unused tokens based on configured weights of the plurality of flows within the envelope. The unused tokens can be provided from a lower rank flow to a higher rank flow. The unused tokens can be determined utilizing Two Rate Three Color Marker (trTCM) metering. The receiving can be at a User-Network Interface (UNI), a Network-Network Interface (NNI), or an External NNI (ENNI) port in a node.

Abstract: Embodiments of the invention relate to chat and, more particularly, to determining an that is to be action taken based on the type of chat session. The resolution of the chat is categorized to decide the necessary steps taken and also to monitor the agent's performance. A chat filter extracts relevant portions of a chat session. The relevant factors are taken into consideration and scored based on the feature vectors. A model is built and the type of resolution is determined. An analysis of the chat session is then performed taking into consideration several factors.

Abstract: User interactions are categorized into predefined hierarchical categories by classifying user interactions, such as queries, during a user interaction session by labeling text data into predefined hierarchical categories, and building a scoring model. The scoring model is then executed on untagged user interaction data to classify the user interactions into either action-based or information-based interactions.