Abstract: One embodiment provides a computer implemented method, including: receiving information corresponding to a customer of a seller, wherein the information is related to credit information of the customer; generating a credit attribute for the customer with respect to the seller, wherein the generating includes utilizing a plurality of artificial intelligence agents that each analyze at least a subset of the information to each generate an agent version of the credit attribute; and recommending a deferral of at least a portion of a pending invoice of the seller for the customer, wherein a value of the deferral is based upon the credit attribute.

Abstract: A time series forecasting system is disclosed that obtains a time series forecast request requesting a forecast for a particular time point. The forecast request identifies a primary time series dataset for generating the requested forecast and a set of features related to the primary time series dataset. The system provides the primary time series dataset and the set of features to a model to be used for generating the forecast. The model computes a feature importance score for one or more features and selects a subset of features based on their feature importance scores. The model determines attention scores for a set of data points in the primary time series dataset based on the selected subset of features. The system predicts an actual forecast for the particular time point based on the attention scores and outputs the actual forecast and explanation information associated with the actual forecast.

Abstract: A micro-electro-mechanical system (MEMS) device includes a first substrate, an interconnect layer, a MEMS device layer, a stopper and a second substrate. The interconnect layer is disposed on the first substrate and includes a plurality of conductive layers and a plurality of dielectric layer stacked alternately. The MEMS device layer is bonded on the interconnect layer and includes a proof mass. The stopper is disposed directly under the proof mass and spaced apart from the proof mass, where the stopper is surrounded by a portion of the interconnect layer, and the stopper includes a bottom portion constructed of one of the plurality of conductive layers, and a silicon-based layer disposed on the bottom portion. The second substrate includes a cavity and is bonded on the MEMS device layer.

Abstract: A method and system are provided of processing a search query entered by a user of a device having a text input interface with overloaded keys. The search query is directed at identifying an item from a set of items. Each of the items has a name including one or more words. The system receives from the user an ambiguous search query directed at identifying a desired item. The search query comprises a prefix substring of at least one word in the name of the desired item. The system dynamically identifies a group of one or more items from the set of items having one or more words in the names thereof matching the search query as the user enters each character of the search query. The system also orders the one or more items of the group in accordance with given criteria.

Abstract: An HVAC system includes a variable-speed compressor which compresses refrigerant flowing through the HVAC system, a blower which provides a flow of air through the HVAC system at a controllable flow rate, and a controller communicatively coupled to the variable-speed compressor and the blower. The controller receives a demand request, which includes a command to operate the HVAC system at a predefined setpoint temperature. In response to receiving the demand request, a setpoint temperature associated with the HVAC system can be adjusted to the predefined setpoint temperature. A speed of the variable-speed compressor is decreased to a low-speed setting. Based on the decreased speed of the variable-speed compressor, an air-flow rate can be determined to provide by the blower. The controllable flow rate of the flow of air provided by the blower can be adjusted based on the determined air-flow rate.

Abstract: Techniques are described that facilitate dynamic multimodal segmentation selection and fusion in medical imaging. In one example embodiment, a computer processing system receives a segmentation dataset comprising a combination of different image segmentations of an anatomical object of interest respectively segmented via different segmentation models from different medical images captured of the (same) anatomical object, wherein the different medical images and the different image segmentations vary with respect to at least one of, capture modality, acquisition protocol, or acquisition parameters. The system employs a dynamic ranking protocol as opposed to a static ranking protocol to determine ranking scores for the different image segmentations that control relative contributions of the different image segmentations in association with combining the different image segmentations into a fused segmentation for the anatomical object.

Abstract: Techniques for optimizing technologies related to network path tracing and network delay measurements are described herein. Some of the techniques may include using an IPv6 header option and/or segment identifier field of a segment list or a TLV of a segment routing header as a telemetry data carrier. The techniques may also include using an SRv6 micro-segment (uSID) instruction to indicate to a node of a network that the node is to perform one or more path tracing actions and encapsulating the packet and forward. Additionally, the techniques may include using short interface identifiers corresponding to node interfaces to trace a packet path through a network. Further, the techniques may include using short timestamps to determine delay measurements associated with sending a packet through a network. In various examples, the techniques described above and herein may be used with each other to optimize network path tracing and delay measurement techniques.

Abstract: Systems and methods for reducing delays between the time at which a need for a resynchronization of data replication between a volume of a local CG and its peer volume of a remote CG is detected and the time at which the resynchronization is triggered (Reseed Time Period) are provided. According to an example, information indicative of the direction of data replication between the volume and the peer volume is maintained within a cache of a node. Responsive to a disruptive operation (e.g., relocation of the volume from a first node to a second node), the Reseed Time Period is lessened by proactively adding a passive cache entry to a cache within the second node at the time the CG relationship is created when the second node represents an HA partner of the first node and prior to the volume coming online when the second node represents a non-HA partner.

Abstract: Described embodiments provide systems and methods for detecting autonomous programs is provided. A device, intermediary to a plurality of clients and a plurality of servers, can receive a first request from a first client of the plurality of clients to a server of the plurality of servers via a connection between the device and the first client. The device can include, into a response from the server to the first client, a uniform resource locator (URL) comprising one or more randomly generated characters within a predetermined character space. The device can determine that the first client has an autonomous program responsive to receiving a second request from the first client using the URL. The device can terminate, responsive to the determination, the connection to the first client.

Abstract: An improved heterostructure for an optoelectronic device is provided. The heterostructure includes an active region, an electron blocking layer, and a p-type contact layer. The heterostructure can include a p-type interlayer located between the electron blocking layer and the p-type contact layer. In an embodiment, the electron blocking layer can have a region of graded transition. The p-type interlayer can also include a region of graded transition.

Abstract: In an example, a computer-implemented method for natural language query translation comprises: receiving, by one or more processors, a natural language query; processing, by the one or more processors, the natural language query to identify an intent and a variable of the natural language query; converting, by the one or more processors, the identified variables into low-level variables; combining the identified intent and the low level variables to form a database expression; querying, by the one or more processors, a database storing flight information, using the database expression; and creating, by the one or more processors, at least one graphical representation based on a result of the querying of the database.

Abstract: A method for predicting parametric vocoder parameter includes receiving a text utterance having one or more words, each word having one or more syllables, and each syllable having one or more phonemes. The method also includes receiving, as input to a vocoder model, prosodic features that represent an intended prosody for the text utterance and a linguistic specification. The prosodic features include a duration, pitch contour, and energy contour for the text utterance, while the linguistic specification includes sentence-level linguistic features, word-level linguistic features for each word, syllable-level linguistic features for each syllable, and phoneme-level linguistic features for each phoneme. The method also includes predicting vocoder parameters based on the prosodic features and the linguistic specification.

Abstract: Systems and methods for remote debugging perform remote debugging of a receiving device, such as a set-top box or other connected media player, even when the receiving device is located behind a firewall. The receiving device has a persistent outbound connection with a message server. Since it is an outbound connection, it connects across firewall restrictions. A remote debug machine sends a message via the message server to the receiving device over a network. The message carries the command/operation to be executed by the receiving device. The receiving device, which receives the command, executes the command and sends the output of the command to a debug data upload server to which the remote debug machine has access.

Abstract: Systems and methods are provided for interpreting a correlation model that predicts a correlation between a pair of data corresponding to a pair of incident tickets using an interpreter model. The correlation model includes a Siamese Network including a plurality of neural networks. The interpreter model, trained by using training data, represents a student model (a glass-box model) while the correlation model, trained using the training data, represents a more complex teacher model (a black-box mode) of a teacher-student model. The present disclosure generates global feature importance scores based on the trained interpreter model, which indicates a degree of influence of a feature compared to other features in incident data in determining correlations, to generate additional training data emphasizing influential features and to retrain the correlation model.

Abstract: A method is performed at an electronic device with one or more processors, a non-transitory memory, a display, and an extremity tracker. The method includes obtaining extremity tracking data via the extremity tracker. The method includes displaying a computer-generated representation of a trackpad that is spatially associated with a physical surface. The physical surface is viewable within the display along with a content manipulation region that is separate from the computer-generated representation of the trackpad. The method includes identifying a first location within the computer-generated representation of the trackpad based on the extremity tracking data. The method includes mapping the first location to a corresponding location within the content manipulation region. The method includes displaying an indicator indicative of the mapping. The indicator may overlap the corresponding location within the content manipulation region.

Abstract: Embodiments are disclosed for adding node highlighting to vector graphics. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a selection of a plurality of anchor points of a vector graphic to be highlighted, generating a graph representing one or more path objects of the vector graphic, each node of the graph corresponding to an anchor point of the one or more path objects and each connection corresponding to a path segment connecting the anchor point to another anchor point, identifying a highlight trajectory including a subset of nodes from the graph, the highlight trajectory including at least a start node and an end node, generating a highlight path including at least one or more highlight nodes corresponding to a subset of nodes from the highlight trajectory, and updating the vector graphic to include the highlight path.

Abstract: A storage appliance or system may support backup and recovery for virtual machines that support various applications. The storage appliance or system may process a backup snapshot of the virtual machine to identify security vulnerabilities in the virtual machine. The storage appliance may generate an index of software packages installed on the virtual machine and software versions of the software packages. The index of software packages may be compared to a list of security vulnerabilities to identify the security vulnerability at the virtual machine. A notification may be triggered, and the notification may indicate a result of comparing the index of software packages and the software versions to the list of vulnerabilities. In some examples, a set of network configurations implemented by the virtual machines may be determined by processing the backup snapshot and used to identify security vulnerabilities.

Abstract: A device includes a master control and one or more circuit boards. The master control receives an executable file containing software associated with circuit boards, extracts a piece of software from the executable file, determines whether a version of the piece of software is more desirable than a version of software installed on an associated circuit board, and upon determination that the version of the piece of software is more desirable, install the piece of software onto the associated circuit board by transmitting the piece of software to the associated circuit board as a plurality of data packets, determining whether an acknowledgment of each data packet is received from the associated circuit board within a threshold time period, and upon determination that acknowledgment of at least one data packet is not received from the associated circuit board within the threshold time period, restarting the installation of the piece of software.

Abstract: A device is configured to detect a triggering event within a network that is associated with a communication error between a first network device and a second network device. The device is further configured to identify a first node in a computer network map corresponding with the first network device and to identify node properties for the first node. The device is further configured to identify the error correction instructions in the node properties for the first node that include an address for rerouting data traffic to a third network device. The device is further configured to apply the error correction instructions where applying the error correction instructions suspends data traffic to the second network device and reroutes data traffic to the third network device.

Abstract: In some implementations a method may involve presenting a graphical user interface in a first configuration on a display of an apparatus. The first configuration may correspond with a first display area. The method may involve enabling operation of a fingerprint sensor system in a first fingerprint sensor area corresponding with at least a portion of the first display area. The method may involve presenting the graphical user interface in a second configuration on the display and enabling fingerprint sensor system operation only in a second fingerprint sensor area corresponding with the second configuration.