Abstract: Systems and methods for deep learning model development for data extraction using a feedback loop. A system generates an interactive graphical user interface (GUI) on one or more user devices for displaying a document with data extracted from the document by a data extraction model together with a user interaction tool allowing the user to correct the extracted data. The system receives, via the interactive GUI, correction information for the extracted data and monitoring performance characteristics of the extraction model in real-time based on the user correction information. The system automatically updates and trains the extraction model using the correction information responsive to detecting that the performance characteristics meet a predetermined performance reduction condition.

Abstract: A method for performing a plasma etch process is provided. The method initiates with receiving a substrate into a chamber. A high frequency (HF) RF signal is generated, said HF RF signal being pulsed in at least a three-state cycle including a first state, a second state, and a third state. The first state is configured at a first power level; the second state is configured at a second power level less than the first power level; and, the third state is configured at a third power level less than the second power level. The second power level of the HF RF signal being in the range of about 0 W to 3500 W. The HF RF signal is applied to an electrode of the chamber for performing the plasma etch process.

Abstract: Techniques are described for routing a customer communication to an agent having appropriate expertise to handle the current communication associated with a customer using one or more machine learning models. For example, a computing system includes a memory and one or more processors in communication with the memory. The one or more processors are configured to: receive a set of emotion factor values for communication data of the current communication; generate, using a composite emotion model running on the one or more processors, a composite emotional score for the current communication based on the set of emotion factor values for the current communication; determine a routing recommendation for the current communication that identifies an agent having appropriate expertise to handle the current communication based on at least the composite emotional score; and route the current communication in accordance with the routing recommendation to a computing device of the agent.

Abstract: A method may include detecting one or more selection boxes and one or more text lines in a primary document. The method may include determining respective vectors associated with the selection box and adjacent text lines to the selection box in a plurality of directions. The method may include determining a set of respective vectors associated with a unique selection box. The method may include determining a variance between respective vectors in the set of respective vectors and identifying a particular direction corresponding to a minimal variance between the respective vectors in the set of respective vectors as compared to a variance of other sets of respective vectors. The method may include generating a key-value pair based on the set of respective vectors characterized by the minimal variance. The method may include generating a document model, including the key-value pair, and extracting data according to the document model.

Abstract: A method may include receiving a primary document including one or more selection boxes, one or more text lines, and one or more annotations. The method may include determining, a class based on the annotations. The method may include identifying the one or more selection boxes and one or more text lines of the primary document. The method may include generating a graph representing the one or more selection boxes and the one or more text lines. The method may include mapping each of the one or more selection boxes to a respective text line of the one or more text lines of the graph based at least in part on one or more characteristics associated with the selection boxes. The method may include generating a key-value pair associated with each of the one or more text lines and generating a document model of the primary document.

Abstract: A method comprising: dividing a 3D space into a voxel grid comprising a plurality of voxels; associating a plurality of distance values with the plurality of voxels, each distance value based on a distance to a boundary of an object; selecting an approximate interpolation mode for stepping a ray through a first one or more voxels of the 3D space responsive to the first one or more voxels having distance values greater than a threshold; and detecting the ray reaching a second one or more voxels having distance values less than the first threshold; and responsively selecting a precise interpolation mode for stepping the ray through the second one or more voxels.

Abstract: A user preference hierarchy is determined from user response to images. Images may be tagged using machine learning models trained to determine values for images. Products are clustered according to product vectors. Images of products within a cluster are clustered according to composition and groups of images are selected from image clusters for soliciting feedback regarding user preference for products of a cluster. Feedback is used to train a user preference model to estimate affinity for a product vector. A user may provide feedback regarding a price point and products are weighted according to a distribution about the price point. The distribution may be asymmetrical according to direction of movement of the price point. Filters may be dynamically defined and presented to a user based on popularity and frequency of occurrence of attribute-value pairs of search results and based on feedback regarding the search results.

Abstract: A chip includes a merger cell including a first p-type length of diffusion (LOD) region extending in a first direction, a first n-well underneath the first p-type LOD region, a first supply rail configured to receive a first supply voltage, and a first n-tap coupling the first n-well to the first supply rail. The merger cell also includes a second p-type length of diffusion (LOD) region extending in the first direction, a second n-well underneath the second p-type LOD region, a second supply rail configured to receive a second supply voltage different from the first supply voltage, and a second n-tap coupling the second n-well to the second supply rail.

Abstract: Semantic analysis to resolve ambiguous user input data with respect to a request for data includes identifying tokens based on the text string, identifying a tables in a database, wherein a token indicates a column from a table and a token indicates a column from another table, identifying candidate join paths for joining tables, obtaining respective candidate results using the candidate join paths, outputting combined candidate results including values from the respective candidate results, obtaining second user input data indicating a selected value, identifying the request for data as unambiguous and identifying a selected join path based on the selected value, and, in response to identifying the request for data as unambiguous, outputting data responsive to the request for data using the selected join path.

Abstract: Systems, computer program products, and methods are described herein for authentication of device transfers in a distributed network. The present disclosure is configured to receive a transaction request, wherein the transaction request comprises a secondary user device, wherein the secondary user device is associated a user; create a pair of authentication codes, wherein the authentication codes are associated with a distributed network; transmit the pair of authentication codes to the secondary user device; authorize the secondary user device; activate a primary user device, wherein the primary user device is associated with the user, and wherein activating the primary user device comprises prompting the user on the primary user device to provide one or more transaction details; and complete the transaction request.

Abstract: A method comprising: dividing a 3D space into a voxel grid comprising a plurality of voxels; associating a plurality of distance values with the plurality of voxels, each distance value based on a distance to a boundary of an object; selecting an approximate interpolation mode for stepping a ray through a first one or more voxels of the 3D space responsive to the first one or more voxels having distance values greater than a threshold; and detecting the ray reaching a second one or more voxels having distance values less than the first threshold; and responsively selecting a precise interpolation mode for stepping the ray through the second one or more voxels.

Abstract: Techniques are described for generating a set of emotion factor values using one or more machine learning models for customer communications. For example, a computing system includes one or more processors in communication with a memory. The one or more processors are configured to receive communication data of a current communication associated with a customer, apply the communication data to an emotion-based indexer as input wherein the emotion-based indexer includes a set of machine-learning models for a set of emotion factors, generate as output from the emotion-based indexer a set of emotion factor values for the current communication wherein each emotion factor value indicates the measure of a particular emotion factor in the current communication, apply the set of emotion factor values to an emotion classification model, and classify the current communication into an emotion state based on the set of emotion factor values.

Abstract: A method performed by a User Equipment (UE) for handling a Non-Terrestrial Network (NTN) connection, includes: detecting at least one of: a presence of the UE in an NTN only coverage area, or a non-availability of a Terrestrial Network (TN) coverage at a location of the UE; determining an availability of an NTN; selecting the NTN for a registration of the UE; determining an absence of a voice-service support from the selected NTN, wherein the absence of the voice-service support indicates that the selected NTN does not support a voice service for the UE; performing at least one control action to avoid searching for the voice service during the registration of the UE on the NTN; and completing the registration of the UE on the NTN, based on the performed at least one control action.

Abstract: Systems, methods and computer software are disclosed for 4G and 5G core interworking. In one embodiment a HetNet gateway (HNG) is disclosed. The HNG includes a virtual 4G core; a virtual 5G core; an interface to a core network; an interface to a 4G Radio Access Network (RAN); and an interface to a 5G RAN. The HNG provides interworking 4G to 5G such that a 5G RAN works with a 4G core.

Abstract: The present disclosure is directed to a technique for reduction of latency in network traffic data transmissions. The method includes: parsing an online document to determine a messaging identifier used to communicate over an asynchronous network-based communication channel between a computing device and a content provider device; pinging, via the asynchronous network-based communication channel, the content provider device corresponding to the messaging identifier; receiving, from the content provider device, a response to the pinging; verifying, based on the response, whether the content provider device is operational to receive electronic messages over the asynchronous network-based communication channel; and authorizing, responsive to verification of the content provider device, a content generator component to insert the messaging identifier in one or more instances of an online content item.

Abstract: Techniques are described herein for generating block extender model. An example method includes a system accessing a base model trained for identifying a base class. The system can access an extender comprising block extenders, the extender class distinct from the base class. The system can connect the extender with the base model to generate an augmented model. The system can input training data to the augmented model, the training data is provided to the base model and the extender, the training data comprising data points associated with the extender class. The system can train the extender model to identify the extender class based at least in part on the training data and the signal received from the base machine learning model. The system can generate a trained extender based at least in part on the training, the extender trained to identify an object associated with the extender class.

Abstract: Systems and methods for message delivery prioritization that can include receiving, via an application programming interface, a messaging request of an entity to transmit one or more messages to a plurality of users, selecting one or more message transmission options based on message-associated delivery attributes, and causing the one or more messages to be transmitted to the plurality of users using the selected one or more message transmission options.

Abstract: A method includes, using a processor, identifying a septum and a Left Atrium Appendage (LAA) of a heart of a patient in an anatomical map of at least part of the heart. An entry surface over which a medical device is defined on the anatomical map, which is to be delivered via a sheath that penetrates the septum, is to engage with the LAA. A normal to the entry surface is calculated. A plurality of curves is calculated that each (i) have one end that is tangent to the normal, (ii) have a second end touching the septum, and (iii) comply with specified mechanical properties of the sheath. Multiple candidate locations on the septum are derived from the curves, for transseptal puncture with the sheath. The multiple candidate locations are presented to a user.

Abstract: Techniques for extracting information from unstructured documents that enable an ML model to be trained such that the model can accurately distinguish in-distribution (“in-D”) elements and out-of-distribution (“OO-D”) elements within an unstructured document. Novel training techniques are used that train an ML model using a combination of a regular training dataset and an enhanced augmented training dataset. The regular training dataset is used to train an ML model to identify in-D elements, i.e., to classify an element extracted from a document as belonging to one of the in-D classes contained in the regular training dataset. The augmented training dataset, which is generated based upon the regular training dataset may contain one or more augmented elements which are used to train the model to identify OO-D elements, i.e., to classify an augmented element extracted from a document as belonging to an OO-D class instead of to an in-D class.