Automatic extractions of situations includes creating a situation image includes accessing a conversation between a first user and a second user, and generating an abstract knowledge graph at one or more textual levels. The method also includes generating one or more manifests by pruning the abstract knowledge graph and segmenting the pruned abstract knowledge graph. The method further includes converting the one or more manifests into the situation image.

Methods, systems, and computer program products for zero-shot entity linking based on symbolic information are provided herein. A computer-implemented method includes obtaining a knowledge graph comprising a set of entities and a training dataset comprising text samples for at least a subset of the entities in the knowledge graph; training a machine learning model to map an entity mention substring of a given sample of text to one corresponding entity in the set of entities, wherein the machine learning model is trained using a multi-task machine learning framework using symbolic information extracted from the knowledge graph; and mapping an entity mention substring of a new sample of text to one of the entities in the set using the trained machine learning model.

Techniques for identifying missing evidence are provided. A plurality of documents, each comprising digitally encoded natural language text data, is received. The plurality of documents is processed to determine a plurality of pair-wise comparisons between a plurality of therapies, where each of the plurality of pair-wise comparisons indicate a relative efficacy of at least one therapy in the plurality of therapies, as compared to at least one other therapy in the plurality of therapies. A knowledge graph is generated based at least in part on aggregating the plurality of pair-wise comparisons, and the knowledge graph is analyzed to identify one or more knowledge gaps within the knowledge graph. Finally, at least an indication of the identified one or more knowledge gaps is output.

Embodiments of the present disclosure provide a method and apparatus for outputting information. A specific embodiment of the method includes: in response to receiving a query, detecting whether there is an entity slot in the query; in response to there being an entity slot in the query, adding the detected entity slot to a candidate slot; detecting, in the query, a relationship-determinative word of an entity; searching in a preset knowledge graph for a peripheral knowledge graph of the candidate slot; and inferring on the basis of the peripheral knowledge graph according to the relationship-determinative word, and outputting an entity word matching the relationship-determinative word.

Techniques for high-performance machine learning (ML) inference in heterogenous edge devices are described. A ML model trained using a variety of different frameworks is translated into a common format that is runnable by inferences engines of edge devices. The translated model is optimized in hardware-agnostic and/or hardware-specific ways to improve inference performance, and the optimized model is sent to the edge devices. The inference engine for any edge device can be accessed by a customer application using a same defined API, regardless of the hardware characteristics of the edge device or the original format of the ML model.

Uncertainty-ware federated learning methods and systems in a mobile edge computing network can include defining an average volume of a training parameter of each user equipment under an uncertainty of a mobile edge computing network based on a federated learning framework; determining an average model size factor and the minimum and maximum number of aggregators during each federated learning task request; determining the number of aggregators; constructing an auxiliary graph, and determining a location decision according to the auxiliary graph; determining a total cost during each federated learning task request according to the location decision; adjusting the number of aggregators according to the total cost with a resource capacity of the mobile edge computing network as a constraint to obtain the decision including aggregator placement, user equipment assignment and the optimal number of aggregators during each federated learning task request, and optimizing the federated learning framework.

Apparatus for generating a putative ontology from a data structure associated with a data store, the apparatus including an electronic processing device that generates a putative ontology by determining at least one concept table in the data structure, determining at least one validated attribute within the at least one concept table, determining at least one selected attribute value from the at least one validated attribute and generating at least one ontology class using the at least one attribute value.

Users have to assign labels to a ticket to route to right domain expert for resolving issue(s). In practice, labels are large and organized in form of a tree. Lack in clarity in problem description has resulted in inconsistent and incorrect labeling of data, making it hard for one to learn/interpret. Embodiments of the present disclosure provide systems and methods that identify relevant queries to obtain user response, for identification of right category and ticket logging there. This is achieved by implementing attention based sequence to sequence (seq2seq) hierarchical classification model to assign the hierarchical categories to tickets, followed by a slot filling model to enable identifying/deciding right set of queries, if the top-k model predictions are not consistent. Further, training data for slot filling model is automatically generated based on attention weight in the hierarchical classification model.

In one embodiment, a method includes receiving an initial input in a first modality from a first user from a client system associated with the first user, determining one or more intents corresponding to the initial input by an intent-understanding module, generating one or more candidate continuation-inputs based on the one or more intents, where the one or more candidate continuation-inputs are in one or more candidate modalities, respectively, and wherein the candidate modalities are different from the first modality, and sending instructions for presenting one or more suggested inputs corresponding to one or more of the candidate continuation-inputs to the client system.

A method includes receiving a current claim associated with care provided to a patient by a provider, the claim including a current diagnosis code and a first current procedural terminology (CPT) code that are based on the care that was provided; identifying, using an artificial intelligence (AI) engine, a second current CPT code based on the current diagnosis code and the first current CPT code; and generating a current confidence level value that the second current CPT code is missing from the current claim.