Abstract: Systems and methods are provided for generating and modifying a state-transition graph based on thresholds and constraints for simulated dependency graphs. For example, systems obtain a dependency graph that defines dependencies between data sources and transformation functions. A state-transition graph is generated based on simulating the dependency graph. A user is able to modify the state-transition graph in a simulation environment. Systems are also configured to generate outputs based on comparing a real-life execution of a plan and its corresponding state-transition graph.

Abstract: A computer implemented method includes obtaining deep learning model embedding for each instance present in a dataset, the embedding incorporating a measure of concept similarity. An identifier of a first instance of the dataset is received. A similarity distance is determined based on the respective embeddings of the first instance and a second instance. Similarity distances between embeddings, represented as points, imply a graph, where each instance's embedding is connected by an edge to a set of similar instances' embeddings. Sequences of connected points, referred to as walks, provide valuable information about the dataset and the deep learning model.

Abstract: The improved exercise of artificial intelligence by providing a systematic way for a computing system to interface with output from AI models. To do this, the computing system obtains results of an input data set being applied to an AI model. The results are then refined based upon characteristic(s) of the AI model and perhaps the input data set. Based upon characteristic(s) of the AI model and perhaps the input data set, interface element(s) are identified that can be used to interface with the refined results. The interface element(s) are then communicated to an interface element that interfaces with the refined results. The interface element(s) may include, for instance, operator(s) or term(s) that may be used to query against the refined results and/or an identification of visualization(s) that may be used to present to a user results of queries against the refined results.

Abstract: A computer implemented method determines differences between documents. The method includes parsing a first document and a second document into respective distinct instances of content. The distinct instances of content are classified into different categories. Category specific matching algorithms are applied to each of the respective instances of content to determine a similarity score for each of the respective instances of content. Semantic differences between the first document and the second document are analyzed as a function of the similarity scores. A characterization of the semantic differences is generated.

Abstract: The present disclosure relates to generating a complex entity index based on a combination of atomic and deep learned attributes associated with instances of a complex entity. For example, systems described herein generate a multi-dimensional representation of entity instances based on evaluation of digital content associated with the respective entity instances. Systems described herein further generate an index representation in which similarity of entity instances are illustrated and presented via an interactive presentation that enables a user to traverse instances of an entity to observe similarities and differences between instances of an entity that have similar embeddings to one another within a multi-dimensional index space.

Abstract: Examples of the present disclosure describe systems and methods for content-based multimedia retrieval with attention-enabled local focus. In aspects, a search query comprising multimedia content may be received by a search system. A first semantic embedding representation of the multimedia content may be generated. The first semantic embedding representation may be compared to a stored set of candidate semantic embedding representations of other multimedia content. Based on the comparison, one or more candidate representations that are visually similar to the first semantic embedding representation may be selected from the stored set of candidate semantic embedding representations. The candidate representations may be ranked, and top ‘N’ candidate representations (or corresponding multimedia items) may be retrieved and provided as search results for the search query.

Abstract: The methods and systems may improve the development of protocol documents used for clinical trials. The methods and systems may automatically estimate the likelihood of success or failure of executing a protocol document for a clinical study using a machine learning model that leverages several hundred thousand of past protocol documents and the outcomes of the clinical studies. The methods and systems may highlight sections of the protocol document that may increase a likelihood of an unsuccessful execution of the protocol document and may provide one or more recommendations to improve the highlighted sections of the protocol document.

Abstract: A computer implemented method includes rendering a document page as an image; detecting tables, columns, and other associated table objects within the image via one or more table recognition models that model objects in the image as overlapping bounding boxes; transforming the set of objects into a structured representation of the table; extracting data from the objects into the structured representation; and exporting the table into the desired output format.

Abstract: An Encoder-Decoder architecture uses two neural networks that work together to learn molecule embedding without any labeled data by transform the molecule graph to an embedding, and then mapping that embedding to a character-based representation of that molecule. An encoder operates as a molecule embedding model to produce a vector of length “n” that reperesents the molecule as a point in an n-dimentional cartesian space. The generated vector is used by a decoder to predict the molecule's character-based representation such as a SMILES, only based on the molecule structure. A loss function is applied to the decoded character-based representation compared to the actual character-based representation of that molecyle, to generate a gradient of the error determined by the loss function which is used to modify weights in the encoder-decoder model during training.

Abstract: The improved exercise of artificial intelligence. Raw output data is obtained by applying an input data set to an artificial intelligence (AI). Such raw output data is sometimes difficult to interpret. The principles defined herein provide a systematic way to refine the output for a wide variety of AI models. An AI model collection characterization structure is utilized for purpose of refining AI model output so as to be more useful. The characterization structure represents, for each of multiple and perhaps numerous AI models, a refinement of output data that resulted from application of an AI model to input data. Upon obtaining output data from the AI model, the appropriate refinement may then be applied. The refined data may then be semantically indexed to provide a semantic index. The characterization structure may also provide tailored information to allow for intuitive querying against the semantic index.

Abstract: The managing of sensed signals used to sense features of physical entities over time. A computer-navigable graph of sensed features is generated. For each sensed feature, a signal segment that was used to sense that feature is computer-associated with the sensed feature. Later, the graph of sensed features may be navigated to that features. The resulting signal segment(s) may then be access allowing for rendering of the signal evidence that resulted in the sensed feature. Accordingly, the principles described herein allow for sophisticated and organized navigation to sensed features of physical entities in the physical world, and allow for rapid rendering of the signals that evidence that sensed features.

Abstract: Procedural optimization is facilitated by receiving user input for creating or modifying a body of text comprising a procedure, detecting one or more procedural steps associated with the procedure using a procedural step detection module, automatically searching within a corpus of references for one or more related procedural steps using a related procedural step extraction module, automatically identifying one or more outcomes within the corpus of references associated with the one or more related procedural steps using an outcome extraction module, automatically determining whether the one or more outcomes comprise detrimental results using an outcome analysis module, and, in response to determining a set of detrimental outcomes from the one or more outcomes that comprise detrimental results, presenting a detriment indicator within the user interface in association with the one or more procedural steps.

Abstract: Claim verification is facilitated by identifying a selection of textual content within a user interface, accessing a claim detection module, inputting the textual content into the claim detection module to detect one or more claims within the selection of textual content, accessing an evidence extraction module, using the evidence extraction module to automatically search one or more reference repositories for one or more related references that have content that is related to the detected one or more claims, automatically determining whether the content in the one or more related references supports or refutes the one or more claims using a claim verification module, and, in response to determining a set of references of the one or more related references supports or refutes the one or more claims, presenting a support indicator or a refute indicator within the user interface in association with the one or more claims.

Abstract: An embedding model maps a graph representation of a molecule to an embedding space. The embedding model may include one or more graph neural network layers that use a message passing framework and one or more attention layers. The one or more attention layers may determine an edge weight for each message received by a receiving node from one or more sending nodes. The edge weight may be based on features of the receiving node and features of the one or more sending nodes. The one or more graph neural network layers may determine embedded features for the graph based on the messages and the edge weights. The embedding model may determine molecule features for the molecule based on the embedded features. The molecule features may map to an embedding space. The embedding model may be trained using multi-task training to generate a more generic embedding space.

Abstract: A relevance system ranks a set of medical studies based on a relevance of each medical study in the set of medical studies to a patient profile. The relevance system includes a relevance model. The relevance model determines a relevance of each medical study to the patient profile based on a semantic relationship score, a concept relationship score, and a term-occurrence score. The semantic relationship score is a measure of a similarity in semantic meaning of a medical study and a patient profile. The concept relationship score is a measure of the closeness of medical concepts in a medical study to medical concepts in a patient profile. The term-occurrence score is a measure of occurrences of terms in a medical study that also appear in a patient profile and the statistical significances of the terms.

Abstract: Routing of communications to group member(s) where group membership is identified by physical status. A computing system detects a communication that identifies targets of the communication at least in part by physical status. The system responds by identifying at least partial membership in a group that is identified by the physical status identified in the communication, and then dispatching the communication to at least one member of the members of that group. The identity of the members of the group may change dynamically as the physical status of particular physical entities changes over time. Accordingly, a user may communicate to individuals based on physical status, rather than identify any particular individual or status group. The communication may be directed to all members of the group. Alternatively, the communication may be initially directed towards a subset of the group, with the communication being conditionally later broadened.

Abstract: The improved exercise of artificial intelligence by systematically refining and semantically indexing the output from AI models, so that the semantic index is highly relevant. To do this, the computing system obtains results of an input data set being applied to an AI model. The computing system then determines a refinement to apply to the obtained results. This determination may be based on one or more characteristics of the AI model and/or input data set. The determination may also be based on hints associated with that AI model, and/or learned behavior regarding how that AI model is typically used. The obtained results are then refined using the determined refinement. It is then this more relevant refined results that are semantically indexed to generate the semantic index. Thus, the semantic index represents, the more useful output from an AI model, which is semantically exposed so as to provide meaning.

Abstract: A computer-implemented technique is described herein which uses a master BOT framework to facilitate a user's interaction with plural BOTs. The BOT framework includes a BOT registry that stores information regarding a plurality of BOTs that may be activated to handle different tasks (and associated intents). The BOT framework also includes various components that facilitate the transition from one BOT to another in the course of a multi-BOT transaction. According to one technical feature, the technique automatically invokes a new BOT without requiring the user to explicitly identify it. This provision simplifies the user's activation of a new BOT. According to another feature, the technique automatically forwards current state information to the new BOT. This provision expedites the user's transaction because it reduces the need for the user to repeat information that has already been supplied in one more prior turns of the transaction.

Abstract: Routing of communications to group member(s) where group membership is identified by physical status. A computing system detects a communication that identifies targets of the communication at least in part by physical status. The system responds by identifying at least partial membership in a group that is identified by the physical status identified in the communication, and then dispatching the communication to at least one member of the members of that group. The identity of the members of the group may change dynamically as the physical status of particular physical entities changes over time. Accordingly, a user may communicate to individuals based on physical status, rather than identify any particular individual or status group. The communication may be directed to all members of the group. Alternatively, the communication may be initially directed towards a subset of the group, with the communication being conditionally later broadened.

Abstract: Performing collaborative search engine searching. The method includes receiving user input at a user interface for performing a plurality searches on a first search engine. The method further includes receiving user input at the user interface applying one or more augmentation AI models to searches in the plurality of searches. The method further includes creating a shareable, executable package executable by one or more search engines based on the plurality of searches and the applied AI models that when executed by the search engines causes the search engines to apply the AI models to searches performed at the search engines.