A device may generate, from a subset of historical ontology data and a substance description of a substance, a knowledge base. The subset of historical ontology data may be associated with historical substances. The device may generate, based on the knowledge base, a substance knowledge graph embedding (KGE) that is representative of the substance; compare the substance KGE and a historical KGE associated with the knowledge base; determine, based on comparing the substance KGE and the historical KGE, a similarity score associated with the substance KGE and the historical KGE; determine, based on the similarity score, whether substance data associated with a related substance is similarly represented in the substance KGE and the historical KGE; and perform, based on whether the substance data is similarly represented in the substance KGE and the historical KGE, an action associated with the related substance relative to the substance description or the knowledge base.

A signal processing apparatus includes: a data input unit to which image data is input; an output unit configured to output an output value based on the data input to the data input unit; an expectation feedback calculator configured to calculate a difference between an expectation based on the input data and the output value; and a Bayesian estimator to which information on the difference and information based on the image data are input and which is configured to perform machine learning in order to approximate the output value to the expectation based on the input information and to search for an optimum configuration.

A signal processing apparatus includes: a data input unit to which image data is input; an output unit configured to output an output value based on the data input to the data input unit; an expectation feedback calculator configured to calculate a difference between an expectation based on the input data and the output value; and a Bayesian estimator to which information on the difference and information based on the image data are input and which is configured to perform machine learning in order to approximate the output value to the expectation based on the input information and to search for an optimum configuration.

Graphs are powerful structures made of nodes and edges, Information can be encoded in the nodes and edges themselves, as well as the connections between them. Graphs can be used to create manifolds which in turn can be used to efficiently train more robust AI systems. Systems and methods for graph-based AI training in accordance with embodiments of the invention are illustrated. In one embodiment, a graph interface system including a processor, and a memory configured to store a graph interface application, where the graph interface application directs the processor to obtain a set of training data, where the set of training data describes a plurality of scenarios, encode the set of training data into a first knowledge graph, generate a manifold based on the first knowledge graph, and train an AI model by traversing the manifold.

Graphs are powerful structures made of nodes and edges, Information can be encoded in the nodes and edges themselves, as well as the connections between them. Graphs can be used to create manifolds which in turn can be used to efficiently train more robust AI systems. Systems and methods for graph-based AI training in accordance with embodiments of the invention are illustrated. In one embodiment, a graph interface system including a processor, and a memory configured to store a graph interface application, where the graph interface application directs the processor to obtain a set of training data, where the set of training data describes a plurality of scenarios, encode the set of training data into a first knowledge graph, generate a manifold based on the first knowledge graph, and train an AI model by traversing the manifold.

A document extraction system executed by a processor, may process documents using manual and automated systems. The document extraction system may efficiently route tasks to the manual and automated systems based on a predicted probability that the results generated by the automated system meet some baseline level of accuracy. To increase document processing speed, documents having a high likelihood of accurate automated processing may be routed to an automated system. To ensure a baseline level of accuracy, documents having a smaller likelihood of accurate automated processing may be routed to a manual system.

A document extraction system executed by a processor, may process documents using manual and automated systems. The document extraction system may efficiently route tasks to the manual and automated systems based on a predicted probability that the results generated by the automated system meet some baseline level of accuracy. To increase document processing speed, documents having a high likelihood of accurate automated processing may be routed to an automated system. To ensure a baseline level of accuracy, documents having a smaller likelihood of accurate automated processing may be routed to a manual system.

An electronic device includes: a processor; and a memory storing instructions. By executing the instructions, the processor is configured to: receive a first image, recognize a plurality of objects in the first image to generate object information representing the plurality of objects, generate an object relationship graph including relationships between the plurality of objects, based on the first image and the object information, obtain image effect data including image effects to be respectively applied to the plurality of objects by inputting the object relationship graph to an image modification Graph Neural Network (GNN) model, and generate a modified image based on the first image, the object information, and the image effect data.

An electronic device includes: a processor; and a memory storing instructions. By executing the instructions, the processor is configured to: receive a first image, recognize a plurality of objects in the first image to generate object information representing the plurality of objects, generate an object relationship graph including relationships between the plurality of objects, based on the first image and the object information, obtain image effect data including image effects to be respectively applied to the plurality of objects by inputting the object relationship graph to an image modification Graph Neural Network (GNN) model, and generate a modified image based on the first image, the object information, and the image effect data.

An information processing apparatus acquires video data that includes target objects including a person and an object, and identifies a relationship between the target objects in the acquired video data, by using graph data that indicates a relationship between target objects and that is stored in a storage. The information processing apparatus identifies a behavior of the person in the video data by using a feature value of the person included in the acquired video data. The information processing apparatus predicts one of a future behavior and a future state of the person by inputting the identified behavior of the person and the identified relationship to a machine learning model.