Abstract: A method and system for multi-table question answering is provided herein. The method includes receiving a complex question from a user. The method may further include decomposing the complex question into one or more sub-questions using one or more of but not limited to coreference resolution, dependency parsing, chunking and prompt techniques. The method may further include generating code scripts for each sub-question using a Large Language Model (LLM). The method may further include executing the code scripts to retrieve relevant structured data from a plurality of tables. The method may further include generating an answer to the complex question based on the retrieved structured data.

Abstract: A method and system for multimodal response generation through a virtual agent is provided herein. The method comprises retrieving information related to an input received by the virtual agent. The virtual agent employs an Artificial Intelligence (AI) model. The method further comprises generating a response corresponding to the input based on the retrieved information. The method may further comprises generating a plurality of prompts based on user characteristics and the input. The method may further comprises modifying the response based on the plurality of prompts to generate a multimodal response.

Abstract: A method and system of predicting molecular properties is provided herein. The method includes representing a molecule as a graph and a string. The method further includes encoding the graph into a first feature representation and the string into a second feature representation, using a graph neural network and a transformer-based network, respectively. The method further includes concatenating the first feature representation obtained from the graph neural network and the second feature representation obtained from the transformer-based network to create a combined feature representation. The method further includes fusing the combined feature representation using a linear layer to obtain a synergistic combined feature representation for the molecule. The method further includes predicting one or more molecular properties for the molecule using the synergistic combined feature representation and a predictor network.

Abstract: The disclosure provides a system, a method, and a computer program product for displaying a a Knowledge Graph at a client device. The method comprises receiving a sequence of selection elements in the Knowledge Graph, by a user. The method may include displaying the sequence of selected elements in a last in, first out order on selecting a UI component by the user. Also, the method may enable saving a state of display on closing display of the Knowledge Graph. Further, on reopening the display of the Knowledge Graph the saved state is rendered. The method also provides box select and panning feature for visually manipulating the Knowledge Graph. Further, in order to optimally execute the above features, nodes and edges which are the elements of a Knowledge Graph are stored in array data structures.

Abstract: Disclosed is an AI-based method for medical diagnosis, comprising: obtaining medical data from data source(s); generating a Directed Acyclic Graph (DAG) (204) using medical data, wherein nodes of DAG represent at least set of symptoms and set of medical conditions, and wherein directed edges between nodes represent relations between nodes; generating graph embeddings for nodes of DAG using graph-embedding technique; receiving input indicative of person's health, wherein input comprises set of symptoms (202); extracting set of test graph embeddings corresponding to test set of symptoms from graph embeddings; and processing test graph embeddings using neural network (206) for obtaining multi-label classification (208) of test set of symptoms matched to test set of medical conditions as labels, wherein given label is probabilistically indicative of presence of medical condition.

Abstract: The disclosure provides a system, a method, and a computer program product for displaying a sentence in a Knowledge Graph at a client device. The method comprises displaying, at the client device, at least an entity in the Knowledge Graph as a node. The method may include displaying, at the client device, at least a relation in the Knowledge Graph as an edge. The method may further include, displaying, at the client device, a sentence on selecting the edge of the Knowledge Graph, wherein the sentence is a natural language expression associated with the relation. The method also allows for visually adjusting the display density of the Knowledge Graph.

Abstract: The present invention discloses a system comprising a server and a database storing data pertaining to a plurality of electronic documents, wherein the server is configured to: send a list including one or more electronic documents to a client device for presentation to a user, wherein the list enables the user to select one of the one or more electronic documents; upon selection of a given electronic document from the one or more electronic documents, retrieve data pertaining to the given electronic document from the database, wherein the retrieved data indicates entities and their inter-relationships; generate a document knowledge graph representing the entities and their inter-relationships as specific to the given document, wherein the document knowledge graph is user controllable; and send the document knowledge graph to the client device for presentation to the user, generate and provide an interface that includes the generated document knowledge graph, wherein the document knowledge graph enables the u

Abstract: The present invention discloses a system comprising a server and a database storing data pertaining to a plurality of electronic documents, wherein the server is configured to: send a list including one or more electronic documents to a client device for presentation to a user, wherein the list enables the user to select one of the one or more electronic documents; upon selection of a given electronic document from the one or more electronic documents, retrieve data pertaining to the given electronic document from the database, wherein the retrieved data indicates entities and their inter-relationships; generate a document knowledge graph representing the entities and their inter-relationships as specific to the given document, wherein the document knowledge graph is user controllable; and send the document knowledge graph to the client device for presentation to the user, generate and provide an interface that includes the generated document knowledge graph, wherein the document knowledge graph enables the u