Abstract: A data narration generating system generates snippets that include representations of data in one of a plurality of formats for inclusion into a data narration. The narration generating system receives selected data to be included into the data narration and provides the selected data to a plurality of ML models. The plurality of ML models are trained in generating snippets in one of the plurality of formats which can include textual format and a tabular format. Snippets in graphical formats can also be generated by rule-based processes. A plurality of snippets are thus generated in one or more of the plurality of formats which can then be presented to a user for selection and inclusion into the data narration. Alternately, a subset of the plurality of snippets can also be selected automatically based on a quality and quantity of data and a voting mechanism. The data narration thus generated is further configured to present different views based on privileges associated with user profiles.

Abstract: A device may receive, from a user device, a request to access a virtual reality (VR) learning environment that includes an identifier associated with a program that supports the VR learning environment. The device may identify a set of objects to use within the VR learning environment by searching a data structure using the identifier associated with the program that supports the VR learning environment. The device may provide the VR learning environment to the user device. The device may receive, from the user device, information associated with interactions within the VR learning environment. The device may identify one or more additional objects to use within the VR learning environment by using one or more natural language processing techniques to analyze the information associated with the interactions within the VR learning environment. The device may provide the one or more additional objects to the user device.

Abstract: A device receives documents from various sources, and processes the documents, with an optical character recognition engine, to generate digitized documents. The device processes the digitized documents, with a first machine learning model, to detect languages utilized in the digitized documents, and processes the digitized documents, in other languages that are different than a common language and with a second machine learning model, to translate the digitized documents, in the other languages, into the common language and to generate translated digitized documents. The device processes the translated digitized documents and untranslated digitized documents, with a classification model, to generate classified documents, and processes the classified documents, with a third machine learning model, to generate extracted information from the classified documents.

Abstract: A data narration generating system generates snippets that include representations of data in one of a plurality of formats for inclusion into a data narration. The narration generating system receives selected data to be included into the data narration and provides the selected data to a plurality of ML models. The plurality of ML models are trained in generating snippets in one of the plurality of formats which can include textual format and a tabular format. Snippets in graphical formats can also be generated by rule-based processes. A plurality of snippets are thus generated in one or more of the plurality of formats which can then be presented to a user for selection and inclusion into the data narration. Alternately, a subset of the plurality of snippets can also be selected automatically based on a quality and quantity of data and a voting mechanism. The data narration thus generated is further configured to present different views based on privileges associated with user profiles.

Abstract: An Artificial Intelligence (AI) based virtual automated assistance system provides services pertaining to component processes of a task that is to be automatically executed. The virtual automated assistance system includes a pipeline studio that enables generating the services. Historical data pertaining to a service is accessed for training and validating various ML models. The ML models are scored and a selected ML model is registered as a service on the virtual automated assistance system. The services thus registered are represented as process blocks within the pipeline studio wherein the process blocks pertaining to the component processes of the task are arranged in order to form a pipeline. The pipeline thus constructed enables automatic execution of the task by receiving and processing a request pertaining to the task via the services that form the pipeline.

Abstract: An Artificial Intelligence (AI)-based data transformation system receives an input package and enables automatic execution of one or more processes in a robotic process automation system (RPA). The input package includes a plurality of documents and metadata required for the execution of the automated processes. The plurality of documents are categorized into a domain. Entities with their corresponding name-value pairs and entity relationships are extracted from the plurality of documents. An ontology is selected based on the domain. The entities are mapped to output fields identified from the selected ontology. The mappings thus generated are transmitted to the RPA system which employs the mappings to automatically execute the one or more processes.

Abstract: A method may include receiving, from multiple, different sources, documents. The documents may be received in multiple, different file formats. The method may include performing operations on the documents to prepare the documents for processing, to obtain data included in the documents, or to determine information describing the documents. The method may include storing or providing, for storage, status information corresponding to the documents. The status information for a document may identify results of performing the operations with regard to the document. The method may include receiving an instruction that identifies an action to perform with regard to the document. The method may include performing the action. The method may include updating the status information to generate updated status information based on a result of performing the action. The method may include providing the updated status information.

Abstract: A device extracts data files from different data sources, and processes the data files to generate data from the data files. The device trains a first artificial intelligence model and a second artificial intelligence model based on historical data parameters, wherein the historical data parameters are associated with historical data previously processed by the device. The device utilizes the trained first artificial intelligence model and the data to generate data parameters for the data, and utilizes the trained second artificial intelligence model, the data, and the data parameters to generate a data structure configuration. The device generates a data structure for the data based on the data parameters and the data structure configuration, stores the data in the data structure, and provides a user interface for accessing the data structure.

Abstract: A device receives documents from various sources, and processes the documents, with an optical character recognition engine, to generate digitized documents. The device processes the digitized documents, with a first machine learning model, to detect languages utilized in the digitized documents, and processes the digitized documents, in other languages that are different than a common language and with a second machine learning model, to translate the digitized documents, in the other languages, into the common language and to generate translated digitized documents. The device processes the translated digitized documents and untranslated digitized documents, with a classification model, to generate classified documents, and processes the classified documents, with a third machine learning model, to generate extracted information from the classified documents.

Abstract: An Artificial Intelligence (AI) based virtual automated assistance system provides services pertaining to component processes of a task that is to be automatically executed. The virtual automated assistance system includes a pipeline studio that enables generating the services. Historical data pertaining to a service is accessed for training and validating various ML models. The ML models are scored and a selected ML model is registered as a service on the virtual automated assistance system. The services thus registered are represented as process blocks within the pipeline studio wherein the process blocks pertaining to the component processes of the task are arranged in order to form a pipeline. The pipeline thus constructed enables automatic execution of the task by receiving and processing a request pertaining to the task via the services that form the pipeline.

Abstract: A device may provide, to user devices, a set of objects that are to be used by the user devices as part of a collaborative virtual environment. The collaborative virtual environment may support a virtual workshop. The set of objects may include objects capable of being used to solve a problem that is presented to users within the virtual workshop. The device may receive data describing a set of solutions. The device may curate the data describing the set of solutions using one or more natural language processing techniques. The device may rank the set of solutions that has been curated using a ranking technique or a machine learning technique. The device may provide data identifying a highest ranked solution or data identifying the set of solutions for display within the virtual workshop or to additional user devices that are accessible outside of the virtual workshop.

Abstract: Electronically received data is validated based on a digital data image that is scanned from a paper document. Known paper document source entities, paper document types and associated paper document configuration information are stored in a database. The paper documents are converted to digital data images and optically processed to identify respective source entity and document type information represented within the digital data images. Appropriate document configuration information is retrieved based on association with the detected type of document. Validation target data is extracted from the digital data images based on the configuration information and processed. The electronically received data is validated based on the extracted and processed validation target data.

Abstract: A device may determine one or more trends by using one or more machine learning techniques to process historical transactional information included in a set of historical transactional documents. The device may receive a set of transactional documents associated with transactions between a client organization and a vendor organization. The device may generate, based on the one or more trends, a first set of exceptions indicating that one or more transactional documents are problematic transactional documents. The device may generate, using a similarity analysis technique, a second set of exceptions indicating that one or more additional transactional documents are duplicate transactional documents. The device may generate a set of claims based on one or more exceptions. The device may perform, based on the set of claims, one or more actions associated with correction or prevention of transaction processing errors relating to the set of transactional documents.

Abstract: A device extracts data files from different data sources, and processes the data files to generate data from the data files. The device trains a first artificial intelligence model and a second artificial intelligence model based on historical data parameters, wherein the historical data parameters are associated with historical data previously processed by the device. The device utilizes the trained first artificial intelligence model and the data to generate data parameters for the data, and utilizes the trained second artificial intelligence model, the data, and the data parameters to generate a data structure configuration. The device generates a data structure for the data based on the data parameters and the data structure configuration, stores the data in the data structure, and provides a user interface for accessing the data structure.

Abstract: Data extraction and automatic validation from digitized documents in non-editable formats is disclosed. Paper documents are digitized or converted into formats suitable for storage on computers or other digital devices. The digitized documents are classified into one of a plurality of document types and based on the document type, document processing rules are selected for analyzing the digitized documents to enable data extraction and automatic validation. The positions and values of the data fields in the digitized documents are obtained using machine learning techniques. The data field values are automatically validated and assigned confidence scores. Data fields with low confidence scores are flagged for manual review.

Abstract: A system for reconciling transactions includes an interface, a processor and non-transitory computer readable media. The interface receives information related to a plurality of organizations. Each of the plurality of organizations includes an enterprise resource planning (ERP) system for maintaining account information associated with the organization, and a document management system (DMS) for maintaining documents for the organization. The non-transitory computer readable media is in communication with the processor. The non-transitory computer readable media that stores instruction code that causes the processor to determine, based on the information, a group of organizations of the plurality of organizations that are structurally related to one another.

Abstract: A device may receive, from a user device, a request to access a virtual reality (VR) learning environment that includes an identifier associated with a program that supports the VR learning environment. The device may identify a set of objects to use within the VR learning environment by searching a data structure using the identifier associated with the program that supports the VR learning environment. The device may provide the VR learning environment to the user device. The device may receive, from the user device, information associated with interactions within the VR learning environment. The device may identify one or more additional objects to use within the VR learning environment by using one or more natural language processing techniques to analyze the information associated with the interactions within the VR learning environment. The device may provide the one or more additional objects to the user device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are described that enable identifying an insurance information associated with a property, retrieving one or more compliance rules related to the insurance information, automatically determining, based on the one or more compliance rules, whether the insurance information has a compliant status or a non-compliant status, in response to determining that the insurance information has the non-compliant status, processing the insurance information, based on one or more exception rules, to generate an exception waiver including a plurality of waiver parameters, applying the plurality of waiver parameters to a waiver model to determine a waiver confidence score, and based on the waiver confidence score selectively generate an insurance certificate for the property.

Abstract: Data extraction and automatic validation from digitized documents in non-editable formats is disclosed. Paper documents are digitized or converted into formats suitable for storage on computers or other digital devices. The digitized documents are classified into one of a plurality of document types and based on the document type, document processing rules are selected for analyzing the digitized documents to enable data extraction and automatic validation. The positions and values of the data fields in the digitized documents are obtained using machine learning techniques. The data field values are automatically validated and assigned confidence scores. Data fields with low confidence scores are flagged for manual review.

Abstract: Electronically received data is validated based on a digital data image that is scanned from a paper document. Known paper document source entities, paper document types and associated paper document configuration information are stored in a database. The paper documents are converted to digital data images and optically processed to identify respective source entity and document type information represented within the digital data images. Appropriate document configuration information is retrieved based on association with the detected type of document. Validation target data is extracted from the digital data images based on the configuration information and processed. The electronically received data is validated based on the extracted and processed validation target data.