Abstract: A method for multi-modal deep learning is provided. The method comprises receiving input data from a database, wherein the input data comprises different data types. Responsive to receiving the input data, a number of corresponding neural extractors are identified to which to route the input data according to data type. Each neural extractor is specialized in extracting latent representations from a specific data type. The neural extractors, via a number of machine learning models, extract latent representations from the input data. The latent representations are then directed to a number of corresponding neural predictors, wherein each input data type is directed to a modality-specific neural predictor. The neural predictors then generate a number of output predictions for each input data type.

Abstract: A system and method for dynamic script generation for automated filing services is provided. In embodiments, a method includes: initiating a clickstream recording of an electronic document filing interface of a remote platform based on a triggering event; generating a clickstream recording of the electronic document filing interface, wherein the clickstream recording comprising a recording of a navigation of the electronic document filing interface through multiple steps of a document filing process, wherein the clickstream recording is in the form of scripts associated with each of the multiple steps of the document filing process; and generating automated filing instructions for the electronic document filing interface using the clickstream recording, the automated filing instructions enabling computer automated submission of one or more documents to the remote platform via the electronic document filing interface.

Abstract: Machine learning based processing of network operations using sequence alignment is described to meet performance criteria. A system can identify, from a plurality of function sequences, a sequence to perform an action and identify, for the action, a constraint on an order of functions within the sequence. The system can identify a machine learning (ML) model trained on performance data related to execution of actions using sequences of functions and according to a plurality of constraints for the plurality of actions. The system can determine, using the ML model, a likelihood that the sequence of functions performs the action within a performance tolerance and according to the constraint. The system can provide, responsive to the likelihood satisfying a threshold, an instruction to the transaction processing system to cause the transaction processing system to perform the action using the sequence of functions.

Abstract: A computer-implemented method, system, and computer program product for configuring a pay statement. An input area is presented for a user to enter settings defining how the pay statement is to be configured. The settings are received from the user. A preview of the pay statement is displayed in a preview area based on the settings. The preview provides a visual representation of how the pay statement will appear for the settings. The user may modify the settings until the preview appears as desired by the user.

Abstract: Vector-based hybrid search for chatbots is provided. A system receives, via a chatbot, a user query. The system generates, using an artificial intelligence model, a vector representation based on a combination of the user query, historical queries, and corresponding responses and identify a cached response corresponding to the user query in a semantic cache using the vector representation. The system executes, based on the cached response, a hybrid search operation including retrieval of first and second results having a first and second accuracy value by execution of a first and second search process on a first and second data source. The system selects one of the first or the second results based on modeling the first and the second accuracy value and displays, responsive to the user query, an output corresponding to the selected results.

Abstract: Systems, methods, and computer-readable storage media for building knowledge graphs which map the aspects of entities, then transforming the graphs into vectors for a similarity comparison. The resulting vectors can be used to identify skills and competencies of individuals, which the system uses to compare those individuals to others. The system can then quantify who would make for a good replacement for a given individual and make an associated recommendation.

Abstract: A method receives an electronic image and uses the image as an input to a neural network. Based on a determination that the image represents a document, the method uses the image as an input to another neural network to identify a portion of the document containing an identifier. The method extracts the identifier by performing character recognition on the identified portion and determines whether the identifier is valid by using a validation API to determine whether the identifier is associated with a valid account at an institution. Based on a determination that the identifier is associated with a valid account, the method authorizes a transaction associated with the identifier. Based on a determination that the identifier is not associated with a valid account, the method denies the transaction. The first neural network classifies the electronic image into one of multiple valid document types and an invalid document type.

Abstract: The technical solutions described herein relate to a method, system, and non-transitory computer-readable medium for forecasting (e.g., predicting) and reporting trends in crime. A method includes: filtering, by one or more processors coupled with memory, employment data and act data for a plurality of locations; identifying, by the one or more processors using a machine-learning model trained on a historic employment data and historic act data, a relationship between the employment data and the crime data; predicting, by the one or more processors based on the relationship identified by the machine-learning model, trends in acts for the plurality of locations; and generating, based on the predicted trends, a request for a preventive measure in a first location of the plurality of locations.

Abstract: A method of latent intent clustering is provided. The method comprises encoding identified features in a number of electronic user reports in a database. A binary matrix is created, wherein each row of the binary matric represents a different report and each column represents a different available feature. A 1 is placed in each cell of the matrix that matches a feature present in a user report. Cosine similarities are calculated for the user reports, and a similarity matrix is created, wherein each row and column of the binary matrix represents a different report, and wherein the cosine similarities of the reports are placed in corresponding cells of the matrix. The reports are clustered according to the cosine similarities. Features common to reports in each cluster are identified, and an intent of each report cluster is labeled according to the common features.

Abstract: A method, computer system, and computer program manage revisions in a document. The document is displayed in a graphical user interface. The document comprises a structured data object composed from a set of tiles, wherein each tile corresponds to one or more data nodes. The tiles are composable according to a domain-specific language of an integrated development environment. One or more revisions to the structured data object are received in sequence. The revisions to each data node of the set of tiles composing the structured data object are independently managed, enabling each revision to be independently reverted to a prior state irrespective of the sequence and revisions to other data nodes of the set of tiles and without reverting the other data nodes of the structured data object to their prior state.