Abstract: Systems and methods for generating a custom document template are disclosed. An example method may be performed by one or more processors of a system and include retrieving a user document including a user data entry in a user data field, identifying a set of system data fields within a plurality of system documents potentially relevant to the user document, determining, for each of the set of system data fields, a weighted value indicative of a likelihood that the system data field is relevant to the user data field, identifying a most relevant system data field of the set of system data fields, the most relevant system data field having a highest weighted value of the determined weighted values, and generating a custom document template including a dynamic data region for the user data entry, the dynamic data region mapped to the most relevant system data field.

Abstract: Systems and methods that may be used to provide multitenant key derivation and management using a unique protocol in which key derivation may be executed between the server that holds the root key and a client that holds the derivation data and obtains an encryption key. In one or more embodiments, the derivation data may be hashed. The disclosed protocol ensures that the server does not get access to or learn anything about the client's derived key, while the client does not get access to or learn anything about the server's root key.

Abstract: A method involves receiving search queries, having search terms, submitted to at least one computerized search engine. For each query, a corresponding pairwise relation in the search queries is calculated. The corresponding pairwise relation is a corresponding probability of a potential edge relationship between at least two terms. Thus, potential edges are formed. A general graph of the terms is constructed by selecting edges from the potential edges. The general graph is nodes representing the terms used in the search queries. The general graph also is edges representing semantic relationships among the nodes. A hierarchical graph is constructed from the general graph by altering at least one of the edges among the nodes in the general graph to form the hierarchical graph.

Abstract: In a collection technique, a user (such as a taxpayer) provides information (such as income-tax information) by submitting an image of a document, such as an income-tax summary or form. In particular, the user may provide a description of the document. In response, the user is prompted for the information associated with the field in the document. Then, the user provides the image of a region in the document that includes the field. Based on the image, the information is extracted, and the field in the form is populated using the extracted information. The prompting, receiving, extracting and populating operations may be repeated for one or more additional fields in the document.

Abstract: A visual-based classification model influenced by text features as a result of the outputs of a text-based classification model is disclosed. A system receives one or more documents to be classified based on one or more visual features and provides the one or more documents to a student classification model, which is a visual-based classification model. The system also classifies, by the student classification model, the one or more documents into one or more document types based on one or more visual features. The one or more visual features are generated by the student classification model that is trained based on important text identified by a teacher classification model for the one or more document types, with the teacher classification model being a text-based classification model. Generating training data and training the student classification model based on the training data are also described.

Abstract: Aspects of the present disclosure provide techniques for displaying reduced data sets based on pre-classification of a larger data set. Embodiments include receiving a plurality of activity records describing a plurality of activities associated with the user. Embodiments further include grouping the plurality of activities into one or more pre-classified data sets based on the plurality of activity records. Embodiments further include providing the user with a summary of a pre-classified data set of the one or more pre-classified data sets via a user interface. Embodiments further include providing the user, via the user interface, with a user interface element that allows the user to provide input related to the pre-classified data set based on the summary. Embodiments further include receiving input from the user via the user interface, the input relating to the pre-classified data set.

Abstract: A method includes receiving event strings from source code repositories, creating, for the source code repositories, digests of keywords, receiving log strings, and aggregating the log strings into a log group. The method further includes comparing the digests to the log group to generate scores, whereby the scores correlate the digests to the log group. The method further includes selecting a source code repository from the source code repositories according to the scores, and associating the log group to a service corresponding to the source code repository, where the source code repository corresponds to the digest with a highest score.

Abstract: A method including training predictor machine learning models (MLMs) using a first data set. The trained predictor MLMs are trained to predict classifications of data items in the first data set. The method also includes training confidence MLMs using second classifications, output by the trained predictor MLMs. The method also includes generating an aggregated ranked list of classes based on third classifications output by the trained predictor MLMs and second confidences output by the trained confidence MLMs. The method also includes training an ensemble confidence MLM using the aggregated ranked list of classes to generate a trained ensemble confidence MLM. The trained ensemble confidence MLM is trained to predict a corresponding selected classification for each corresponding data item in a training data set containing second data items similar to the first data items.

Abstract: A processor may receive an image and identify a plurality of characters in the image using a machine learning (ML) model. The processor may generate at least one word-level bounding box indicating one or more words including at least a subset of the plurality of characters and/or may generate at least one field-level bounding box indicating at least one field including at least a subset of the one or more words. The processor may overlay the at least one word-level bounding box and the at least one field-level bounding box on the image to form a masked image including a plurality of optically-recognized characters and one or more predicted fields for at least a subset of the plurality of optically-recognized characters.

Abstract: A method that includes obtaining, for a task, a help file including steps, and generating, from the help file, a knowledge graph for the task, the knowledge graph includes nodes connected by directed edges. Generating the knowledge graph includes, for a step of the set of steps obtaining, from the step, a first step attribute value defining an action type of an action specified by the step, generating a natural language instruction based on the action type and a second step attribute value, in the step, corresponding to a parameter of the action, and storing the natural language instruction in a node. The method further includes storing the knowledge graph.

Abstract: Multimodal multitask machine learning system for document intelligence tasks includes a feature extractor processing token values obtained from a document to obtain features, and a token extraction head classifying, using the features, the token values to obtain classified tokens. The classified tokens are aggregated into entities. A document classification model is executed on the features to classify the document and obtain a document label prediction. Further a confidence head model applying the document label prediction processes the entities to obtain a result.

Abstract: A method for performing a parity check of a table by a software application may include obtaining, from a data lake, data lake records stored in the table during a time interval, obtaining partitioning information used to partition the table in a database during the time interval, extracting, from the data lake records and for the partitioning information, partition identifiers stored in the table during the time interval, generating a partition-specific database query including a partition identifier, executing the partition-specific database query to obtain database records stored in the table in a partition of the database during the time interval, extracting a subset of the data lake records that include the partition identifier, and performing a parity comparison on the subset of the data lake records and the database records to generate a parity result.

Abstract: A method includes obtaining a help file including steps for a task and generating a knowledge graph including instructions corresponding to the steps. The method further includes extracting, from a user input of a user, an intent to complete the task. Responsive to extracting the intent to complete the task, obtaining the knowledge graph is obtained. Using the knowledge graph, an instruction of the knowledge graph is presented to perform an action in a workflow to complete the task.

Abstract: A browser executing on a computer terminal associated with a merchant receives a payment request for a purchase by a customer from the merchant. The computer terminal transmits, over a communications network to a mobile communication device associated with the customer, a push notification including the payment request and a set of instructions. The payment request indicates an identifier and amount of the purchase. The set of instructions causes the mobile communication device to activate a card reader using a mobile payment app, present the purchase amount to the customer on a touch-sensitive display of the mobile computing device, receive an acceptance of the purchase amount from the customer via the touch-sensitive display, and authorize the card reader to process payment for the purchase amount based on the acceptance. The computer terminal receives, over the communications network, a confirmation of the processed payment from the mobile computing device.

Abstract: Systems and methods are described for automatically documenting queries and dynamically populating interactive graphical user interfaces with query recommendations. A computing system receives an initial query from an interactive graphical user interface and asynchronously parses the query for strings matching predetermined phrases. In response to determining that the initial query recites strings matching the predetermined phrases, the system extracts metadata and identifies a table name in the initial query, and modifies a table data in key-value data structure corresponding to the table. Subsequent queries related to the initial query cause the system to asynchronously populate the graphical user interface with query recommendations related to the initial query.

Abstract: A method implements a table discovery service. The method includes receiving a query string, converting the query string to a query graph, and identifying a selected graph, of a set of graphs, that matches the query graph. The method further includes transmitting a notification identifying a previously generated table corresponding to the selected graph, receiving a notification response to accept the previously generated table, and transmitting data from the previously generated table in response to the query string.

Abstract: A method includes establishing a connection with a spreadsheet at a source location, receiving at least one selected field from an entry in the spreadsheet at the source location, and generating an assured reference record for the entry using at least one value in the at least one selected field. The assured reference record includes an assurance value and a reference to the entry at the source location. The method further includes storing, at a second location, the assured reference record in an assured reference file associated with the spreadsheet. The method further includes validating, after storing the assured reference record, the reference to the first entry in the spreadsheet at the source location using the first assurance value in the assured reference record.

Abstract: Systems and methods are described for training a large language model with query auto-completion training data and automatically generating query auto-completion training data in an interactive GUI. A computing system continuously trains and refines a large language model utilizing masking techniques to on complex software-related queries. The computing system is further configured to utilize the large language model to provide complex software-related query suggestions to users operating a graphical user interface real-time.

Abstract: A method including isolating a protocol language of a data set comprising a text structure representing data regarding a network communication procedure between a plurality of user devices, wherein the protocol language comprises a pattern for implementing the network communication procedure; generating a document from the data set, wherein the document includes a text structure, organizing, in light of the protocol language, the text structure into a natural language scheme; and detecting, using the natural language scheme, insights in the document.