Abstract: A system for automatically generating responses to user queries includes one or more processors, operable when executing instructions to: receive a query from a user, determine a first set of similarity scores between the query and a plurality of stored queries stored in a data store, and determine whether a first similarity score of the first set of similarity scores meets a first threshold. In accordance with a determination that the first similarity score meets the first threshold, the processors are further operable to obtain a set of case information for the current case; retrieve case information for at least one precedent case; determine a second set of similarity scores between the current case and the at least one precedent case; determine whether a second similarity score of the second set of similarity scores meets a second threshold; and generate a response to the query.

Abstract: Systems and methods are provided for using a structured data database and for exchanging electronic files containing unstructured or partially structured data. A system stores first structured data in a database, wherein the structured data represents a property. The system generates an electronic file, including by (a) storing unstructured data in the electronic file, wherein the unstructured data causes a representation of the property to be rendered on a face of a document represented by the file and (b) storing an identifier in the electronic file indicating a location in the database at which the first structured data is stored. The file is transmitted outside the system. Upon receipt of a copy of the file, the system reads the identifier from the copy of the received file and accesses the database location indicated by the identifier read from the received file.

Abstract: Provided herein are methods and systems for identifying a related data values in a plurality of datasets. The method can include extracting data from the plurality of datasets, identifying potential linking categories, and determining a validity of the potential linking categories. One or more linking categories can be selected from the potential linking categories based on the validity, and related data values can be identified between the plurality of datasets based on the selected linking categories. Also provided herein are methods and systems for classifying data values as reconciled or non-reconciled. The method can include identifying a plurality of related data values in a plurality of datasets. For each of the plurality of related data values, a similarity score and confidence score can be determined, and the plurality of related data values can be classified as reconciled or non-reconciled based on the similarity score and/or the confidence score.

Abstract: Described herein are techniques for optimizing real-time traffic flow of a multi-class vehicle network. In some embodiments, a trained machine learning model may be used to determine one or more segments of a street network where traffic congestion is predicted to occur at a predetermined future time. The vehicles may include a first type of vehicle and a second type of vehicle, each occupying different portions of a given segment. A subset of vehicles occupying the segments at the predetermined future time may be identified and, for each, a set of alternative routes may be determined. Quantum optimization data, including the pre-selected routes, the alternative routes, and an indication of whether the vehicle is of a first or second type, may be provided to a quantum computing system, which may return an updated route for at least some of the vehicles to minimize traffic congestion at the predetermined future time.

Abstract: A system for processing relational database data using a generative artificial intelligence (AI) language models is provided. The system receives relational database data and generates, based on the relational database data, schema data. The system also receives a user query input. The system generates and provides a first prompt to a generative AI language model, based on the user query input and the schema data. The system responsively receives, from the generative AI language model, an indication of a first subset of the database data identified as relevant to the query. The system generates and provides a second prompt to the generative AI language model, based on the user query input and the identified first subset. The system responsively receives, from the generative AI language model, an output comprising insight data generated based on the user query input and the identified first subset of the database data.

Abstract: A method for operating a hybrid energy network comprising a plurality of power sources is described. After receiving information indicating predicted operating conditions of the hybrid energy network, the values of one or more constraints associated with an objective function that defines a relationship between a plurality of performance parameters associated with the hybrid energy network may be updated. Using a quantum computing system, an optimal value of each of the plurality of performance parameters may be determined. Based on the optimal values of each of the plurality of performance parameters, an operating plan for the hybrid energy network may be determined. Adjustments may be made to at least one of power sources according to the generated operating plan.

Abstract: Described herein are systems, methods, and graphical user interfaces for creating conversation models that may be executed by natural language understanding systems and/or intelligent assistant systems, particularly in enterprise and corporate environments. A conversation modeling interface may allow a modeler to position a plurality of graphical conversation-element objects on a canvas region of the interface, to specify associations and relationships between the various represented conversation-elements to define a conversation flow, and to provide input data to define various parameters and characteristics of the conversation-elements of the conversation.

Abstract: The present disclosure relates generally to natural language understanding.

Abstract: An exemplary system for constructing data structures that can perform inferential reasoning to answer input queries may receive input data, extract and cluster entities in the input data into topic clusters, and for a first topic cluster construct a data structure comprising a plurality of nodes, wherein nodes of the data structure respectively represent a topic entity extracted from the input data and grouped into the first topic cluster, and wherein a first node of the data structure is associated with a second node of the data structure based on the first node and the second node respectively representing a first topic entity and a second topic entity associated in the input data with a common one of the one or more identified linguistic modalities. An exemplary system comprising the data structure may receive an input query and generate a response to the input query using the data structure.

Abstract: Systems and methods for automated document processing for use in AI-augmented auditing platforms are provided. A system for determining the composition of document bundles extracts substantive content information and metadata information from a document bundle and generates, based on the extracted information regarding a composition of the document bundle. A system for validating signatures in documents extracts data representing a spatial location for respective signatures and generates a confidence level for respective signatures, and determines, based on location and confidence level, whether signature criteria are met. A system for extracting information from documents applies a set of data conversion processing steps to a plurality received documents to generate structured data, and then applies a set of knowledge-based modeling processing steps to the structured data to generating output data extracted from the plurality of electronic documents.

Abstract: A method for providing a hybrid AI and human electronic communication interface includes receiving a first electronic transmission comprising a user query from a user device. The method further includes automatically generating, by processing the user query by a set of AI models, an automatic response to the user query. The method further includes electronically transmitting the automatic response to the user device. The method further includes receiving, from the user device, a second electronic transmission comprising a user input in response to the automatic response. The method further includes determining, based at least in part on processing the user input, that a set of criteria is met; and in accordance with the determination that the set of criteria are met, automatically instantiating an electronic communication connection between the user device and a second user device.

Abstract: Systems and methods for implementing an automation platform that is configured to analyze computing activities from a plurality of users so as to identify potential automation processes is provided. In one or more examples, a plurality of data collection agents are deployed across a plurality of computing devices and can be configured to collect and record activities performed on the computing device by one or more users of the computing devices. In one or more examples, each agent deployed on a computing device can be configured to transmit the collected data to a central server that can store the collected data in memory. The central server can be configured to collect the data from each agent and can be configured to apply one or more data science algorithms that can be configured to cluster various activities collected by the agents into groups for potential automation.

Abstract: Techniques for determining levels of interactions amongst entities in a group are provided. A plurality of mobile electronic devices detect signal data indicating when pairs of devices are proximate to one another. A receiver receives the detected signal data, and a data structure representing a contact network is generated based on the received detected signal data. Based on the contact network, a first metric is generated comprising a quantification of an average number of other entities in the contact network with which an entity in the contact network will have interactions in a predetermined amount of time. Based on the contact network, a second metric is generated comprising a quotient comprising of a size of a component of the contact network divided by an overall network size of the contact network. Based on the first and second metric, a level of interaction amongst entities in the group is determined.

Abstract: A system for automatically generating responses to user queries includes one or more processors, operable when executing instructions to: receive a query from a user, determine a first set of similarity scores between the query and a plurality of stored queries stored in a data store, and determine whether a first similarity score of the first set of similarity scores meets a first threshold. In accordance with a determination that the first similarity score meets the first threshold, the processors are further operable to obtain a set of case information for the current case; retrieve case information for at least one precedent case; determine a second set of similarity scores between the current case and the at least one precedent case; determine whether a second similarity score of the second set of similarity scores meets a second threshold; and generate a response to the query.

Abstract: System and methods for generating synthetic data according to a plurality of options are provided. According to a first option, synthetic data is generated based on an indication of one or more target distributions. According to a second option, a one or more target distributions are determined based on a sample data set, and synthetic data is generated based on the determined target distribution(s). According to a third option, a temporary synthetic data set is generated based on an indication of one or more target distributions, matches between the temporary synthetic data set and a sample data set are then identified, and a synthetic data set is then generated based on the identified matches. A system may automatically determine which option to leverage based on whether a user provides a sample data set, one or more target distributions, or both.

Abstract: Provided is a method for generating a personalized content suggestion in response to a query from a user. The method may be performed by a system comprising one or more processors. The method may include receiving the query from the user, generating one or more user parameters associated with the user, determining a predicted content topic of the query, and generating the content suggestion based on the predicted content topic and the one or more user parameters.

Abstract: Systems and methods for generating secure ephemeral cloud-based computing resources for data operations is provided. In one or more examples, a computing hub can receive a data set as well as one or more business process instructions from an external entity. In response to receiving the data set and business process instructions, the computing hub can create one or more containers within a persistent data storage computing resource and store the data set in the one or more containers. The computing hub can generate one or more cloud-based computing resources on one or more cloud-based computing resource platforms based on the received business processes. The computing hub can be configured to arbitrate access to the stored data set from the generated cloud-based computing resources and can be also configured to track lineage information of the data set as it is process by the one or more cloud-based computing resources.

Abstract: A system for parsing journal entries is configured to receive input data comprising a plurality of journal entries from one or more data sources and consecutively parse each respective journal entry. The journal entries can be parsed according to an algorithm that selects subsets of either credit or debit records from the journal entry, identifies matching subsets of records that foot to zero when combined with the selected records, and removes subsets containing records in the matching subsets from respective credit and debit data structures.

Abstract: Hardware and/or software systems, devices, networks, and methods for managing for access authentication, and verification to devices, networks, and systems based on a wireless signal identity developed for wireless-enabled devices based on wireless signal information associated with wireless signals previously detected by the wireless-enabled devices. The system may be used to authenticate access requests, transactions, etc. based on comparison between wireless signal information associated with wireless signals presently detected by the WED and its wireless signal identity via a management platform and/or the WED itself.

Abstract: An entity trust index relating to an entity may indicate a trustworthiness level of the entity. To generate an entity trust index, entity information may be received from one or more information sources. Using the entity information and one or more machine learning models, a performance index, an innovation index, and a sustainability index for the entity may be generated. The entity trust index may be generated based on the performance index, the innovation index, and the sustainability index. One or more actions for the entity that will modify the entity trust index may then be determined.