Abstract: An automated system and corresponding method is configured to predict a call duration of a customer service interaction between a caller and a customer-service agent of a call center, based at least in part on information provided orally by the caller to the automated system. The automated system transcribes the orally provided information, preprocesses the transcribed data, adds feature enrichment data to supplement the transcribed data, and executes a machine-learning model to predict the caller's intent. If the predicted caller's intent does not have an adequate confidence score associated therewith, the system requests additional data from the caller, and supplements the original data with newly provided data, and again determines a predicted call intent. This process may iterate until the confidence score satisfies applicable confidence criteria prior to utilizing two additional machine-learning models to predict a call duration of the interaction between the caller and a customer-service agent.

Abstract: Various embodiments provide methods, apparatus, systems, computing entities, and/or the like, for identifying deviated behavior of an individual indicated by outlying activity counts and outlying activity timings classified by a prediction interval profile generated from historical behavior data. In an embodiment, an example method comprises accessing sensor data describing behavioral activities of an individual during historical time periods and generating a prediction interval profile for the behavioral activities comprising a predicted count interval within a prediction time period for at least some behavioral activities. The method further includes receiving sensor data for the prediction time period and extracting an observed activity count and an observed activity timing for each behavioral activity.

Abstract: Various embodiments of the present disclosure provide multi-stage data lineage tracking techniques for automatically generating holistic and accurate data catalog for complex data ecosystems. The techniques may include generating a critical attribute collection for a data-related task based on one or more natural language descriptions for the data-related task. The techniques include receiving a data lineage map that defines a plurality of hierarchical data layers for a data ecosystem associated with the data-related task. The techniques include generating a critical attribute map for the data-related task by identifying a data element for a critical attribute at each of the plurality of hierarchical data layers of the data lineage map. The techniques include identifying noncritical attributes for the data related task generating a task attribute map for the data-related task based on the noncritical attributes and the critical attribute map.

Abstract: To schedule a future interaction between a caller and a call-center, a management computing system associated with the call center is configured to determine an estimated call time for addressing the caller's issues, based at least in part on a predicted call intent as well as feature enrichment data received from one or more memory storage areas. Upon determining a predicted call duration for the call, the management computing entity accesses the caller's calendar, such as through an internet-based communication between the caller's user computing entity and the management computing entity, or via third-party access permissions provided by the caller. The management computing entity identifies one or more candidate timeslots based at least in part on the predicted call duration, and receives user input selecting a candidate timeslot for scheduling the callback.

Abstract: A clinical harvester system may provision, based at least in part on information associated with a piece of clinical data associated with a user, a plurality of harvesters that query a plurality of data sources to locate the piece of clinical data. The clinical harvester system may transmit data between two or more of the plurality of harvesters as the plurality of harvesters query the plurality of data sources to communicate information used for locating the piece of clinical data within the plurality of data sources. The clinical harvester system may retrieve, using the plurality of harvesters, the piece of clinical data from one of the plurality of data sources.

Abstract: Embodiments provide for predicted data use obligation matching using data differentiators. Example embodiments retrieve a cross-link relationship graph structure from a data repository, where the cross-link relationship graph structure includes a plurality of cross-link relationship graph nodes connected by a plurality of cross-link relationship graph edges. Each cross-link relationship graph node is associated with a unique logical data record set identifier of a plurality of logical data record set identifiers associated with a dataset identifier. For each unique logical data record set identifier, the cross-link relationship graph structure is traversed. Based at least in part on a separation measure associated with each cross-link relationship of one or more cross-link relationships associated with the unique logical data record set identifier, one or more data use obligation scores for the unique logical data record set identifier is generated.

Abstract: Various embodiments of the present disclosure provide automated data compliance techniques for complex access controlled datasets subject to a plurality of data access constraints. Some of the techniques may include generating, using one or more natural language models, entity-relationship data for an access controlled dataset and generating a knowledge graph based on the entity-relationship data. The knowledge graph includes a plurality of vertices connected by a plurality of edges that may be traversed to identify a data access condition indicative of a data access violation or a data coverage violation. Some of the techniques may include generating, using the knowledge graph, a natural language condition description based on the data access condition and providing a condition alert indicative of the natural language condition description.

Abstract: Various embodiments of the present invention provide methods, apparatus, systems, computing devices, computing entities, and/or the like for production line conformance monitoring. For example, certain embodiments of the present invention utilize systems, methods, and computer program products that perform production line conformance monitoring by utilizing categorical validation machine learning models that are generated using a plurality of training production line images associated with a related category subset of a plurality of validation categories for a target validation category.

Abstract: A data file comprising a plurality of rows, each of the rows includes at least a first column and a second column, the first column contains a first-level resource ID that identifies a first-level resource, the second column provides information regarding the first-level resource. For each respective unique first-level resource ID, the processing circuitry identifies a row set for the respective first-level resource ID, performs a sequential deduplication process on the row set, and enqueues remaining rows in a queue for a thread assigned to the respective first-level resource ID. For each row enqueued in the queue for the thread, the thread dequeues the row from the queue for the respective thread, requests creation of a second-level resource that stores a version of the data element contained in the second column of the dequeued row, and requests creation of relationship data for the second-level resource.

Abstract: Various embodiments of the present disclosure provide query processing techniques for generating optimized query results. The techniques include generating using a machine learning framework, one or more predictions for a natural language query. The one or more predictions may include an intent prediction and an event prediction. The technique may include generating an intent classification for the natural language query based on the intent prediction and the event prediction. The techniques may include in response to the intent classification corresponding to a target query intent: generating, a plurality of candidate data objects based on an identifier associated with the natural language query, identifying one or more relevant data objects from the plurality of candidate data objects based on a relevancy score for each of the plurality of candidate data object; and providing, via a user interface, a natural language query result.

Abstract: Systems and methods are disclosed for processing forms to automatically adjudicate religious exemptions. The method includes receiving an input from a user to data fields of forms associated with a religious exemption request, wherein the input is in a first data format and includes location information, religious information, employment information, or demographic information associated with the user. Exemption-relevant features are determined from the input. A data object including the exemption-relevant features is generated. The exemption-relevant features are transformed into corresponding embeddings in a second data format, wherein the embeddings represent semantic relations between the exemption-relevant features. The authenticity of the data object is determined based on the embeddings using a classification model that has been trained using a plurality of embeddings representative of a plurality of exemption-relevant features.

Abstract: There is a need for more effective and efficient predictive data analysis solutions and/or more effective and efficient solutions for generating an emotional sentiment score without the use of labelled data. In one example, embodiments comprise receiving an input text sequence, generating an intermediate emotional sentiment score object based at least in part on the input text sequence and by utilizing an emotional sentiment machine learning model, generating an overall emotional sentiment score based at least in part on the intermediate sentiment score object and by utilizing an emotional sentiment score transformation object, and performing one or more prediction-based actions based at least in part on the overall emotional sentiment score.

Abstract: Various embodiments of the present disclosure provide model-based domain-aware autocomplete techniques for generating autocomplete suggestions in a complex search domain. Example embodiments are configured to generate, using a domain-aware autocomplete model, a label for an autocomplete suggestion based on a set of keywords within an autocomplete suggestion training dataset associated with a target domain source. Example embodiments are also configured to generate, using a weak-labeling model, an updated label for the autocomplete suggestion by decorrelating the set of keywords from the label. Example embodiments are also configured to generate, using a sentence classification model, a category for the autocomplete suggestion based on the updated label. Example embodiments are also configured to, using the domain-aware autocomplete model, generate a suggestion-category pair (SCP) based on the autocomplete suggestion and the category for the autocomplete suggestion.

Abstract: Various embodiments provide methods, apparatus, systems, computing entities, and/or the like, generating predictions based at least in part on recognizing significant words in unstructured text. In an embodiment, a method is provided. The method comprises: generating a plurality of word-level tokens for an input unstructured textual data object; and for each word-level token: determining a significance type and a significance subtype for the word-level token by using a significance recognition machine learning model, and assigning a significance token label or an insignificance token label to the word-level token.

Abstract: Various embodiments of the present invention provide methods, apparatuses, systems, computing devices, computing entities, and/or the like for facilitating efficient and effective execution of database management operations. For example, various embodiments of the present invention describe techniques for performing one or more database update operations given a concurrent write request group for a database using P concurrent request processor computing nodes, a match result serialization queue, and a centralized match result serializer computing node.

Abstract: Various embodiments provide for summarization of an interaction, conversation, encounter, and/or the like in at least an abstractive manner. In one example embodiment, a method is provided. The method includes generating, using an encoder-decoder machine learning model, a party-agnostic representation data object for each utterance data object. The method further includes generating an attention graph data object to represent semantic and party-wise relationships between a plurality of utterance data objects. The method further includes modifying, using the attention graph data object, the party-agnostic representation data object for each utterance data object to form a party-wise representation data object for each utterance data object. The method further includes selecting a subset of party-wise representation data objects for each of a plurality of parties.

Abstract: Embodiments of the present disclosure provide methods, apparatus, systems, computing devices, and computing entities for predictive data protection using a data protection policy determination machine learning model.

Abstract: Various embodiments of the present disclosure provide federated query processing techniques for dynamically tailoring the use and parameters of intermediary local sources based on the identification of federated query. The techniques include receiving an execution plan for executing a federated query that include a plurality of executable tasks for generating a result set from a plurality of third-party data sources. The techniques include generating a result set hash for the result set based on the execution plan and determining a query uniqueness status for the federated query based on a comparison between the result set hash and a plurality of historical result set hashes. In response to determining that the federated query is a unique query, the techniques include generating a time interval that is tailored to the unique query.