Abstract: An improved search engine is disclosed. The search engine receives search queries from client devices and inputs these queries into a first neural network (an action understanding model) that includes an action embedding layer. The action embedding layer can be a word embedding layer constructed using action terms. The action understanding model outputs a filter match associated with a type of filter and, in some scenarios, an action-condition pair. The action-condition pair includes an action associated with the type of filter and a condition comprising an adaptive value associated with the action. Based on the filter and, if present, action-condition pair(s), the embodiments generate a structured query and issue the structured query to a data repository (e.g., database). The search engine then returns a search results page responsive to the search query that includes the results returned by the data repository in response to the structured query.

Abstract: One or more computing devices, systems, and/or methods for identifying anomalous behavior of users are provided. In an example, users of a telecommunication service provider may be segmented into a plurality of user segments based upon telecommunication service metrics associated with the users. A machine learning model may be trained using telecommunication service information associated with users of the first user segment to generate a trained machine learning model. Using the trained machine learning model, a forecast of telecommunication service usage associated with a first user segment of the plurality of user segments. A telecommunication service usage metric, associated with a user belonging to the first user segment, may be compared with a range indicated by the forecast. The user may be flagged as having anomalous behavior based upon a determination that one or more telecommunication usage metrics, associated with the user, are outside one or more ranges indicated by the forecast.

Abstract: An improved search engine is disclosed. The search engine receives search queries from client devices and inputs these queries into a first neural network (an action understanding model) that includes an action embedding layer. The action embedding layer can be a word embedding layer constructed using action terms. The action understanding model outputs a filter match associated with a type of filter and, in some scenarios, an action-condition pair. The action-condition pair includes an action associated with the type of filter and a condition comprising an adaptive value associated with the action. Based on the filter and, if present, action-condition pair(s), the embodiments generate a structured query and issue the structured query to a data repository (e.g., database). The search engine then returns a search results page responsive to the search query that includes the results returned by the data repository in response to the structured query.

Abstract: One or more computing devices, systems, and/or methods for identifying anomalous behavior of users are provided. In an example, users of a telecommunication service provider may be segmented into a plurality of user segments based upon telecommunication service metrics associated with the users. A machine learning model may be trained using telecommunication service information associated with users of the first user segment to generate a trained machine learning model. Using the trained machine learning model, a forecast of telecommunication service usage associated with a first user segment of the plurality of user segments. A telecommunication service usage metric, associated with a user belonging to the first user segment, may be compared with a range indicated by the forecast. The user may be flagged as having anomalous behavior based upon a determination that one or more telecommunication usage metrics, associated with the user, are outside one or more ranges indicated by the forecast.

Abstract: A framework uses artificial intelligence to provide suggestions for minimizing stagnant resources in contracts across multiple business relationships. A network device receives multiple smart contracts governing relationships between a telecommunications carrier and partner entities; extracts delivery timelines from the multiple smart contracts; generates an embedding layer based on historical vendor data, in-house procedural data; predicts one or more windows of stagnant resources in the delivery timelines; and generates a policy suggestion to optimize stagnant resources during the one or more windows.

Abstract: A transaction management platform may partition an amount associated with a group service plan into a plurality of portions. The transaction management platform may provide a graphical user interface to a primary user device of the plurality of user devices. The transaction management platform may receive, from the primary user device, a request for a transaction associated with a portion of the plurality of portions. The portion may be attributable to a secondary user device of the plurality of user devices. The transaction management platform may provide to the secondary user device of the plurality of user devices a unique link that has been generated based on one or more parameters and that enables the secondary user device to complete the transaction. Based on the secondary user device completing the transaction, the transaction management platform may process the transaction to provide an updated amount.

Abstract: One or more computing devices, systems, and/or methods for identifying anomalous behavior of users are provided. In an example, users of a telecommunication service provider may be segmented into a plurality of user segments based upon telecommunication service metrics associated with the users. A machine learning model may be trained using telecommunication service information associated with users of the first user segment to generate a trained machine learning model. Using the trained machine learning model, a forecast of telecommunication service usage associated with a first user segment of the plurality of user segments. A telecommunication service usage metric, associated with a user belonging to the first user segment, may be compared with a range indicated by the forecast. The user may be flagged as having anomalous behavior based upon a determination that one or more telecommunication usage metrics, associated with the user, are outside one or more ranges indicated by the forecast.

Abstract: Techniques for determining anomalous user behavior in connection with an online application are disclosed. In one embodiment, a method is disclosed comprising obtaining user behavior data in connection with a user of an application, generating feature data using the obtained user behavior data, obtaining one or more user behavior anomaly predictions from one or more anomaly prediction models trained to output a user behavior anomaly prediction in response to the feature data. Each user behavior anomaly prediction indicates a probability that the user behavior is anomalous. A user behavior anomaly determination is made using the user behavior anomaly prediction(s).

Abstract: Techniques for generating conversational responses for a conversational user interface are disclosed. In one embodiment, a method is disclosed comprising obtaining user input from a user via a conversational user interface, using the user input to obtain a user emotion and a user intent, obtaining candidate probabilities for a fragment of a response to the user input using the obtained user emotion, the obtained user intent and the user input, generating the response to the user input using the candidate probabilities obtained for the fragment to select a candidate for the fragment of the response, and communicating the response to the user via the conversational user interface.

Abstract: An improved search engine is disclosed. The search engine receives search queries from client devices and inputs these queries into a first neural network (an action understanding model) that includes an action embedding layer. The action embedding layer can be a word embedding layer constructed using action terms. The action understanding model outputs a filter match associated with a type of filter and, in some scenarios, an action-condition pair. The action-condition pair includes an action associated with the type of filter and a condition comprising an adaptive value associated with the action. Based on the filter and, if present, action-condition pair(s), the embodiments generate a structured query and issue the structured query to a data repository (e.g., database). The search engine then returns a search results page responsive to the search query that includes the results returned by the data repository in response to the structured query.

Abstract: A transaction management platform may partition an amount associated with a group service plan into a plurality of portions. The transaction management platform may provide a graphical user interface to a primary user device of the plurality of user devices. The transaction management platform may receive, from the primary user device, a request for a transaction associated with a portion of the plurality of portions. The portion may be attributable to a secondary user device of the plurality of user devices. The transaction management platform may provide to the secondary user device of the plurality of user devices a unique link that has been generated based on one or more parameters and that enables the secondary user device to complete the transaction. Based on the secondary user device completing the transaction, the transaction management platform may process the transaction to provide an updated amount.

Abstract: A device may receive alarm data identifying alarms associated with an occurrence of an event, and may identify, from the alarm data, a set of alarms that include false positives. The device may perform feature engineering on the set of alarms to extract features from a feature store and may train a model with the features to generate a trained model. The device may process the alarm data, with the trained model, to determine rules for reducing a quantity of future alarms that include the false positives, and may identify, from the rules for reducing the quantity of future alarms, a set of rules that satisfy a threshold for reducing the quantity of future alarms. The device may perform one or more actions based on the set of rules.