Abstract: Methods and apparatuses are described for automatic intelligent query suggestion for information retrieval applications. A server a) determines candidate intents associated with user input text received from a remote device, including applying a trained intent classification model to the user input text to predict candidate intents. The server b) calculates a likelihood value for each of the candidate intents. The server c) compiles a list of suggested queries based upon the candidate intents and associated likelihood values. The server d) identifies a subset of the list of suggested queries for display on the remote device. Upon detecting an update to the user input text at the remote device, the server repeats steps a) to d) using the updated user input text, or upon detecting a selection of one of the suggested queries at the remote device, the server retrieves content responsive to the selected query.

Abstract: Systems and methods for measuring impact of online search queries on user actions. The method includes capturing clickstream data entered via a website, the clickstream data including text-based queries associated with web searches, and clustering the queries to generate query clusters. The method also includes assigning each query cluster to an intent such that each assigned intent estimates a desired action behind the queries in the corresponding query cluster. The method further includes mapping each intent assigned to a query cluster to at least one action motivated by the intent. The method also includes computing metrics using the mapping to quantitatively measure the impact of the queries on the mapped actions by tracking performance of the actions within a predefined time period after the queries.

Abstract: Methods and apparatuses are described for automated predictive virtual assistant intervention. A server computing device captures clickstream data corresponding to web browsing sessions of a user at a client computing device, and generates predicted needs of the user based upon the clickstream data. The server computing device identifies virtual assistant messages for the user based upon the predicted needs of the user, and displays the identified virtual assistant messages in a virtual assistant application on the client computing device.

Abstract: An example method for determining an influence score of a social media blog domain in accordance with aspects of the present disclosure includes receiving data regarding asocial media blog domain based on relevancy to a plurality of keywords, extracting values from the data for a set of categories of metrics for the social media blog domain, assigning a weight to each metric, and calculating an influence score for the social media blog domain based on the weight of the extracted values for each social media profile. The set of categories comprises social engagement, activity, social media page influence and social media blog domain influence.

Abstract: Systems and methods for generating proposed search queries based on sequence semantics. The method includes receiving clickstream data from a database. The method also includes generating for each user a digital timeline based on the clickstream data. The method further includes determining for each user event pairs based on the digital timeline. The method also includes generating a vector matrix including the event pairs for each user. The method further includes receiving an initial search query from a user. The method also includes determining an intended user activity based on the initial search query. The method further includes generating proposed search queries based on the vector matrix, the intended user activity, and the initial search query.

Abstract: Methods and apparatuses are described for automated predictive call routing using reinforcement learning. A server captures a bitstream of an incoming call from a first client device, the bitstream including metadata comprising attributes of the incoming call and attributes of a user of the device. The server determines an identity of the user based upon the metadata. The server generates a first context vector comprising a multidimensional array corresponding to the metadata. The server inserts the first vector into a high-dimensional vector space comprising historical context vectors, each historical vector (i) corresponding to metadata associated with a historical call and (ii) associated with an income value and a routing decision. The server determines historical vectors in proximity to the first vector. The server identifies one of the determined historical vectors with an optimal income value and routes the bitstream to a second device using the routing decision.

Abstract: Methods and apparatuses are described for automated routing of voice calls using time-based predictive clickstream data. A server captures clickstream data comprising uniform resource locators (URLs) and one or more timestamps of a web session. The server converts the clickstream data into tokens and generates a frequency matrix based upon the tokens. The server generates a feature vector based upon the frequency matrix. The server receives an incoming voice call from a remote device and identifies that the remote device is associated with a user of the client computing device. The server determines intent for the incoming voice call based upon the feature vector, and routes the incoming voice call to a destination device based upon the determined intent.

Abstract: An example method for determining an influence score of a brand in accordance with aspects of the present disclosure includes receiving data regarding a plurality of social media profiles associated with a plurality of social media platforms based on relevancy to a plurality of keywords, identifying a first set of data received from a first social media platform and a second set of data received from a second social media platform, extracting, values from the first set of data for a first set of categories of metrics for each social media profile associated with the first social media platform, extracting values from the second set of data for a second set of categories of metrics for each social media profile associated with the first social media platform, assigning a weight to each metric, determining an influence score for each social media profile based on calculating a weighted sum of the extracted values for each social media profile, and determining an influence score for the brand for each social med