Abstract: Disclosed herein are system, method, and computer program product embodiments for extracting an image object, such as a vehicle, from background imagery for computer browsing. The method includes generating a first segmentation mask of an image object, wherein the first segmentation mask comprises at least an array of first pixels of the image object within the digital imagery and second pixels located outside a perimeter boundary of the first segmentation mask (strays); extracting a plurality of contours from the digital imagery; generating a contour hierarchy of the plurality of contours, wherein the hierarchy is based on a length of each of the contours; discarding, based on the contour hierarchy, all contours from the plurality of contours except a longest contour; filling an interior of the longest contour to generate a second segmentation mask; and extracting the image object from the digital imagery using the second segmentation mask.

Abstract: Disclosed herein are system, method, and computer program product embodiments for generating realistic shadows for an image object, such as a vehicle, for computer browsing. The method includes generating a segmentation of an image object; generating a contour from the segmentation mask, wherein the contour comprises an array of the pixels along a boundary of the segmentation mask; calculating a plurality of regions of the contour, wherein each of the plurality of regions comprise a set of continuous points; identifying within the plurality of the regions of the contour, a plurality of key points that correspond to ground contact points of the image object; applying, based on the plurality of key points, a perspective warping to a first shadow template to generate the shadow for the image object, and rendering, on a selected background, the image segmentation as an overlay on the shadow.

Abstract: In some implementations, a device may obtain a data set that indicates scores for first terms based on association scores between the first terms and second terms. The association scores may be based on occurrences of the first terms in electronic documents that provide transcripts relating to telecommunication interactions, and occurrences of the second terms in electronic records that provide summaries relating to the telecommunication interactions. The device may process an electronic document, that provides a transcript relating to a new telecommunication interaction involving an agent device and a user device, to extract candidate key phrases from the transcript. The device may determine a relevance score for each candidate key phrase based on the score(s), of the data set, associated with the first term(s) in the candidate key phrase. The device may generate tag(s) for the new telecommunication interaction based candidate key phrase(s) associated with highest relevance score(s).

Abstract: In some implementations, a device may obtain a data set that indicates scores for first terms based on association scores between the first terms and second terms. The association scores may be based on occurrences of the first terms in electronic documents that provide transcripts relating to telecommunication interactions, and occurrences of the second terms in electronic records that provide summaries relating to the telecommunication interactions. The device may process an electronic document, that provides a transcript relating to a new telecommunication interaction involving an agent device and a user device, to extract candidate key phrases from the transcript. The device may determine a relevance score for each candidate key phrase based on the score(s), of the data set, associated with the first term(s) in the candidate key phrase. The device may generate tag(s) for the new telecommunication interaction based candidate key phrase(s) associated with highest relevance score(s).

Abstract: In some implementations, a device may obtain a data set that indicates scores for first terms based on association scores between the first terms and second terms. The association scores may be based on occurrences of the first terms in electronic documents that provide transcripts relating to telecommunication interactions, and occurrences of the second terms in electronic records that provide summaries relating to the telecommunication interactions. The device may process an electronic document, that provides a transcript relating to a new telecommunication interaction involving an agent device and a user device, to extract candidate key phrases from the transcript. The device may determine a relevance score for each candidate key phrase based on the score(s), of the data set, associated with the first term(s) in the candidate key phrase. The device may generate tag(s) for the new telecommunication interaction based candidate key phrase(s) associated with highest relevance score(s).

Abstract: The exemplary embodiments may provide a search tool that can locate customer issues in call transcripts and agent notes and can provide an accurate count of how often such issues appear in the call transcripts and agent notes. The exemplary embodiments may improve the speed with which the search of documents is performed. The exemplary embodiments rely upon a document matrix that is computed once for a given corpus of documents and a given vocabulary of the documents. The document matrix may be used across multiple queries. The exemplary embodiments also account for similar terms in processing a query. The exemplary embodiments may use a word coverage factor to improve the relevance of the search results returned by the search tool. The word coverage factor acts as a multiple factor that computes the fraction a query terms that are present in a document.

Abstract: Learning frameworks for processing text transcripts may include receiving, by an application, a query comprising a topic. A topic model may determine a plurality of subtopics based on the topic. The application may receive, from a database based on the topic and plurality of subtopics, a plurality of text transcripts. A sentiment model may compute, for each text transcript, a respective sentiment score based on a text of the respective text transcript. The application may determine, for each text transcript, a duration of a communication session associated with the respective text transcript. The application may compute, for each text transcript, a total score based on the sentiment score and the duration of the respective text transcript. The application may return, as responsive to the query, a subset of the plurality of text transcripts having a total score that exceeds a threshold.

Abstract: Routing peer-to-peer communications via telecommunications networks based on bifurcated user-specific sentiment analysis may be facilitated. In some embodiments, a system may generate a sentiment value related to each utterance of a set of utterances associated with a user by providing each utterance of the set of utterances to a sentiment machine learning model. The system may bin each utterance into a set of bins based on the sentiment values. The system may determine a sentiment probability of each bin of the set of bins by randomly sampling a subset of utterances corresponding to a respective bin of the set of bins. The system may determine an overall sentiment probability for a transcript based on the determined sentiment probability of each bin. In response to receiving a communication request, the system may route the communication request to an agent based on the overall sentiment probability satisfying a threshold sentiment probability.

Abstract: Learning frameworks for processing text transcripts may include receiving, by an application, a query comprising a topic. A topic model may determine a plurality of subtopics based on the topic. The application may receive, from a database based on the topic and plurality of subtopics, a plurality of text transcripts. A sentiment model may compute, for each text transcript, a respective sentiment score based on a text of the respective text transcript. The application may determine, for each text transcript, a duration of a communication session associated with the respective text transcript. The application may compute, for each text transcript, a total score based on the sentiment score and the duration of the respective text transcript. The application may return, as responsive to the query, a subset of the plurality of text transcripts having a total score that exceeds a threshold.

Abstract: Systems, methods, and computer program products for search platforms for unstructured interaction summaries. An application executing on a processor may receive a query comprising a term. The application may generate, based on an embedding vector and the term, an expanded query comprising a plurality of additional terms. The application may generate, based on a term frequency inverse document frequency model, a vector for the expanded query and generate an entity vector for the query. The application may generate a combined vector for the query based on the entity vector and the vector for the expanded query. The application may compute, based on the combined vector for the query and a feature matrix of a corpus, a respective cosine similarity score for a plurality of results in the corpus. The application may return one or more of the plurality of results as responsive to the query based on the similarity scores.

Abstract: The exemplary embodiments may provide a search tool that can locate customer issues in call transcripts and agent notes and can provide an accurate count of how often such issues appear in the call transcripts and agent notes. The exemplary embodiments may improve the speed with which the search of documents is performed. The exemplary embodiments rely upon a document matrix that is computed once for a given corpus of documents and a given vocabulary of the documents. The document matrix may be used across multiple queries. The exemplary embodiments also account for similar terms in processing a query. The exemplary embodiments may use a word coverage factor to improve the relevance of the search results returned by the search tool. The word coverage factor acts as a multiple factor that computes the fraction a query terms that are present in a document.

Abstract: Systems, methods, and computer program products for search platforms for unstructured interaction summaries. An application executing on a processor may receive a query comprising a term. The application may generate, based on an embedding vector and the term, an expanded query comprising a plurality of additional terms. The application may generate, based on a term frequency inverse document frequency model, a vector for the expanded query and generate an entity vector for the query. The application may generate a combined vector for the query based on the entity vector and the vector for the expanded query. The application may compute, based on the combined vector for the query and a feature matrix of a corpus, a respective cosine similarity score for a plurality of results in the corpus. The application may return one or more of the plurality of results as responsive to the query based on the similarity scores.

Abstract: Learning frameworks for processing text transcripts may include receiving, by an application, a query comprising a topic. A topic model may determine a plurality of subtopics based on the topic. The application may receive, from a database based on the topic and plurality of subtopics, a plurality of text transcripts. A sentiment model may compute, for each text transcript, a respective sentiment score based on a text of the respective text transcript. The application may determine, for each text transcript, a duration of a communication session associated with the respective text transcript. The application may compute, for each text transcript, a total score based on the sentiment score and the duration of the respective text transcript. The application may return, as responsive to the query, a subset of the plurality of text transcripts having a total score that exceeds a threshold.

Abstract: Systems, methods, and computer program products for search platforms for unstructured interaction summaries. An application executing on a processor may receive a query comprising a term. The application may generate, based on an embedding vector and the term, an expanded query comprising a plurality of additional terms. The application may generate, based on a term frequency inverse document frequency model, a vector for the expanded query and generate an entity vector for the query. The application may generate a combined vector for the query based on the entity vector and the vector for the expanded query. The application may compute, based on the combined vector for the query and a feature matrix of a corpus, a respective cosine similarity score for a plurality of results in the corpus. The application may return one or more of the plurality of results as responsive to the query based on the similarity scores.

Abstract: Systems, methods, and computer program products for search platforms for unstructured interaction summaries. An application executing on a processor may receive a query comprising a term. The application may generate, based on an embedding vector and the term, an expanded query comprising a plurality of additional terms. The application may generate, based on a term frequency inverse document frequency model, a vector for the expanded query and generate an entity vector for the query. The application may generate a combined vector for the query based on the entity vector and the vector for the expanded query. The application may compute, based on the combined vector for the query and a feature matrix of a corpus, a respective cosine similarity score for a plurality of results in the corpus. The application may return one or more of the plurality of results as responsive to the query based on the similarity scores.