Abstract: In an embodiment, a method for secure messaging integration with message apps includes identifying a trigger event within a default messaging channel established between a message aggregator and a messaging application executing at a client device. In response to the trigger event, the method sends to the client device over the default messaging channel, access data usable to access a secure channel established between the message aggregator and the client device. The access data is presented within the messaging application and communications over the secure channel are not visible to the default messaging channel.

Abstract: Embodiments discussed herein are directed to systems and methods for processing audio feedback on a business, product or service offered and providing the feedback to an associated company in a way that enables the appropriate actors within the company's organizational hierarchy to analyze and take action with respect to the feedback. Customers or employees can interact with a virtual assistant platform or other voice recognition platform to access a feedback service that enables customers or employees to provide feedback to or have a conversation with any business about their product or service. The feedback service can be accessed at any time using a mobile phone or internet connected speaker device using a digital assistant platform.

Abstract: Embodiments discussed herein refer to systems and methods for chatbot interactions. When chatbot derived interactions are detected, the system can prevent those interactions from being further processed. This can be performed by an analysis system operative to engage in a dialog with customers. The system can manage a dialog with a first customer and evaluate the dialog to determine whether any interactions or responses are associated with a chatbot or a human. Interactions or responses determined be associated with a chatbot are dropped and not permitted to be further processed by the analysis system.

Abstract: A speech redaction engine includes a natural language processing (NLP)-based content redaction module receives an automatic speech recognition (ASR) decoding of a decoded portion of said digitized speech signal and utilizes NLP techniques to determine whether it contains sensitive information that should be redacted, and an ASR confidence-based redaction module that receives a confidence indicator and utilizes said confidence indicator to determine, independent of said NLP-based content redaction module, whether said decoded portion contains one or more word(s) that were recognized with a confidence level that is below a threshold. The speech redaction engine includes means for redacting said decoded portion if the NLP-based content redaction module determines that said portion should be redacted, and means for redacting the one or more word(s) if the ASR confidence-based redaction module determines that the one or more word(s) have the confidence level that is below the threshold.

Abstract: A plurality of histograms are maintained with respect to a dataset. The dataset includes a plurality of data segments. In response to a query that includes a plurality of conditions ordered in an initial sequence, a plurality of corresponding rejection rates is determined for the plurality of conditions based at least in part on the plurality of histograms. The plurality of conditions are re-ordered according to the plurality of corresponding rejection rates associated with the plurality of conditions to form a reordered sequence for the plurality of conditions. The query is executed according to the reordered sequence of the plurality of conditions.

Abstract: Embodiments of the present invention provide a system that can be used to classify a feedback image in a user review into a semantically meaningful class. During operation, the system analyzes the captions of feedback images in a set of user reviews and determines a set of training labels from the captions. The system then trains an image classifier with the set of training labels and the feedback images. Subsequently, the system generates a signature for a respective feedback image in a new set of user reviews using the image classifier. The signature indicates a likelihood of the image matching a respective label in the set of training labels. Based on the signature, the system can allocate the image to an image cluster.

Abstract: The invention relates to systems/methods that enable real-time monitoring/processing of contact center communications to provide timely, actionable analytic insights and real-time critical call alerts, while simultaneously providing best-in-class protection of sensitive customer information.

Abstract: Embodiments of the present invention provide a system that that can be used to determine whether a sentiment analysis model is portable between two data sets. During operation, the system analyzes the text of a respective review in a data set (e.g., a set of reviews) using the sentiment analysis model to determine a sentiment expressed in the review. The system then computes a confidence score, which indicates the accuracy of a respective sentiment. The system subsequently determines a confidence score distribution for various sentiments, as determined by the sentiment analysis model. The system determines the significance of changes between the confidence score distribution and a benchmark confidence score distribution, which is associated with a benchmark data set for which the sentiment analysis model yields a high accuracy. The system can then determine whether the sentiment analysis model is portable to the data set based on the significance of changes.

Abstract: A process for compressing an audio speech signal utilizes ASR processing to generate a corresponding text representation and, depending on confidence in the corresponding text representation, selectively applies more, less, or no compression to the audio signal. The result is a compressed audio signal, with corresponding text, that is compact and well suited for searching, analytics, or additional ASR processing.

Abstract: Conversing across fragmented messaging services based on a discussion topic is disclosed. In an embodiment, a method includes receiving, via a first messaging channel and at a message aggregator, a first message from a first messaging service. The first message is sent by a first user. The method includes sending the first message to a second user via a second messaging channel, then receiving, via the second messaging channel and at the message aggregator, a second message. The second message is sent by the second user. In response to a request from the first user to continue a conversation via a second messaging service, the method opens a third messaging channel to the second messaging service. The third messaging channel is associated with an account of the first user on the second messaging service. The method includes sending the second message via the third messaging channel to the second user.

Abstract: A compact, self-authenticating, and speaker-verifiable record of an audio communication involving one or more persons comprises a record, encoded on a non-transitory, computer-readable medium, that consists essentially of: a voiceprint for each person whose voice is encoded in the record; a plurality of transcription records, where each transcription record consists essentially of a computer-generated speech-to-text decoding of an utterance and voiceprint associating information that associates a speaker of the utterance with one of the voiceprints stored in the record; and self-authenticating information sufficient to determine whether any of the information encoded in the communication record has been altered.

Abstract: In an embodiment, a method for secure messaging integration with message apps includes identifying a trigger event within a default messaging channel established between a message aggregator and a messaging application executing at a client device. In response to the trigger event, the method sends to the client device over the default messaging channel, access data usable to access a secure channel established between the message aggregator and the client device. The access data is presented within the messaging application and communications over the secure channel are not visible to the default messaging channel.

Abstract: A method includes removing sensitive information from an audio recording. The method includes receiving a digitally encoded audio recording; transcoding, if necessary, the audio recording to a pre-defined audio format; identifying periods of voice in/activity in the audio recording; segregating the audio recording into a sequence of separated utterances or words; streaming the sequence of separated utterances or words to an ASR server; receiving, for each streamed utterance or word, an associated ASR decoding; receiving, for each ASR decoding, an associated confidence score indicative of a probability that the associated ASR decoding is correct; identifying for redaction; any ASR decoding that contains sensitive information, and any ASR decoding with a confidence score less than a redaction threshold; and preparing a redacted audio recording by eliminating or masking those word(s) and/or utterance(s) for which an associated ASR decoding was identified for redaction.

Abstract: A query for data stored in a database that includes a set of segments is received at a computer system. The set of segments are divided into a plurality of columns and at least one column of the plurality of columns includes one or more fields. The system analyzes the query to determine fields required to be retrieved from the database. The system determines whether a required field of the query is located in a main memory of the computer system. The system creates an input/output request for a column containing the required field for a plurality of segments of the set of segments prior to executing the query.

Abstract: Embodiments of the present invention provide a system that that can be used to determine whether a sentiment analysis model is portable between two data sets. During operation, the system analyzes the text of a respective review in a data set (e.g., a set of reviews) using the sentiment analysis model to determine a sentiment expressed in the review. The system then computes a confidence score, which indicates the accuracy of a respective sentiment. The system subsequently determines a confidence score distribution for various sentiments, as determined by the sentiment analysis model. The system determines the significance of changes between the confidence score distribution and a benchmark confidence score distribution, which is associated with a benchmark data set for which the sentiment analysis model yields a high accuracy. The system can then determine whether the sentiment analysis model is portable to the data set based on the significance of changes.

Abstract: The invention relates to systems/methods that enable real-time monitoring/processing of contact center communications to provide timely, actionable analytic insights and real-time critical call alerts, while simultaneously providing best-in-class protection of sensitive customer information.

Abstract: A plurality of histograms are maintained with respect to a dataset. The dataset includes a plurality of data segments. In response to a query that includes a plurality of conditions ordered in an initial sequence, a plurality of corresponding rejection rates is determined for the plurality of conditions based at least in part on the plurality of histograms. The plurality of conditions are re-ordered according to the plurality of corresponding rejection rates associated with the plurality of conditions to form a reordered sequence for the plurality of conditions. The query is executed according to the reordered sequence of the plurality of conditions.

Abstract: Embodiments discussed herein refer to systems and methods for identifying relevantly similar sentiment in text strings.

Abstract: Conversing across fragmented messaging services based on a discussion topic is disclosed. In an embodiment, a method includes receiving, via a first messaging channel and at a message aggregator, a first message from a first messaging service. The first message is sent by a first user. The method includes sending the first message to a second user via a second messaging channel, then receiving, via the second messaging channel and at the message aggregator, a second message. The second message is sent by the second user. In response to a request from the first user to continue a conversation via a second messaging service, the method opens a third messaging channel to the second messaging service. The third messaging channel is associated with an account of the first user on the second messaging service. The method includes sending the second message via the third messaging channel to the second user.

Abstract: Embodiments of the present invention provide a system that can be used to classify a feedback image in a user review into a semantically meaningful class. During operation, the system analyzes the captions of feedback images in a set of user reviews and determines a set of training labels from the captions. The system then trains an image classifier with the set of training labels and the feedback images. Subsequently, the system generates a signature for a respective feedback image in a new set of user reviews using the image classifier. The signature indicates a likelihood of the image matching a respective label in the set of training labels. Based on the signature, the system can allocate the image to an image cluster.