Abstract: Systems and methods for generating training data for a supervised topic modeling system from outputs of a topic discovery model are described herein. In an embodiment, a system receives a plurality of digitally stored call transcripts and, using a topic model, generates an output which identifies a plurality of topics represented in the plurality of digitally stored call transcripts. Using the output of the topic model, the system generates an input dataset for a supervised learning model by identify a first subset of the plurality of digitally stored call transcripts that include the particular topic, storing a positive value for the first subset, identifying a second subset that do not include the particular topic, and storing a negative value for the second subset. The input training dataset is then used to train a supervised learning model.

Abstract: Systems and methods for improving machine learning systems used to model topics on a plurality of calls are described herein. In an embodiment, a server computer receives plurality of digitally stored call transcripts that have been prepared from digitally recorded voice calls. The server computer uses a topic model of an artificial intelligence machine learning system, the topic model modeling words of a call as a function of one or more word distributions for each topic of a plurality of topics, to generate an output of the topic model which identifies the plurality of topics represented in the plurality of call transcripts. The server computer computes, for a particular topic of the plurality of topics a first value representing a vocabulary of the particular topic and a second value representing a consistency of the particular topic in two more call transcripts of the plurality of call transcripts which include the particular topic.

Abstract: There are disclosed systems and methods for facilitating communications between individuals and enterprises and in particular, to methods and systems for tracking and attributing customer and/or customer prospect online and offline communications in association with a marketing campaign.

Abstract: In one embodiment, the disclosed technology involves: digitally generating and storing a machine learning statistical topic model in computer memory, the topic model being programmed to model call transcript data representing words spoken on a call as a function of one or more topics of a set of topics that includes pre-seeded topics and non-pre-seeded topics; programmatically pre-seeding the topic model with a set of keyword groups; programmatically training the topic model using unlabeled training data; conjoining a classifier to the topic model to create a classifier model; programmatically training the classifier model using labeled training data; receiving target call transcript data; programmatically determining at least one of one or more topics of the target call or one or more classifications of the target call; and digitally storing the target call transcript data with additional data indicating the determined topics and/or classifications of the target call.

Abstract: There are disclosed devices, system and methods for determining a performance score for a trained binary signal classifier (classifier) by determining test output predictions for test input data entries that are input into the classifier. The test outputs are then compared to known outputs of each of the input data entries to determine whether each test output is a true negative (TN), true positive (TP), false negative (FN) or false positive (FP). A number of correct test outputs (R) is defined as a number of the true negative outputs (TN) plus a number of the true positive outputs (TP). A number of incorrect test outputs (W) is defined as a number of the false negative outputs (FN) plus a number of the false positive outputs (FP). The performance score is then calculated using a mathematical expression that decreases as W increases, decreases as TN decreases and decreases as TP decreases.

Abstract: Systems and methods for generating training data for a supervised topic modeling system from outputs of a topic discovery model are described herein. In an embodiment, a system receives a plurality of digitally stored call transcripts and, using a topic model, generates an output which identifies a plurality of topics represented in the plurality of digitally stored call transcripts. Using the output of the topic model, the system generates an input dataset for a supervised learning model by identify a first subset of the plurality of digitally stored call transcripts that include the particular topic, storing a positive value for the first subset, identifying a second subset that do not include the particular topic, and storing a negative value for the second subset. The input training dataset is then used to train a supervised learning model.

Abstract: Systems and methods for improving call topic models are described herein. In an embodiment a server computer receives call transcript data comprising an electronic digital representation of a verbal transcription of a call between a first person of a first person type and a second person of a second person type. The server computer splits the call transcript data into first person type data comprising words spoken by the first person in the call and second person type data comprising words spoken by the second person type in the call.

Abstract: There are disclosed systems and methods for facilitating communications between individuals and enterprises and in particular, to methods and systems for tracking and attributing customer and/or customer prospect online and offline communications in association with a marketing campaign.

Abstract: There are disclosed devices, system and methods for a machine learning binary classifier automatically tolerating training data that is incorrect by determining a correct and an incorrect likelihood ratio that each training data entry has a correctly and an incorrectly labeled output. The correct and an incorrect likelihood ratio are combined with a correct and an incorrect priori odds ratio that the set of training data entries have correctly and incorrect labeled output labels. These two combinations are a correct probability and an incorrect probability that each entry of the set of entries has a correctly and an incorrect labeled output. A logistic regression model if fit to a combination of the correct probability and the incorrect probability for each training data entry to complete the training.

Abstract: There are disclosed systems and methods for facilitating communications between individuals and enterprises and in particular, to methods and systems for tracking and attributing customer and/or customer prospect online and offline communications in association with a marketing campaign.

Abstract: There are disclosed devices, system and methods for desired signal spotting in noisy, flawed environments by identifying a signal to be spotted, identifying a target confidence level, and then passing a pool of cabined arrays through a comparator to detect the identified signal, wherein the cabined arrays are derived from respective distinct environments. The arrays may include plural converted samples, each converted sample include a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form. Detecting may include measuring a confidence of the presence of the identified signal in each of plural converted samples using correlation of the identified signal to bodies of known matching samples. If the confidence for a given converted sample satisfies the target confidence level, the given sample is flagged.

Abstract: There are disclosed devices, system and methods for desired signal spotting in noisy, flawed environments by identifying a signal to be spotted, identifying a target confidence level, and then passing a pool of cabined arrays through a comparator to detect the identified signal, wherein the cabined arrays are derived from respective distinct environments. The arrays may include plural converted samples, each converted sample include a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form. Detecting may include measuring a confidence of the presence of the identified signal in each of plural converted samples using correlation of the identified signal to bodies of known matching samples. If the confidence for a given converted sample satisfies the target confidence level, the given sample is flagged.

Abstract: There are disclosed devices, system and methods for desired signal spotting in noisy, flawed environments by identifying a signal to be spotted, identifying a target confidence level, and then passing a pool of cabined arrays through a comparator to detect the identified signal, wherein the cabined arrays are derived from respective distinct environments. The arrays may include plural converted samples, each converted sample include a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form. Detecting may include measuring a confidence of the presence of the identified signal in each of plural converted samples using correlation of the identified signal to bodies of known matching samples. If the confidence for a given converted sample satisfies the target confidence level, the given sample is flagged.

Abstract: Methods and systems for reducing the impact of fraudulent or spam calls are disclosed. One or more calls to a first phone address are received, the first phone address not currently associated with a communication for a customer prospect. The calling party phone addresses associated with the calls received prior to the association of the first phone address to the first communication are stored. Then the first phone address is associated to the first communication. A first call to the first phone address is received. Prior to answering the first call and at least partly in response to a determination that a calling party phone address of the first call matches one of the previously stored calling party phone address, the first call is identified as a spam or otherwise undesirable call candidate and may be rejected.

Abstract: Methods and systems for reducing the impact of fraudulent or spam calls are disclosed. One or more calls to a first phone address are received, the first phone address not currently associated with a communication for a customer prospect. The calling party phone addresses associated with the calls received prior to the association of the first phone address to the first communication are stored. Then the first phone address is associated to the first communication. A first call to the first phone address is received. Prior to answering the first call and at least partly in response to a determination that a calling party phone address of the first call matches one of the previously stored calling party phone address, the first call is identified as a spam or otherwise undesirable call candidate and may be rejected.

Abstract: An online and offline communication processing and tracking using data processing and data/voice networks is described. A phone address from a phone address number pool is automatically assigned to a first entity. A call quality rating is determined and recorded. A call from a caller directed to the phone address is received at a call bridging system coupled to at least one network, wherein the call is associated with call signaling information. Based at least in part on the call quality associated with the caller call, the caller call is assigned to a first location in a call queue. An outbound call is generated from the call bridging system and the inbound and the outbound calls are bridged. One or more parameters of the bridged call are compared to the call quality rating. An indication is recorded regarding the successful bridging of the calls in association with an entity identifier.

Abstract: An online and offline communication processing and tracking using data processing and data/voice networks is described. A phone address from a phone address number pool is automatically assigned to a first entity. A call quality rating is determined and recorded. A call from a caller directed to the phone address is received at a call bridging system coupled to at least one network, wherein the call is associated with call signaling information. Based at least in part on the call quality associated with the caller call, the caller call is assigned to a first location in a call queue. An outbound call is generated from the call bridging system and the inbound and the outbound calls are bridged. One or more parameters of the bridged call are compared to the call quality rating. An indication is recorded regarding the successful bridging of the calls in association with an entity identifier.

Abstract: An online and offline communication processing and tracking using data processing and data/voice networks is described. A phone address from a phone address number pool is automatically assigned to a first entity. A call quality rating is determined and recorded. A call from a caller directed to the phone address is received at a call bridging system coupled to at least one network, wherein the call is associated with call signaling information. Based at least in part on the call quality associated with the caller call, the caller call is assigned to a first location in a call queue. An outbound call is generated from the call bridging system and the inbound and the outbound calls are bridged. One or more parameters of the bridged call are compared to the call quality rating. An indication is recorded regarding the successful bridging of the calls in association with an entity identifier.

Abstract: An online and offline communication processing and tracking system using data processing and data/voice networks is described. A phone address from a phone address number pool is automatically assigned to a first customer prospect communication. A call quality rating is determined and recorded. A call from a caller directed to the phone address is received at a call bridging system coupled to at least one network, wherein the call is associated with call signaling information. Based at least in part on the call quality associated with the caller call, the caller call is routed to entity placing a bid on the caller call. An outbound call is generated from the call bridging system and the inbound and the outbound calls are bridged.

Abstract: Methods and systems for reducing the impact of fraudulent or spam calls are disclosed. One or more calls to a first phone address are received, the first phone address not currently associated with a communication for a customer prospect. The calling party phone addresses associated with the calls received prior to the association of the first phone address to the first communication are stored. Then the first phone address is associated to the first communication. A first call to the first phone address is received. Prior to answering the first call and at least partly in response to a determination that a calling party phone address of the first call matches one of the previously stored calling party phone address, the first call is identified as a spam or otherwise undesirable call candidate and may be rejected.