A communication event processing method performed at a computer server includes: obtaining identification information and call description information from multiple different terminals about a phone number; determining whether the phone number is a nuisance phone number according to the call description information and a quantity of the terminals identifying the phone number; and sending, after receiving a query request for the phone number, a blocking instruction to a terminal initiating the query when it is determined that the phone number is a nuisance phone number, so that the terminal initiating the query blocks a communication event of the phone number. According to the present disclosure, the server can determine which phone numbers are nuisance phone numbers according to specific identification cases and the call description information, and therefore provide highly accurate processing in response to a query request of a terminal, thereby greatly improving efficiency of communication event processing.

The location of voice prompts within a call waveform is usually conducted by match filtering a snippet of the prompt (approx. 800 ms) to the call waveform. In an enhanced process that can accommodate transmission errors when detecting voice prompts on lower quality transmission lines, a snippet of a voice prompt may be divided into sniplets, typically 100 ms long. The sniplets can be individually detected. If a sufficient number of sniplets are detected within allowed time tolerances, then this subset of detected sniplets can indicate the presence of the snippet, and thus the associated voice prompt.

The system and methods described herein can classify electronic activities based on sender and recipient information. The system can determine a relationship between a sender of an electronic activity and at least one recipient of the electronic activity using a sender node profile and a recipient node profile. The system can assign a tag to the electronic activity based on the relationship between the sender and one or more recipients of the electronic activity. The system can process the electronic activity based on the assigned tag.

Disclosed are systems and methods for robocall steering over voice-hosted traffic networks. The disclosed framework provides novel systems and methods for increasing the accuracy and efficiency in tracking, identifying, blocking and preventing robocalls and robocallers. The disclosed systems and methods provide mechanisms for identifying and removing unwanted voice traffic from networks. The disclosed systems and methods analyze voice traffic over a predetermined period of time (e.g., 1 day or 30 days, for example), and leverage this information into a “know your customer” (KYC) score. This score enables incoming calls to be routed, controlled and/or blocked as they are communicated over voice networks.

Methods and apparatuses are described for determining customer service quality through digitized voice characteristic measurement and filtering. A voice analysis module captures a first digitized voice segment corresponding to speech submitted by a user of a remote device. The voice analysis module extracts a first set of voice features from the first voice segment, and determines an emotion level of the user based upon the first set of voice features. The voice analysis module captures a second digitized voice segment corresponding to speech submitted by the user. The voice analysis module extracts a second set of voice features from the second voice segment, and determines a change in the emotion level of the user by comparing the first set of voice features to the second set of voice features. The module normalizes the change in the emotion level of the user using emotion influence factors, and generates a service score.

Prompt snippets (typically 800 ms long) that are used to detect voice prompts within a call waveform may be divided into smaller sniplet portions (approx. 100 ms) long. The presence of a prompt in a call waveform may be detected by detecting the sniplets and determining if a sufficient number of the sniplets of a snippet were detected in sequence and within allowable time constraints. The use of sniplets improves accuracy of prompt detection in call waveforms in lower quality transmissions.

A method and apparatus of applying user profile information to a customized application are disclosed. One example method of operation may include receiving an inquiry from a user device at a customer call center server and identifying and authorizing the user from the received inquiry. The method may also provide retrieving a user profile from memory that includes history information based on previous interactions between the user device and the customer call center server and calculating a prediction as to a purpose for the inquiry. The prediction may be based on user profile history, social networking profile information, recent transactions, etc. The method may also provide transmitting a response to the inquiry based on the calculated prediction.

The present invention discloses a system, apparatus, and method that obtains audio and metadata information from voice calls, generates textual transcripts from those calls, and makes the resulting data searchable via a user interface. The system converts audio data from one or more sources (such as a telecommunications provider) into searchable usable text transcripts. One use of which is law enforcement and intelligence work. Another use relates to call centers to improve quality and track customer service history. Searches can be performed for callers, callees, keywords, and/or other information in calls across the system. The system can also generate automatic alerts based on callers, callees, keywords, phone numbers, and/or other information. Further the system generates and provides analytic information on the use of the phone system, the semantic content of the calls, and the connections between callers and phone numbers called, which can aid analysts in detecting patterns of behavior, and in looking for patterns of equipment use or failure.

A system herein provides automated call-back of customers who have terminated an inbound call by exercising a call-back option of an interactive voice response unit or by abandoning the inbound call, using predictive modeling of caller value to prioritize call-backs. The call management system monitors the inbound customer call and detects any termination of the customer call. A call-back module opens a call-back record for the terminated customer call and associates that call-back record with an identified customer. The call-back module retrieves customer demographic data and other data associated with the identified customer. A predictive module determines a value prediction signal for the identified customer by modeling purchase and lapse behaviors and classifies each identified customer for either priority call-back or subordinate call-back treatment. Priority call-back classification may result in assignment to a priority call-back queue, assignment to a priority call-back queue position, or call-back by a selected agent.

Systems and methods are shown for routing task objects to multiple agents that involve analyzing content of each task object in an input buffer to determine a classification relevant to the content of the task object that is added to task object metadata, which is placed in a second buffer. Objects in the second buffer are analyzed and the classification in the object metadata used to search workforce management data representing agent characteristics to identify agents who match the classification. A routing strategy is applied to the object to select an agent and the object is routed to the agent's workbin. Another aspect involves organizing workbin tasks objects by priority, according to recent system conditions excluding objects that cannot presently be processed based on a workflow strategy or status data and presenting remaining objects based on order of priority, or re-arranging objects between workbins based on recent status info.