Abstract:
A system and method for processing call data is provided. A call between a user and an agent is monitored. A selected script having a dialog grammar is received. The selected script is executed by converting at least a portion of the script into synthesized speech utterances and providing the synthesized speech utterances to the user. Speech utterances are received from the user in reply to each of the synthesized speech utterances from the script. Each received speech utterance is converted to text as a user message and a form is populated with the user messages. The user speech utterances and the form with the user messages are provided to the agent.
Abstract:
A system and method for providing agent guidance is provided. Speech communicated by a user to an agent is monitored during a call within a call center. Traits of the user are identified during the call based on the speech of the user. A determination is made as to how likely the user is to accept an offer provided by the agent based on the user traits. The user is classified as belonging to one of a plurality of stages of persuasion based on the likelihood determination, and guidance is provided to the agent based on classification of the user in at least one of the classes. The offer is provided to the user based on the guidance.
Abstract:
A system and method for identifying special information is provided. Endpoints are defined within a voice recording. One or more of the endpoints are identified within the voice recording and the voice recording is partitioned into segments based on the identified endpoints. Elements of text are identified by applying speech recognition to each of the segments and a list of prompt list candidates are applied to the text elements. The segments with text elements that match one or more prompt list candidates are identified. Portions of the voice recording following the prompt list candidates that include special information are identified and the special information is rendered unintelligible within the voice recording.
Abstract:
A computer-implemented system and method for detecting events for use in an automated call center environment are provided. A plurality of messages is monitored by a call center. Those messages sharing one or more keywords representative of one or more potential events are identified. The one or more potential events are detected based on the shared keywords. At least one of the potential events is identified as an event based on the number of messages that share the keywords representative of that potential event. Metadata regarding the event is extracted from the messages sharing the keywords representative of the event. A message regarding the event that includes the extracted metadata is generated. The generated message from the call center is provided to at least one user related to the event.
Abstract:
A computer-implemented system and method for facilitating agent-customer calls is provided. A call from a customer is accepted into a call center and is assigned to an agent associated with the call center. At least one text message is received from the customer during the call and is directed to the agent. Outgoing text messages are received from the agent in response to the text message from the customer and content of the outgoing text messages from the agent are converted into synthesized speech. The synthesized speech is provided to the customer during the call.
Abstract:
A system and method for determining customer hold times is provided. A database of caller profiles is maintained. A call from a caller is received into a call center and assigned to an agent. A delay during which the caller is to be placed on hold is identified. A hold time for the delay is determined based on a length of a hold queue, a level of busyness of the agent and the caller profile associated with the caller.
Abstract:
A system and method for providing guidance to persuade a caller is provided. A call is received from a caller into a call center and an offer is provided to the caller. A likelihood of the caller to accept the offer is measured by analyzing voice input of the caller during the call. One or more paralinguistic voice characteristics in the voice input are determined. A stage of persuasion is assigned to the caller based on the paralinguistic voice characteristics and a recommendation is made for guidance to persuade the caller to accept the offer.
Abstract:
A computer-implemented system and method for voice transcription error reduction is provided. Speech utterances are obtained from a voice stream and each speech utterance is associated with a transcribed value and a confidence score. Those utterances with transcription values associated with lower confidence scores are identified as questionable utterances. One of the questionable utterances is selected from the voice stream. A predetermined number of questionable utterances from other voice streams and having transcribed values similar to the transcribed value of the selected questionable utterance are identified as a pool of related utterances. A further transcribed value is received for each of a plurality of the questionable utterances in the pool of related utterances. A transcribed message is generated for the voice stream using those transcribed values with higher confidence scores and the further transcribed value for the selected questionable utterance.
Abstract:
A computer-implemented system and method for identifying and masking special information within recorded speech is provided. A field for entry of special information is identified. Movement of a pointer device along a trajectory towards the field is also identified. A correlation of the pointer device movement and entry of the special information is determined based on a location of the trajectory in relation to the field. A threshold is applied to the correlation. The special information is received as verbal speech. A recording of the special information is rendered unintelligible when the threshold is satisfied.
Abstract:
A computer-implemented system and method for masking special data is provided. Speakers of a call recording are identified. The call recording is separated into strands corresponding to each of the speakers. A prompt list of elements that prompt the speaker of the other strand to utter special information is applied to one of the strands. At least one of the elements of the prompt list is identified in the one strand. A special information candidate is identified in the other strand and is located after a location in time where the element was found in the voice recording of the one strand. A confidence score is assigned to the element located in the one strand and to the special information candidate in the other strand. The confidence scores are combined and a threshold is applied. The special information candidate is rendered unintelligible when the combined confidence scores satisfy the threshold.