发明名称 |
FACE-TO-FACE COMMUNICATION ANALYSIS VIA MONO-RECORDING SYSTEM AND METHODS |
摘要 |
The methods, apparatus, non-transitory computer readable media, and systems described herein include recording a mono recording of a face-to-face communication between an agent and a customer using a microphone, wherein the mono recording is unseparated and includes agent voice data and customer voice data, separately recording the agent voice data in an agent recording using a second microphone; aligning the unseparated mono recording and the agent recording so they are time-synched; subtracting agent voice data from the unseparated mono recording using the agent recording to provide a separated recording including only customer voice data, wherein the agent voice data is subtracted from the unseparated mono recording based on the alignment, sound frequency analysis, or both; converting at least the customer voice data to text; and determining a personality type of the customer by applying one or more computer-implemented linguistic algorithms to the text of the customer voice data. |
申请公布号 |
US2017110121(A1) |
申请公布日期 |
2017.04.20 |
申请号 |
US201615389780 |
申请日期 |
2016.12.23 |
申请人 |
Mattersight Corporation |
发明人 |
WARFORD Roger;DANSON Christopher;KUHN Jennifer |
分类号 |
G10L15/18;G06Q30/00;G10L25/63;G10L21/0272;G10L17/06 |
主分类号 |
G10L15/18 |
代理机构 |
|
代理人 |
|
主权项 |
1. A system for analyzing a face-to-face customer-agent communication, comprising:
a node comprising a processor and a non-transitory computer readable medium operably coupled thereto, the non-transitory computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, wherein the plurality of instructions when executed:
record a mono recording of a communication between an agent and a customer using a microphone, wherein the mono recording is unseparated and includes agent voice data and customer voice data;separately record the agent voice data in an agent recording using a second microphone;align the unseparated mono recording and the agent recording so they are time-synched;subtract agent voice data from the unseparated mono recording using the agent recording to provide a separated recording including only customer voice data, wherein the agent voice data is subtracted from the unseparated mono recording based on the alignment, sound frequency analysis, or both;convert at least the customer voice data to text; anddetermine a personality type of the customer by applying one or more computer-implemented linguistic algorithms to the text of the customer voice data. |
地址 |
Chicago IL US |