# US 2008/0187109 A1 · Audio archive generation and presentation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2008/0187109 A1
- Document ID: US20080187109A1
- Status: Published application
- Kind: A1
- Application number: 12/025,535
- Filed: 2008-02-04
- Published: 2008-08-07
- Earliest claimed: 2007-02-05
- Assignees: International Business Machines Corporation
- Inventors: FAN PING MENG; Yong Qin; Qin Shi; Zhi Wei Shuang
- Web page: https://patentgrep.com/patent/US20080187109A1

## CPC

- H04M 3/4936: {Speech interaction details (speech recognition per se G10L15/00)}
- H04M 3/5166: {in combination with interactive voice response systems or voice portals, e.g. as front-ends}
- H04M 3/42221: {Conversation recording systems (at the subscriber's set H04M1/656)}
- H04M 2203/2011: Service processing based on information specified by a party before or during a call, e.g. information, tone or routing selection
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

A method, information processing system, and computer program storage product for automatically generating auditory archives in a customer service environment are disclosed. A communication link with an end user is established. An information form is retrieved. The information form includes at least a category choice information set and at least one audio recoding information set. The end user is prompted to answer a set of questions based on information in the information form. A data set associated with each answer to each question in the set of questions given by the end user is stored. The data is stored under a set of fields corresponding to a question. Each data set stored under the set of fields for each question in the set of questions are combined with each other. An audio archive file is generated including the data sets that have been combined.

## Claims

### Claim at position 1

1-20. (canceled)

### Claim 21

A method for automatically generating and presenting auditory archives in a customer service environment, the method on an information processing system comprising:
establishing a communication link with an end user;
retrieving an information form, wherein the information form comprises at least a category choice information set, at least one audio recoding information set, an auditory archive information set, a time tag information set, and an index information set;
prompting the end user to answer a set of questions based on information in the information form,
wherein prompting the end user further comprises:
prompting the end user to answer at least one question corresponding to the category information set via at least one of voice and keypad entry and at least one question corresponding to the audio recording set via voice;
storing a data set associated with each answer to each question in the set of questions by given by the end user, wherein the data is stored under a set of fields corresponding to a question;
combining each data set stored under the set of fields for each question in the set of questions,
wherein combining each data set further comprises:
determining that at least one data set comprises data in a text form;
convening the data in the text form into an audio format;
adding at least one audible voice prompt to each data set combined;
deleting redundant voice information detected between each data set;
deleting intervals of silence greater than a given threshold; and
receiving a desired sequence for combining each data set from a customer service representative; and
combining each data set according to the desired sequence received from the customer service representative;
generating an audio archive file comprising the data sets that have been combined, wherein generating an audio archive further comprises:
generating time tag information corresponding to a set of audio recordings stored in the auditory archive file;
storing the time tag information into the time tag information set in the information form;
generating index information coffesponding to a set of audio recordings stored in the auditory archive file;
storing the index information into the index information set in the information form;
determining a set of customer service representatives that are available to assist the end user;
prioritizing each customer service representative in the set of customer service representatives according to customer feedback;
transmitting the audio archive file to a customer service representative in the set of customer service representatives based on the prioritizing; and
displaying text prompts to the customer service representative corresponding to audio within the audio archive file while the customer service representative is interacting with the audio archive file.
