Using web FAQ data for creating self-service speech applications

• US 7,558,734 B1
• Filed: 11/16/2008
• Issued: 07/07/2009
• Est. Priority Date: 02/27/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: International Business Machines Corporation
• Inventors: Jan, Ea-Ee, Lubensky, David M., Li, Xiang, Stewart, Osamuyimen T.
• Primary Examiner(s): Wozniak; James S
• Application Number:
  US12/271,912
• Time in Patent Office: 233 Days
• Field of Search: 704/270, 704/270.1, 704/275, 379/88.01
• US Class Current: 704/270
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/95 Retrieval from the web
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 3/4938 comprising a voice browser which renders and interprets, e.g. VoiceXML

Abstract

In one example, this invention presents a method of providing the same self-service content that is available on the web interface to users contacting by telephone, knowing that the web and telephone are fundamentally different user interfaces. In one embodiment, this patent seeks to protect the general idea of how to playback web data in real-time to the user over the speech interface. For this purpose, a method is presented comprising of the general steps through which the web data is initially sent to an automatic transformation module. Then, that transformation module refines or re-structures the web data to make it suitable for the speech interface. The algorithm in the module is predicated on the user interface principles of cognitive complexity and limitations on short term memory based on which FAQ types are classified into one of the following four classes: simple, medium, complex, and complex-complex.

Claims

1. A system of using web data for telephone self-service, said system comprising:

a web data storage comprising a plurality of web domains;

a speech application that performs the following;

pulls scripts for frequently-asked issues for all problem types from a relevant web domain selected from the plurality of web domains using a web crawler;

automatically parses a content of said frequently-asked issues into speech acts relevant to a speech domain by picking out verbs, verb phrases, nouns, noun phrases, adjective phrases, or adjunct clauses;

reformats speech acts;

creates a different number of steps corresponding to said speech acts, wherein a causality function is preserved, by keeping a sequential order of said verbs associated with said speech acts;

analyzes all said speech acts corresponding to a specific problem;

categorizes all said speech acts corresponding to said specific problem into multiple numbers of classes by counting tokens of the speech acts, corresponding to different ranges of complexity of steps, based on a typical human'"'"'s short-term memory limitation and recollection, wherein the classes comprise simple, medium, complex, and complex-complex; and

plays back a script of a content corresponding to said specific problem, according to said categorized classes, problem type of said specific problem, and frequently-asked issue associated with said specific problem; and

a user phone interface that enables said user to control and navigate said playback.