Natural language knowledge servers as network resources
First Claim
Patent Images
1. A network resource system, comprising:
- a plurality of web servers;
wherein each of said plurality of web servers provides a commercial service and produces (i) a speech signal representing speech from a user of said commercial service, and (ii) context information;
wherein said context information reflects said commercial service and a predefined format in which data are returned to said web server;
wherein said context information varies among said plurality of web servers; and
a network knowledge server in communication with and separated from said plurality of web servers;
wherein said network knowledge server receives said speech signal and said context information and returns to each of said plurality of web servers a text structure having one or more fields based on said context information associated with said web server.
4 Assignments
0 Petitions
Accused Products
Abstract
A network resource system includes a first server which can communicate with a client computer. The first server produces a speech signal representing speech from a user at the client computer, and context information which indicates the semantic context of the user'"'"'s speech and a predefined format in which data are returned to the first server. A network knowledge server is in communication with and separated from the first server. The network knowledge server returns to the first server a text structure having one or more fields corresponding to the predefined format. The first server uses data from the one or more fields to determine a response to the user'"'"'s speech.
222 Citations
10 Claims
-
1. A network resource system, comprising:
-
a plurality of web servers;
wherein each of said plurality of web servers provides a commercial service and produces (i) a speech signal representing speech from a user of said commercial service, and (ii) context information;
wherein said context information reflects said commercial service and a predefined format in which data are returned to said web server;
wherein said context information varies among said plurality of web servers; and
a network knowledge server in communication with and separated from said plurality of web servers;
wherein said network knowledge server receives said speech signal and said context information and returns to each of said plurality of web servers a text structure having one or more fields based on said context information associated with said web server. - View Dependent Claims (2, 3, 4)
a search engine associated with at least one of the web servers that uses data from said one or more fields and returns a result to its associated web server.
-
-
3. A system as defined in claim 1, further comprising:
a script controlling operation of at least one of the web servers.
-
4. A system as defined in claim 1, wherein:
at least one of the web servers produces voice prompts for a telephone user and captures speech from a telephone user.
-
5. A method of recognizing speech for use in a computer network, comprising the following steps:
-
sending from each of a plurality of web servers to a network knowledge server (i) a speech signal representing speech, and (ii) context information;
wherein each of said plurality of web servers provides a commercial service;
receiving said speech signal and said context information at said network knowledge server;
wherein said context information reflects said commercial service and a predefined format in which data are returned to said web server;
wherein said context information varies among said plurality of web servers;
receiving by each of said plurality of web servers a text structure having one or more fields based on said context information associated with said web server. - View Dependent Claims (6, 7, 8, 9)
querying a database using data from said one or more fields to determine a response.
-
-
7. A method as defined in claim 5, wherein:
said plurality of web servers and said network knowledge server are separated in said computer network.
-
8. A method as defined in claim 5, further comprising the step of:
-
adapting each of said plurality of web servers to (i) run a preexisting application, (ii) generate a user interface based on said preexisting application, said user interface presenting a set of prompts and displays, and (iii) capture a speech signal produced by a client computer interacting with said user interface.
-
-
9. A method as defined in claim 5, wherein:
each of said plurality of web servers is adapted to produce voice prompts for a telephone user and capture speech produced by said telephone user in response to said voice prompts.
-
10. A method of providing a speech recognition service to a plurality of web servers, comprising the steps of:
-
receiving at a network knowledge server and from a plurality of web servers via a computer network (i) a speech signal representing speech, and (ii) context information;
wherein each of said plurality of web servers provides a commercial service;
wherein said context information reflects said commercial service and a predefined format in which data are returned to said web server;
wherein said context information varies among said plurality of web servers;
performing a speech recognition process on said speech signal; and
returning to each of said plurality of web servers a text structure having one or more fields corresponding to said predefined format associated with said web server.
-
Specification