Personal voice-based information retrieval system
CAFCFirst Claim
1. A method for retrieving information from an information source, the information source being periodically updated with current information, over a network, by speech commands received from a particular user of a plurality of users provided by the particular user via an electronic-communication device, and wherein each of the plurality of users has a respective electronic-communication device, said method comprising:
- (a) receiving a speech command from each of the plurality of users provided via the respective electronic-communication device, by a speech-recognition engine coupled to a media server, the media server configured to identify and access the information source via the network, the speech-recognition engine adapted to select speech-recognition grammar established to correspond to the speech commands received from the plurality of users and assigned to a desired search;
(b) selecting, by the media server, at least one information-source-retrieval instruction corresponding to the speech-recognition grammar established for a particular speech command, the at least one information-source-retrieval instruction stored in a database associated with the media server and adapted to retrieve information;
(c) accessing, by a web-browsing server, a portion of the information source to retrieve information of interest requested by the particular user, by using a processor of the web-browsing server, which processor (i) performs an instruction that requests information from an identified webpage, and (ii) utilizes a content extractor within the web-browsing server to separate a portion of the information from other information, the information derived from only a portion of the webpage containing information of interest to the particular user, wherein the content extractor uses a content-descriptor file containing a description of the portion of information and wherein the content-descriptor file indicates a location of the portion of the information within the information source;
(d) selecting by the web-browsing server the information of interest from the information source and retrieving only the portion of the information of interest requested by the particular user according to the at least one information-source-retrieval instruction;
(e) converting the information retrieved from the information source into an audio message by a speech-synthesis engine, the speech-synthesis engine coupled to the media server; and
(f) transmitting the audio message to the electronic-communication device of the particular user requesting information of interest to the particular user.
1 Assignment
3 Petitions
Accused Products
Abstract
The present invention relates to a system for retrieving information from a network such as the Internet. A user creates a user-defined record in a database that identifies an information source, such as a web site, containing information of interest to the user. This record identifies the location of the information source and also contains a recognition grammar based upon a speech command assigned by the user. Upon receiving the speech command from the user that is described within the recognition grammar, a network interface system accesses the information source and retrieves the information requested by the user.
403 Citations
26 Claims
-
1. A method for retrieving information from an information source, the information source being periodically updated with current information, over a network, by speech commands received from a particular user of a plurality of users provided by the particular user via an electronic-communication device, and wherein each of the plurality of users has a respective electronic-communication device, said method comprising:
-
(a) receiving a speech command from each of the plurality of users provided via the respective electronic-communication device, by a speech-recognition engine coupled to a media server, the media server configured to identify and access the information source via the network, the speech-recognition engine adapted to select speech-recognition grammar established to correspond to the speech commands received from the plurality of users and assigned to a desired search; (b) selecting, by the media server, at least one information-source-retrieval instruction corresponding to the speech-recognition grammar established for a particular speech command, the at least one information-source-retrieval instruction stored in a database associated with the media server and adapted to retrieve information; (c) accessing, by a web-browsing server, a portion of the information source to retrieve information of interest requested by the particular user, by using a processor of the web-browsing server, which processor (i) performs an instruction that requests information from an identified webpage, and (ii) utilizes a content extractor within the web-browsing server to separate a portion of the information from other information, the information derived from only a portion of the webpage containing information of interest to the particular user, wherein the content extractor uses a content-descriptor file containing a description of the portion of information and wherein the content-descriptor file indicates a location of the portion of the information within the information source; (d) selecting by the web-browsing server the information of interest from the information source and retrieving only the portion of the information of interest requested by the particular user according to the at least one information-source-retrieval instruction; (e) converting the information retrieved from the information source into an audio message by a speech-synthesis engine, the speech-synthesis engine coupled to the media server; and (f) transmitting the audio message to the electronic-communication device of the particular user requesting information of interest to the particular user. - View Dependent Claims (2, 3, 4, 5)
-
-
6. A system for retrieving information from an information source, the information source being periodically updated with current information, over a network, by speech commands received from a particular user of a plurality of users provided by the particular user via an electronic-communication device, and wherein each of the plurality of users has a respective electronic-communication device, said system comprising:
-
(a) a speech-recognition engine including a processor and coupled to a media server, the speech-recognition engine adapted to receive a speech command from each of the plurality of users provided via the respective electronic-communication device, the media server configured to identify and access the information source via the network, the speech-recognition engine adapted to select speech-recognition grammar established to correspond to the speech commands received from the plurality of users and assigned to a desired search; (b) the media server further configured to select at least one information-source-retrieval instruction corresponding to the speech-recognition grammar established for a particular speech command, the at least one appropriate information-source-retrieval instruction stored in a database associated with the media server and adapted to retrieve information; (c) a web-browsing server coupled to the media server and adapted to access a portion of the information source to retrieve information of interest requested by the particular user, by using a processor of the web-browsing server, which processor (i) performs an instruction that requests information from an identified webpage, and (ii) utilizes a content extractor within the web-browsing server to separate a portion of the information from other information, the information derived from only a portion of a webpage containing information of interest to a particular user, wherein the content extractor uses a content-descriptor file containing a description of the portion of information and wherein the content-descriptor file indicates a location of the portion of the information within the information source, and selecting, by the web-browsing server, the information of interest from the information source and retrieving only the portion of the information of interest requested by the particular user according to the at least one information-source-retrieval instruction; and (d) a speech-synthesis engine including a processor and coupled to the media server, the speech-synthesis engine adapted to convert the information retrieved from the information source into an audio message and transmit the audio message by the electronic-communication device of the particular user requesting information of interest to the particular user. - View Dependent Claims (7, 8, 9, 10)
-
-
11. A method for retrieving desired information from an information source of a plurality of information sources, the information source being periodically updated with current information, over a network, by speech commands received from a particular user of a plurality of users, wherein each of the plurality of users has a respective electronic-communication device, said method comprising:
-
(a) receiving a speech command, from each of the plurality of users via the respective electronic-communication device, the speech-recognition engine coupled to a media server, the media server configured to identify and access an information source from the plurality of information sources via the network, the speech-recognition engine adapted to select speech-recognition grammar established to correspond to the speech commands received, from certain of the plurality of users and assigned to a desired search; (b) selecting, by the media server, at least one information-source-retrieval instruction corresponding to the speech-recognition grammar established for a particular speech command, the at least one information-source-retrieval instruction stored in a database associated with the media server and adapted to retrieve information; (c) providing access, by the speech command, via a web-browsing server, to a portion of the information source to retrieve the desired information for the particular user, by using a processor of the web-browsing server, which processor (i) performs an instruction that requests information from an identified webpage, and (ii) utilizes a content extractor within the web-browsing server to separate a portion of the information from other information, the information is derived from only a portion of the webpage containing information of interest to a particular user, wherein the content extractor uses a content-descriptor file containing a description of the portion of information and wherein the content-descriptor file indicates a location of the portion of the information within the information source, (d) selecting, by the web-browsing server, the desired information from the appropriate information source and retrieving only the portion of the information of interest requested by the particular user according to the at least one information-source-retrieval instruction; (e) converting the information retrieved from the information source into an audio message, by a speech-synthesis engine, the speech-synthesis engine coupled to the media server; (f) conveying the audio message through the electronic-communication device to the respective electronic-communication device of the particular user requesting the desired information; and (g) providing a graphical display and adapted to display the desired information retrieved from the information source to the particular user on the respective electronic-communication device of the particular user. - View Dependent Claims (12, 13, 14, 15, 16, 17, 18, 25)
-
-
19. An information-retrieval system for retrieving information from an information source, the information source being periodically updated with current information, comprising:
-
(a) a speech-recognition engine coupled to a processor and a media server and adapted to receive a speech command from a particular user of a plurality of users via an electronic-communication device to access desired information, wherein each of the plurality of users has a respective electronic-communication device, the media server configured to identify and access an information source from a plurality of information sources via the network, the speech-recognition engine adapted to select speech-recognition grammar established to correspond to the speech commands received, the speech-recognition grammar associated with the desired information; (b) the media server, adapted to select at least one information-source-retrieval instruction corresponding to the speech-recognition grammar established for a particular speech command, the at least one information-source-retrieval instruction stored in a database associated with the media server and adapted to retrieve information from a particular one of the information sources that has the desired information; (c) a web-browsing server, adapted to provide access, by the speech command, to a portion of the information source to retrieve the desired information, by using a processor of the web-browsing server, which process (i) performs an instruction that requests information from an identified webpage, and (ii) utilizes a content extractor within the web-browsing server to separate a portion of the information from other information, the information derived from only a portion of the webpage containing information of interest to the particular user, wherein the content extractor uses a content-descriptor file containing a description of the portion of information and wherein the content-descriptor file indicates a location of the portion of the information within the information source and selecting, by the web-browsing server, the desired information from the information source and retrieving only the portion of the information desired by the particular user according to the at least one information-source-retrieval instruction; (d) a speech-synthesis engine coupled to the media server, and adapted to convert the portion of the information from the information source into an audio message for the particular user of the plurality of users and conveying the audio message through the electronic-communication device to the particular user of the plurality of users; and (e) a graphical display interface coupled to the media server and adapted to provide for display the desired information retrieved from the information source to certain others of the plurality of users. - View Dependent Claims (20, 21, 22, 23, 24, 26)
-
Specification