Voice activated web browser

• US 6,311,182 B1
• Filed: 11/17/1997
• Issued: 10/30/2001
• Est. Priority Date: 11/17/1997
• Status: Expired due to Term

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Genuity Inc. (Lumen Technologies, Inc.), GTE Service Corporation (Verizon Communications Inc.)
• Inventors: Colbath, Sean C., Nguyen, Long, Pham, Cecile, Stallard, David
• Primary Examiner(s): Homere, Jean R.
• Assistant Examiner(s): ROBINSON, GRETA LEE
• Application Number:
  US08/971,606
• Time in Patent Office: 1,443 Days
• Field of Search: 707/10, 707/1, 707/102, 707/104, 707/3, 707/4, 707/5, 707/6, 704/9, 704/3, 704/10, 704/231, 704/233, 704/246, 704/247, 379/900, 379/907
• US Class Current: 704/246
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: Y10S 379/90 Internet, e.g. Internet phone, webphone, internet-based telephony
• CPC Class Codes: Y10S 707/912 Applications of a database
• CPC Class Codes: Y10S 707/917 Text
• CPC Class Codes: Y10S 707/99933 Query processing, i.e. searching
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

A voice activated and operated Internet web browser where voiced utterances are digitized and the digitized representation is input to a speech recognition program is disclosed. The speech recognition program determines the most likely set of words from a stored vocabulary making up the utterances. The words are analyzed and searched against a database of topics or micro-domain areas. If a match occurs the words are analyzed by a subprogram associated with the specific topic area and key words are identified and other words discarded. The key words are input to a search engine or the equivalent. The search engine returns information associated with the topic. If no topic match is found a general search on the recognized words is performed. The recognized words are fed to a identification module where key words are extracted that are associated with names of people, organizations, locations, and companies; times; money amounts; percentages; dates; and not-a-name. The extraneous not-a-name words are discarded and the remaining key words are passed to a search engine. The search engine returns with web pages or other such information are found and displayed to the user. The user may re-run the identification module for marking hyperlinks for more particular information.

Claims

1. A method of determining search words from digitized representations of voiced utterances, using a database of preselected words and phrases associated with preselected specific areas of interest, the method comprising the steps of:

identifying words and phrases in a digitized representation of a voiced utterance;

comparing said identified words and phrases to said database of preselected words and phrases associated with preselected specific areas of interest;

determining whether a match exists between said identified words and phrases and said database of preselected words and phrases, the match representing at least one of the preselected specific areas of interest;

generating, when a match exists, a search string based on the at least one area of interest;

wherein, if no match exists, generating a search string comprising;

classifying parts of said identified words and phrases as at least one of names of people, locations, organizations and companies,

classifying parts of said identified words and phrases as indicating at least one of times, dates and amounts of money,

marking all other words in said identified words and phrases as extraneous words, and

assembling a search string composed of the words and phrases classified as at least one of people, locations, organizations, companies, times, dates and amounts of money; and

passing said search string to a search facility.

2. The method of claim 1 further comprising the step of:

receiving and displaying web pages or other information found by said search facility.

3. The method of claim 2 further comprising the steps of:

selecting from said displayed web page or other information a subset of displayed text from which hypertext links are to be formed;

classifying parts of said subset of displayed text as at least one of people, locations, organizations and companies;

marking all other words of said subset of displayed text as extraneous words;

deleting said extraneous words;

forming hypertext links composed of the classified parts of said subset of displayed text; and

passing said hypertext links to a search facility.

4. A method of determining search words from digitized representations of voiced utterances, using a database of preselected words and phrases associated with preselected specific areas of interest, the method comprising the steps of:

identifying words and phrases in a digitized representation of a voiced utterance;

comparing said identified words and phrases to said database of preselected words and phrases associated with preselected specific areas of interest;

determining whether a match exists between said identified words and phrases and said database of preselected words and phrases, the match representing at least one of the preselected specific areas of interest;

generating, when a match exists, a search string based on the at least one area of interest;

passing said search string to a search facility;

receiving and displaying web-pages or information returned by said search facility;

selecting from said displayed web page or other information a subset of displayed text from which hypertext links are to be found;

classifying parts of said subset of displayed text as at least one of people, locations, organizations and companies;

marking all other words in said subset of displayed text as extraneous words;

deleting said extraneous words;

forming hypertext links composed of the classified parts of said subset of displayed text; and

passing said hypertext links to a search facility.

5. An apparatus for determining search words from digitized representations of voiced utterances comprising:

a speech recognition apparatus outputting digitized representations of voiced utterances;

a database of preselected words and phrases associated with preselected specific areas of interest;

a search facility;

means for identifying words and phrases in a digitized representation of a voiced utterance;

means for comparing said identified words and phrases to said database of preselected words and phrases associated with preselected specific areas of interest;

means for determining whether a match exists between said identified words and phrases and said database of preselected words and phrases, the match representing at least one of the preselected specific areas of interest;

means for generating, when a match exists, a search string of search words;

wherein if no match exists, the means for generating a search string comprises;

means for classifying parts of said identified words and phrases as at least one of names of people, locations, organizations and companies,

means for classifying parts of said identified words and phrases as indicating at least one of times, dates and amounts of money,

means for marking all other words in said identified words and phrases as extraneous words, and

means to assemble a search string composed of the words identified as at least one of people, locations, organizations, companies, times, dates and amounts of money; and

means for passing said search string to said search facility.

7. The apparatus of claim 5 wherein the search facility is a web search facility.

6. An apparatus for determining search words from digitized representations of voiced utterances comprising:

a speech recognition apparatus outputting digitized representations of voiced utterances;

a database of preselected words and phrases associated with preselected specific areas of interest;

a search facility;

means for identifying words and phrases in a digitized representation of a voiced utterance;

means for comparing said identified words and phrases to said database of preselected words and phrases associated with preselected specific areas of interest;

means for determining whether a match exists between said identified words and phrases and said database of preselected words and phrases, the match representing at least one of the preselected specific areas of interest;

means for generating, when a match exists, a search string of search words;

means for passing said search string of search words to said search facility;

means for receiving and displaying a web page or other information found by said search facility;

means for selecting from said displayed web page or other information a subset of displayed text from which hypertext links are to be formed;

means for classifying said subset of displayed text to identify at least one of names of people, locations, organizations and companies and all other words as extraneous words;

means for forming hypertext links composed of the identified at least one of names of people, locations, organizations and companies; and

means for passing said hypertext links to a search facility.