Natural language web browser

Abstract

Described are natural language web browsers configured to provide a natural language interface to an existing web browser or a newly created web browser. That is, users interact with the web browser employing speech (or text) as input and output instead of using a mouse and keyboard as input and an electronic display screen as output. Embodiments of a natural language web browser converts user questions, statements, and/or commands into actions, reads the resulting HTML and converts the HTML into natural language descriptions to provide to the user.

What is claimed is: 
     
         1 . A natural language web browsing method comprising:
 accepting by a web browser a natural language input, the web browser configured to browse a computer network including a plurality of websites having web pages;   parsing the natural language input into at least one of a question, a statement, and a command;   operating the web browser in accordance with the parsed natural language input; and   returning results of the natural language web browsing, wherein the web browsing is accomplished by use of at least a digital processing device.   
     
     
         2 . The method of  claim 1  further including:
 determining if the natural language input is ambiguous; 
 generating a query asking what was meant by the natural language input when the natural language input is determined to be ambiguous; and 
 accepting by the web browser, a same or conceptually similar natural language input as the previously accepted natural language input and parsing the same or conceptually similar natural language input into at least one of a question, a statement, and a command of the same or conceptually similar natural language input, when the natural language input was determined to be ambiguous. 
 
     
     
         3 . The method according to  claim 1  further including providing information related to actions of the web browser that occurred during the natural language web browsing. 
     
     
         4 . The method according to  claim 3  further including providing information when a current focus of the web browsing has changed. 
     
     
         5 . The method according to  claim 2  wherein the operating of the web browser in accordance with at least one of the determined and parsed natural language input and the same or conceptually similar natural language input, without the method limiting access to web sites on the world wide web. 
     
     
         6 . The method according to  claim 5  wherein the operating includes navigating directly to a particular web page on the world wide web not restricted by the method to a preset number of web sites. 
     
     
         7 . The method according to  claim 1  wherein the parsing includes:
 enumerating web elements of a current web page that has been identified in a current web browsing session; 
 generating potential references for each enumerated web element; 
 finding a best match between segments of the natural language input and the generated potential references; 
 finding a best match between the segments of the natural language input and known question, statement, and command types; and 
 creating an ambiguity when more than one best match of the finding steps is possible. 
 
     
     
         8 . The method according to  claim 7  wherein the enumerated web elements include at least one of a header section, a first section, and a second section. 
     
     
         9 . The method according to  claim 1  wherein the natural language input includes one of a navigation command, a read command, a summarize command, a describe command, a click command, a type command, a find command, and a search command. 
     
     
         10 . The method according to  claim 9  wherein the navigation command is performed by:
 directing the web browser to visit a destination named by a universal resource locator (URL) when the destination of the navigation command is a URL destination; 
 setting a focus to the URL destination; and 
 describing the focus to a user. 
 
     
     
         11 . The method according to  claim 10  wherein visiting the URL destination includes:
 giving the URL destination to the web browser; 
 loading a selected web page corresponding to the URL destination; and 
 restructuring the selected web page to improve an ability to describe the selected web page. 
 
     
     
         12 . The method according to  claim 11  wherein the restructuring of the web page includes:
 creating a tree structure, having tree elements, for the loaded web page based the HTML of the tree structure; 
 finding labels for tree elements in the HTML of the loaded web page; 
 replacing unlabeled HTML document division element, (<div>), with their children; and 
 for a tree element having more than N children, creating a “more” element with the remainder of children elements. 
 
     
     
         13 . The method according to  claim 9  wherein the describe command further includes:
 enumerating children of a given web element; 
 generating a simple reference for each child; 
 generating a reference for the given web element; 
 identifying that the given web element reference has a generated list of references; and 
 when the given web element is a URL, identifying a title of the web page. 
 
     
     
         14 . The method according to  claim 13  wherein if two or more adjacent children have a same reference, replace them with a group reference. 
     
     
         15 . The method according to  claim 9  wherein the read command further includes:
 recursively describing a web element; and including the text of any web element encountered that has a text associated with it. 
 
     
     
         16 . The method according to  claim 9  wherein the click command further includes:
 directing the web browser to click on a web element; 
 performing a navigation operation if the web element is a link; and 
 otherwise identifying how the web page changed. 
 
     
     
         17 . The method of  claim 1  wherein the natural language input includes a question, statement, or command that is specific to the web site currently being visited. 
     
     
         18 . A system for performing natural language web browsing, the system comprising:
 a communication arrangement including, at least one digital processing device, an electronic storage and an input/output device configured to communicate with a computer network including a plurality of websites having web pages the communication arrangement configured to:   accept by a web browser a natural language input, the web browser configured to browse the computer network;   parse the natural language input into at least one of a question, a statement, and a command;   operate the web browser in accordance with at least one of the parsed natural language inputs; and   return results of the natural language web browsing.   
     
     
         19 . The system according to  claim 18 , the system comprising:
 determining if the natural language input is ambiguous;   generating a query asking what was meant by the natural language input when the natural language input is determined to be ambiguous;   accepting by the web browser, a same or conceptually similar natural language input as the previously accepted natural language input and parse the same or conceptually similar natural language input into at least one of a question, a statement, and a command of the same or conceptually similar natural language input, when the natural language style input was determined to be ambiguous.