Method and apparatus for processing natural language with a hierarchy of mapping routines
First Claim
1. A computer system having the ability to process natural language, the system comprising:
- a processor;
memory for maintaining a database of task-pertinent events, said memory being coupled to said processor;
an input device coupled to said processor for receiving natural language from a user;
means for developing a string from said natural language coupled to said input device;
means for mapping a portion of said string into said database using a plurality of different mapping routines arranged in a hierarchy, wherein a successive mapping routine in said hierarchy is used when a previous different mapping routine in said hierarchy does not map said portion of said string; and
means for performing a computer-implemented task based upon said mapped portion of said string.
1 Assignment
0 Petitions
Accused Products
Abstract
A method and apparatus for processing natural language and deducing meaning from a natural language input characterized by the steps of (a) receiving an ordered string of word objects having a natural language meaning, (b) selecting a word window length, and (c) successively moving the word window along the ordered string and analyzing the meaning of a substring of word objects that fall within the word window. The substring is removed from the ordered string if the substring has a recognized meaning, until all substrings of the ordered string that fit within the window have been analyzed. In a step (d), the word window length is reduced and step (c) is repeated until only an unrecognized residual of the ordered string remains. The meaning of the substring is analyzed by mapping the substring against a database using one or more mapping routines. The mapping routines are preferably arranged in a hierarchy, wherein a successive mapping routine is used to analyze the substring when a previous mapping routine in the hierarchy cannot map the substring. A computer-implemented task is determined from the recognized substrings and performed by the computer system. The apparatus of the present invention implements the method on a pen-based computer system, and the ordered string is preferably received from strokes entered by a stylus on a display screen of the pen-based computer or from a microphone receiving speech input.
209 Citations
20 Claims
-
1. A computer system having the ability to process natural language, the system comprising:
-
a processor; memory for maintaining a database of task-pertinent events, said memory being coupled to said processor; an input device coupled to said processor for receiving natural language from a user; means for developing a string from said natural language coupled to said input device; means for mapping a portion of said string into said database using a plurality of different mapping routines arranged in a hierarchy, wherein a successive mapping routine in said hierarchy is used when a previous different mapping routine in said hierarchy does not map said portion of said string; and means for performing a computer-implemented task based upon said mapped portion of said string. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A method for implementing a task input in natural language by a user into a computer system, the method comprising:
-
developing a string including recognized word objects from input received from a user; examining a number of said word objects of said string shown in a word window according to a first mapping routine to map said number of word objects into a database, said word window having a predetermined length; examining said word objects shown in said word window according to a second mapping routine when said number of word objects of said string do not map according to said first mapping routine, said second mapping routine utilizing a different mapping process from said first mapping routine and requiring more time to implement than said first mapping routine when examining said number of word objects; examining said word objects shown in said word window according to a third mapping routine when said number of word objects of said string do not map according to said second mapping routine, said third mapping routine utilizing a different mapping process from said first mapping routine and said second mapping routine and requiring more time to implement than said second mapping routine when examining said number of word objects; and performing a task in accordance with a mapping obtained by said examination of said word objects shown in said word window. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A method for recognizing meanings of natural language phrases comprising:
-
attempting to map at least a portion of an ordered string of words into a database according to a phrasal mapping routine; attempting to map said portion into a database according to a pattern mapping routine when said portion does not map according to said phrasal mapping routine; and attempting to map said portion according to a database query mapping routine when said portion does not map according to said pattern mapping routine. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification