Knowledge system method and appparatus

• US 7,860,706 B2
• Filed: 09/11/2003
• Issued: 12/28/2010
• Est. Priority Date: 03/16/2001
• Status: Expired due to Fees

• Current Assignee: Meaningful Machines LLC
• Original Assignee: Meaningful Machines LLC
• Inventors: Abir, Eli
• Primary Examiner(s): Hudspeth; David R
• Assistant Examiner(s): NEWAY, SAMUEL G
• Application Number:
  US10/659,792
• Publication Number:
  US 20040122656A1
• Time in Patent Office: 2,665 Days
• Field of Search: None
• US Class Current: 704/4
• CPC Class Codes: G06F 16/30 of unstructured textual data document management systems G06F16/93
• CPC Class Codes: G06F 16/3337 Translation of the query language, e.g. Chinese to English
• CPC Class Codes: G06F 40/55 Rule-based translation
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition

Abstract

A method and apparatus for automating the acquisition, reconstruction, and generation of knowledgebases of associated ideas and using such knowledgebases in many applications including machine translation of human languages, search and retrieval of unstructured text, or other data, based on concept search, voice recognition, data compression, and artificial intelligence systems.

Claims

1. A computer device including a processor, a memory coupled to the processor, and a program stored in the memory, wherein the computer is configured to execute the program and perform the steps of:

providing a translation of words expressed in a first language to words and/or strings of words expressed in a second language;

providing a corpus of documents expressed in said second language;

receiving a query to be analyzed, wherein said query is expressed in said first language, and wherein said query consists of a string of words;

identifying for said query, all translations of each word comprising said word string query, to said second language utilizing said provided translation;

analyzing said corpus of documents for word strings expressed in said second language, wherein said analyzing only identifies word strings having a user defined maximum number of words, and wherein said analyzing only identifies word strings having translations obtained from a user defined minimum number of words expressed in the first language in said identifying step without regard for the combination or order of the words in said corpus, wherein said analyzing only counts one of the possible translations for each of said words expressed in the first language;

returning a list of said word strings expressed in said second language from said analyzing said corpus of documents as word string results without regard for the combination or order in the second language strings of the second language words corresponding to translations of the works in the first language query,

providing a corpus of documents expressed in said first language;

identifying a user defined number of occurrences of said query in said corpus of documents expressed in said first language;

analyzing a user defined number of words and/or word strings to the left and to the right of each of said occurrences of said query and identifying word strings comprising the user defined number of words and/or word strings to the left of said query, said query, and the user defined number of words and/or word strings to the right of said query;

creating a list of returned word strings comprising the results of said analyzing step;

analyzing each returned word string individually and identifying all translations of each word comprising each of said returned word strings, to said second language utilizing said provided translation;

analyzing said corpus of documents for word strings expressed in said second language, wherein said analyzing only identifies word strings having a user defined maximum number of words, and wherein said analyzing only identifies word strings having translations obtained from a user defined minimum number of words expressed in the word string in the first language determined by said creating step, wherein said analyzing said corpus counts only one translation for each of said words expressed in said first language;

returning a list of said second word strings expressed in said second language from said analyzing said corpus of documents as a result;

analyzing said list of word strings and said list of second word strings to identify the number of occurrences wherein each word string on said list of word strings occurs as a word string subset of a word string on said list of second word strings;

returning a list based on said analyzing said list of word strings and said list of second word strings step.

2. The computer device of claim 1, wherein said analyzing said list of word strings and said list of second words strings step includes modifying said number of occurrences by omitting each occurrence of a word string if the word string is a subset of a longer word string that is also on the returned list.

3. The computer device of claim 1, wherein a word expressed in the first language includes word strings in the first language such as idioms and collocations.

4. The computer device of claim 1, further configured to perform the step of ranking said list of word string results based on user-defined criteria.

5. A non-transitory computer readable storage medium having stored thereon a program executable by a computer processor for performing the steps of:

providing a translation of words expressed in a first language to words and/or strings of words expressed in a second language;

providing a corpus of documents expressed in said second language;

receiving a query to be analyzed, wherein said query is expressed in said first language, and wherein said query consists of a string of words;

identifying for said query, all translations of each word comprising said word string query, to said second language utilizing said provided translation;

analyzing said corpus of documents for word strings expressed in said second language, wherein said analyzing only identifies word strings having a user defined maximum number of words, and wherein said analyzing only identifies word strings having translations obtained from a user defined minimum number of words expressed in the first language in said identifying step without regard for the combination or order of the words in said corpus, wherein said analyzing only counts one of the possible translations for each of said words expressed in the first language;

returning a list of said word strings expressed in said second language from said analyzing said corpus of documents as word string results without regard for the combination or order in the second language strings of the second language words corresponding to translations of the works in the first language query;

providing a corpus of documents expressed in said first language;

identifying a user defined number of occurrences of said query in said corpus of documents expressed in said first language;

analyzing a user defined number of words and/or word strings to the left and to the right of each of said occurrences of said query and identifying word strings comprising the user defined number of words and/or word strings to the left of said query, said query, and the user defined number of words and/or word strings to the right of said query;

creating a list of returned word strings comprising the results of said analyzing step;

analyzing each returned word string individually and identifying all translations of each word comprising each of said returned word strings, to said second language utilizing said provided translation;

analyzing said corpus of documents for word strings expressed in said second language, wherein said analyzing only identifies word strings having a user defined maximum number of words, and wherein said analyzing only identifies word strings having translations obtained from a user defined minimum number of words expressed in each word string in the first language determined by said creating step, wherein said analyzing said corpus counts only one translation for each of said words expressed in said first language;

returning a list of said second word strings expressed in said second language from said analyzing of said corpus of documents as a result;

analyzing said list of word strings and said list of second word strings to identify the number of occurrences wherein each word string on said list of word strings occurs as a word string subset of a word string on said list of second word strings; and

returning a list based on said analyzing said list of word strings and said list of second word strings step.

6. The non-transitory computer medium of claim 5, wherein said analyzing said list of word strings and said list of second words strings step includes modifying said number of occurrences by omitting each occurrence of a word string if the word string is a subset of a longer word string that is also on the returned list.

7. The non-transitory computer medium of claim 5, wherein a word express in a first language includes word strings in a first language such as idioms and collocations.

8. The non-transitory computer medium of claim 5, further performing the step of ranking said list of word strings results based on user-defined criteria.