Knowledge System Method and Apparatus

• US 20110202332A1
• Filed: 12/23/2010
• Published: 08/18/2011
• Est. Priority Date: 03/16/2001
• Status: Active Grant

• Current Assignee: Meaningful Machines LLC
• Original Assignee: Meaningful Machines LLC
• Inventors: ABIR, Eli
• Granted Patent: US 8,880,392 B2
• Time in Patent Office: Days
• 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 application 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 method for acquiring a knowledge base of associated ideas comprising the steps of:

providing a pair of documents representing the same content in two different languages, wherein the first of said pair of documents is expressed in a first language, and the second of said pair of documents is expressed in a second language;

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

analyzing said first of said pair of documents to identify all occurrences of said query in said first of said pair of documents;

selecting a plurality of ranges of words in said second of said pair of documents, wherein said selected ranges correspond to each of said identified occurrences of said query in said first of said pair of documents based on user defined criteria;

calculating the frequency of words and word strings contained in said selected ranges based on occurrences of all unique words and word strings;

returning a list of occurrences of all unique words and word strings if said unique words and word strings occur in more than one of the selected ranges using said calculated frequency; and

ranking said returned list of occurrences based on said calculation of the frequency of words and word strings.

2. The method of claim 1, wherein said calculating step omits the occurrence of a word or word string if the word or word string is a subset of a longer word string that occurs in more than one of the selected ranges.

3. A method for acquiring a knowledge base of associated ideas comprising the steps of:

a. providing a plurality of document pairs where each pair represents the same content in a first language and a second language;

b. receiving a query to be analyzed, wherein said query is expressed in said first language, and wherein said query consists of a word or word string;

c. analyzing all first language documents in said plurality of document pairs to identify all occurrences of said query;

d. selecting a plurality of ranges of words in all second language documents in said plurality of document pairs that corresponds to each of said identified occurrences of said query in said first language document, based on user defined criteria;

e. calculating the frequency of words and word strings contained in said selected ranges based on occurrences of all unique words and word strings;

f. returning a list of occurrences of all unique words and word strings if said unique words and word strings occur in more than one of the selected ranges using said calculated frequency; and

g. ranking said returned list of occurrences based on said calculation of the frequency of words and word strings.

4. The method of claim 3, wherein said calculating step omits the occurrence of a word or word string if the word or word string is a subset of a longer word string that occurs in more than one of the selected ranges.

5. 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 pair of documents representing the same idea in two different languages, wherein the first of said pair of documents is expressed in a first language, and the second of said pair of documents is expressed in a second language;

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

analyzing said first of said pair of documents to identify all occurrences of said query in said first of said pair of documents;

selecting a plurality of ranges of words in said second of said pair of documents, wherein said selected ranges correspond to each of said identified occurrences of said query in said first of said pair of documents based on user defined criteria;

calculating the frequency of words and word strings contained in said selected ranges based on occurrences of all unique words and word strings; and

returning a list of occurrences of all unique words and word strings if said unique words and word strings occur in more than one of the selected ranges using said calculated frequency; and

ranking said returned list of occurrences based on said calculation of the frequency of words and word strings.

6. The computer device of claim 5, wherein said calculating step omits the occurrence of a word or word string if the word or word string is a subset of a longer word string that occurs in more than one of the selected ranges.

7. 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:

a. providing a plurality of document pairs where each pair represents the same content in a first language and a second language;

b. receiving a query to be analyzed, wherein said query is expressed in said first language, and wherein said query consists of a word or word string;

c. analyzing all first language documents in said plurality of document pairs to identify all occurrences of said query;

d. selecting a plurality of ranges of words in all second language documents in said plurality of document pairs that corresponds to each of said identified occurrences of said query in said first language document, based on user defined criteria;

e. calculating the frequency of words and word strings contained in said selected ranges based on occurrences of all unique words and word strings;

f. returning a list of occurrences of all unique words and word strings if said unique words and word strings occur in more than one of the selected ranges using said calculated frequency; and

g. ranking said returned list of occurrences based on said calculation of the frequency of words and word strings.

8. The computer device of claim 7, wherein said calculating step omits the occurrence of a word or word string if the word or word string is a subset of a longer word string that occurs in more than one of the selected ranges.

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

providing a pair of documents representing the same idea in two different languages, wherein the first of said pair of documents is expressed in a first language, and the second of said pair of documents is expressed in a second language;

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

analyzing said first of said pair of documents to identify all occurrences of said query in said first of said pair of documents;

selecting a plurality of ranges of words in said second of said pair of documents, wherein said selected ranges correspond to each of said identified occurrences of said query in said first of said pair of documents based on user defined criteria;

calculating the frequency of words and word strings contained in said selected ranges based on occurrences of all unique words and word strings;

returning a list of occurrences of all unique words and word strings if said unique words and word strings occur in more than one of the selected ranges using said calculated frequency; and

ranking said returned list of occurrences based on said calculation of the frequency of words and word strings.

10. The computer medium of claim 9, wherein said calculating step omits the occurrence of a word or word string if the word or word string is a subset of a longer word string that occurs in more than one of the selected ranges.

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

a. providing a plurality of document pairs where each pair represents the same content in a first language and a second language;

b. receiving a query to be analyzed, wherein said query is expressed in said first language, and wherein said query consists of a word or word string;

c. analyzing all first language documents in said plurality of document pairs to identify all occurrences of said query;

d. selecting a plurality of ranges of words in all second language documents in said plurality of document pairs that corresponds to each of said identified occurrences of said query in said first language document, based on user defined criteria;

e. calculating the frequency of words and word strings contained in said selected ranges based on occurrences of all unique words and word strings;

f. returning a list of occurrences of all unique words and word strings if said unique words and word strings occur in more than one of the selected ranges using said calculated frequency; and

g. ranking said returned list of occurrences based on said calculation of the frequency of words and word strings.

12. The computer medium of claim 11, wherein said calculating step omits the occurrence of a word or word string if the word or word string is a subset of a longer word string that occurs in more than one of the selected ranges.