Knowledge system method and apparatus
First Claim
Patent Images
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:
- receiving content in the form of words in a first language, wherein said content is parsed into two segments of content in a first language, and wherein said two segments of parsed content contain identical words such that said two segments have overlapping content;
translating said first of said segments of content in a first language to a second language to create a third segment of content, expressed in said second language;
translating said second of said segments of content in a first language to said second language to create a fourth segment of content, expressed in said second language;
analyzing said third segment and said fourth segment to determine if said third segment and said fourth segment have overlapping content; and
creating, if said third segment and said fourth segment have overlapping content, a single second language word string comprised of the merger of said third and said fourth segments, eliminating duplicative words; and
associating said merged third and fourth segments with said received content in the form of words in a first language.
0 Assignments
0 Petitions
Accused Products
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.
66 Citations
8 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:
-
receiving content in the form of words in a first language, wherein said content is parsed into two segments of content in a first language, and wherein said two segments of parsed content contain identical words such that said two segments have overlapping content; translating said first of said segments of content in a first language to a second language to create a third segment of content, expressed in said second language; translating said second of said segments of content in a first language to said second language to create a fourth segment of content, expressed in said second language; analyzing said third segment and said fourth segment to determine if said third segment and said fourth segment have overlapping content; and creating, if said third segment and said fourth segment have overlapping content, a single second language word string comprised of the merger of said third and said fourth segments, eliminating duplicative words; and associating said merged third and fourth segments with said received content in the form of words in a first language. - View Dependent Claims (2)
-
-
3. A non-transitory computer readable storage medium having stored thereon a program executable by a computer processor for performing the steps of:
-
receiving content in the form of words in a first language, wherein said content is parsed into two segments of content in a first language, and wherein said two segments of parsed content contain identical words such that said two segments have overlapping content; translating said first of said segments of content in a first language to a second language to create a third segment of content, expressed in said second language; translating said second of said segments of content in a first language to said second language to create a fourth segment of content, expressed in said second language; analyzing said third segment and said fourth segment to determine if said third segment and said fourth segment have overlapping content; and creating, if said third segment and said fourth segment have overlapping content, a single second language word string comprised of the merger of said third and said fourth segments, eliminating duplicative words; and associating said merged third and fourth segments with said received content in the form of words in a first language. - View Dependent Claims (4)
-
-
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:
-
a. providing content comprising data segments in a first language associated with data segments in a second language in a database; b. receiving a document to be translated in a first language; c. selecting from the document to be translated in a first language a first delimited data segment that begins the document; d. retrieving from the database a segment in the second language associated with the selected first delimited data segment in the first language; e. selecting at least a second delimited segment in the first language from the document that has one or more overlapping portions with the first delimited data segment in the first language; f. retrieving from the database a second segment in the second language associated with the selected second delimited segment in the first language that has an overlapping portion with the segment in the second language; g. combining the two segments in the second language, and merging the overlapping portions;
eliminating duplicate words;h. creating a first language merged segment from said first language first delimited data segment and said selected second delimited segment eliminating duplicative words; and i. associating the merged second language segment with the merged first language segments. - View Dependent Claims (6)
-
-
7. A non-transitory computer readable storage medium having stored thereon a program executable by a computer processor for performing the steps of:
-
a. providing content comprising data segments in a first language associated with data segments in a second language in a database; b. receiving a document to be translated in a first language; c. selecting from the document to be translated in a first language a first delimited data segment that begins the document; d. retrieving from the database a segment in the second language associated with the selected first delimited data segment in the first language; e. selecting at least a second delimited segment in the first language from the document that has one or more overlapping portions with the first delimited data segment in the first language; f. retrieving from the database a second segment in the second language associated with the selected second delimited segment in the first language that has an overlapping portion with the segment in the second language; g. combining the two segments in the second language, and merging the overlapping portions;
eliminating duplicative words;h. creating a first language merged segment from said first language first delimited data segment and said selected second delimited segment eliminating duplicative words; and i. associating the merged second language segment with the merged first language segments. - View Dependent Claims (8)
-
Specification