Enhancement of multi-lingual business indicia through curation and synthesis of transliteration, translation and graphemic insight

• US 9,489,351 B2
• Filed: 03/14/2014
• Issued: 11/08/2016
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Dun & Bradstreet Corp., DUN & Bradstreet Incorporated (Dun & Bradstreet Corp.), Hoover's Incorporated (Dun & Bradstreet Holdings, Inc.)
• Original Assignee: Dun & Bradstreet Corp.
• Inventors: Scriffignano, Anthony J., Klein, Michael, Carolan, Sean, Matthews, Warwick
• Primary Examiner(s): Godbold, Douglas
• Application Number:
  US14/213,700
• Publication Number:
  US 20140278350A1
• Time in Patent Office: 970 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/129 Handling non-Latin characters, e.g. kana-to-kanji conversion
• CPC Class Codes: G06F 40/55 Rule-based translation

Abstract

There is provided a method that includes parsing a string of characters into its graphemes, and generating a pattern of characters that represents an abstraction of the graphemes. There is also provided a system that performs the method, and a storage device that contains instructions for controlling a processor to perform the method.

Claims

1. A method comprising:

receiving input data that includes (a) a string of characters in a first language, and (b) semantic contextual data concerning a source of said input data;

parsing said string of characters into its graphemes;

generating a pattern of characters that represents an abstraction of said graphemes;

analyzing said semantic contextual data and said pattern of characters in accordance with rules, to yield a potential interlingual transformation of said pattern of characters;

transforming said string of characters from said first language into a second language in accordance with said potential interlingual transformation, thus yielding a transformation;

analyzing performance indicia about said transformation; and

updating said rules based on said performance indicia.

2. The method of claim 1, wherein said pattern of characters includes a group of characters that corresponds to a grapheme in said graphemes, and that is mapped to said source.

3. The method of claim 2, further comprising retrieving from said source, information about said grapheme.

4. The method of claim 1,

wherein said pattern of characters includes a sequence of a first group of characters and a second group of characters,

wherein said first group of characters corresponds to a first grapheme in said graphemes,

wherein said second group of characters corresponds to a second grapheme in said graphemes, and

wherein said method further comprises:

selecting, based on said sequence, a process from among a plurality of processes; and

executing said process on said string of characters.

5. The method of claim 4, wherein said process yields a combination of translation and interlingual transformation of said string of characters.

6. The method of claim 1,

wherein said analyzing said semantic contextual data and said pattern of characters is also performed in accordance with preferences and attributions, and yields (a) candidate meanings and candidate interlingual disposition strategies of said pattern of characters, and (b) information to inform a future iteration of said method, and

wherein said method further includes, after said analyzing said semantic contextual data and said pattern of characters, and before said transforming:

selecting an optimal interlingual disposition strategy for constituent parts of said pattern of characters having regard to (a) said analyzing of said semantic contextual data and said pattern of characters, and (b) said rules, preferences and attributions, and being informed by learning from a prior iteration of said method.

7. A system comprising:

a processor; and

a memory that is communicatively coupled to said processor, and that contains instructions that are readable by said processor to cause said processor to perform actions of;

receiving input data that includes (a) a string of characters in a first language, and (b) semantic contextual data concerning a source of said input data;

parsing said string of characters into its graphemes;

generating a pattern of characters that represents an abstraction of said graphemes;

analyzing said semantic contextual data and said pattern of characters in accordance with rules, to yield a potential interlingual transformation of said pattern of characters;

transforming said string of characters from said first language into a second language in accordance with said potential interlingual transformation, thus yielding a transformation;

analyzing performance indicia about said transformation; and

updating said rules based on said performance indicia.

8. The system of claim 7, wherein said pattern of characters includes a group of characters that corresponds to a grapheme in said graphemes, and that is mapped to said source.

9. The system of claim 8, wherein said instructions also cause said processor to perform an action of:

retrieving from said source, information about said grapheme.

10. The system of claim 7,

wherein said pattern of characters includes a sequence of a first group of characters and a second group of characters,

wherein said first group of characters corresponds to a first grapheme in said graphemes,

wherein said second group of characters corresponds to a second grapheme in said graphemes, and

wherein said instructions also cause said processor to perform actions of:

selecting, based on said sequence, a process from among a plurality of processes; and

executing said process on said string of characters.

11. The system of claim 10, wherein said process yields a combination of translation and interlingual transformation of said string of characters.

12. The system of claim 7,

wherein said analyzing said semantic contextual data and said pattern of characters is also performed in accordance with preferences and attributions, and yields (a) candidate meanings and candidate interlingual disposition strategies of said pattern of characters, and (b) information to inform a future iteration of said method, and

wherein said instructions also cause said processor to perform actions of, after said analyzing said semantic contextual data and said pattern of characters, and before said transforming:

selecting an optimal interlingual disposition strategy for constituent parts of said pattern of characters having regard to (a) said analyzing of said semantic contextual data and said pattern of characters, and (b) said rules, preferences and attributions, and being informed by learning from a prior iteration of said method.

13. A storage device comprising instructions that are readable by a processor to cause said processor to perform actions of:

receiving input data that includes (a) a string of characters in a first language, and (b) semantic contextual data concerning a source of said input data;

parsing said string of characters into its graphemes;

generating a pattern of characters that represents an abstraction of said graphemes;

analyzing said semantic contextual data and said pattern of characters in accordance with rules, to yield a potential interlingual transformation of said pattern of characters;

transforming said string of characters from said first language into a second language in accordance with said potential interlingual transformation, thus yielding a transformation;

analyzing performance indicia about said transformation; and

updating said rules based on said performance indicia.

14. The storage device of claim 13, wherein said pattern of characters includes a group of characters that corresponds to a grapheme in said graphemes, and that is mapped to said source.

15. The storage device of claim 14, wherein said instructions also cause said processor to perform an action of:

retrieving from said source, information about said grapheme.

16. The storage device of claim 13,

wherein said pattern of characters includes a sequence of a first group of characters and a second group of characters,

wherein said first group of characters corresponds to a first grapheme in said graphemes,

wherein said second group of characters corresponds to a second grapheme in said graphemes, and

wherein said instructions also cause said processor to perform actions of:

selecting, based on said sequence, a process from among a plurality of processes; and

executing said process on said string of characters.

17. The storage device of claim 16, wherein said process yields a combination of translation and interlingual transformation of said string of characters.

18. The storage device of claim 13,

wherein said analyzing said semantic contextual data and said pattern of characters is also performed in accordance with preferences and attributions, and yields (a) candidate meanings and candidate interlingual disposition strategies of said pattern of characters, and (b) information to inform a future iteration of said method, and

wherein said instructions also cause said processor to perform actions of, after said analyzing said semantic contextual data and said pattern of characters, and before said transforming:

selecting an optimal interlingual disposition strategy for constituent parts of said pattern of characters having regard to (a) said analyzing of said semantic contextual data and said pattern of characters, and (b) said rules, preferences and attributions, and being informed by learning from a prior iteration of said method.