SYSTEMS AND METHODS FOR AN AUTONOMOUS AVATAR DRIVER

• US 20080221892A1
• Filed: 12/19/2007
• Published: 09/11/2008
• Est. Priority Date: 03/06/2007
• Status: Abandoned Application

• Current Assignee: Botanic Technologies, Inc., Ogg Trading, LLC (OTC Exchange Network, Inc.)
• Original Assignee: Botanic Technologies, Inc.
• Inventors: Meadows, Mark Stephen, Leibert, Florian Thomas, Nathan, Paco Xander, Mallis, Jan Susan, Cox, Cathi Joann
• Application Number:
  US11/960,507
• Publication Number:
  US 20080221892A1
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/263 Language identification
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06T 13/00 Animation

Abstract

The autonomous avatar driver is useful in association with language sources. A sourcer may receive dialog from the language source. It may also, in some embodiments, receive external data from data sources. A segmentor may convert characters, represent particles and split dialog. A parser may then apply a link grammar, analyze grammatical mood, tag the dialog and prune dialog variants. A semantic engine may lookup token frames, generate semantic lexicons and semantic networks, and resolve ambiguous co-references. An analytics engine may filter common words from dialog, analyze N-grams, count lemmatized words, and analyze nodes. A pragmatics analyzer may resolve slang, generate knowledge templates, group proper nouns and estimate affect of dialog. A recommender may generate tag clouds, cluster the language sources into neighborhoods, recommend social networking to individuals and businesses, and generate contextual advertising. Lastly, a response generator may generate responses for the autonomous avatar using the analyzed dialog. The response generator may also incorporate the generated recommendations.

Claims

1. A computer implemented method for driving an autonomous avatar, useful in association with at least on language source, the method comprising:

receiving dialog from the language source;

segmenting the dialog;

parsing the segmented dialog;

analyzing the parsed dialog for semantics;

analyzing the semantically analyzed dialog for analytics;

analyzing the analytically analyzed dialog for pragmatics;

generating recommendations from the pragmatically analyzed dialog; and

generating responses for the autonomous avatar using the pragmatically analyzed dialog.

2. The computer implemented method, as recited in claim 1, further comprising receiving external data from at least one data source.

3. The computer implemented method, as recited in claim 2, wherein the segmenting the dialog includes at least one of performing particle representation, converting characters and splitting dialog.

4. The computer implemented method, as recited in claim 2, wherein the parsing the segmented dialog includes at least one of linking grammar, generating grammatical mood, tagging the dialog and pruning variants.

5. The computer implemented method, as recited in claim 2, wherein the analyzing the parsed dialog for semantics includes at least one of lookup of token frame, generation of semantic lexicons, generation of semantic networks and resolving co-reference ambiguity.

6. The computer implemented method, as recited in claim 2, wherein the analyzing the semantically analyzed dialog for analytics includes at least one of filtering for common words, generating token frame statistics and analyzing N-grams for word popularity.

7. The computer implemented method, as recited in claim 6, wherein the generating token frame statistics includes at least one of counting lemmatized words, and nodal analysis.

8. The computer implemented method, as recited in claim 2, wherein the analyzing the analytically analyzed dialog for pragmatics includes at least one of resolving slang, generating knowledge templates, grouping proper nouns and estimating affect.

9. The computer implemented method, as recited in claim 2, wherein the generating recommendations from the pragmatically analyzed dialog includes at least one of generating aggregate tag clouds, clustering the language sources into neighborhoods, recommending social networking, and generating contextual advertising.

10. The computer implemented method, as recited in claim 2, wherein the generating responses for the autonomous avatar also includes incorporating the generated recommendations.

11. An automated avatar driver system useful in association with an avatar and at least one language source, the automated avatar driver system comprising:

a sourcer configured to receive dialog from the language source;

a segmentor configured to segment the dialog;

a parser configured to parse the segmented dialog;

a semantic engine configured to analyze the parsed dialog for semantics;

an analytics engine configured to analyze the semantically analyzed dialog for analytics;

a pragmatics analyzer configured to analyze the analytically analyzed dialog for pragmatics;

a recommender configured to generate recommendations from the pragmatically analyzed dialog; and

a response generator configured to generate responses for the autonomous avatar using the pragmatically analyzed dialog.

12. The automated avatar driver system of claim 11, wherein the sourcer is further configured to receive external data from at least one data source.

13. The automated avatar driver system of claim 12, wherein the segmentor includes at least one of a particle representor configured to perform particle representation, a character converter configured to convert characters and a splitter configured to split dialog.

14. The automated avatar driver system of claim 12, wherein the parser includes at least one of a linker configured to link grammar, a grammatical mood analyzer configured to generate grammatical mood, a tagger configured to tag the dialog and a variant pruner configured to prune variants of the dialog.

15. The automated avatar driver system of claim 12, wherein the semantics engine includes at least one of a token framer configured to lookup token frames, a lemmatizer configured to generate semantic lexicons, a semantic network generator configured to generate semantic networks and a co-reference resolver configured to resolve co-reference ambiguity.

16. The automated avatar driver system of claim 12, wherein the analytics engine includes at least one of a common word filter configured to filter dialog for common words, a token frame statistics engine, and an N-gram analyzer configured to analyze N-grams for word popularity.

17. The automated avatar driver system of claim 16, wherein the token frame statistics engine configured to count lemmatized words, and perform nodal analysis.

18. The automated avatar driver system of claim 12, wherein the pragmatics analyzer includes at least one of a slang resolver configured to resolve slang, a knowledge template resolver configured to generate knowledge templates, a proper noun grouper configured to group proper nouns and an affect estimator configured to estimate affect of the dialog.

19. The automated avatar driver system of claim 12, wherein the recommender includes at least one of a cloud aggregator configured to generate aggregate tag clouds, a hood cluster or configured to cluster the language sources into neighborhoods, a social network recommender configured to recommend social networking, and a contextual advertising generator configured to generate contextual advertising.

20. The automated avatar driver system of claim 12, wherein the response generator also includes incorporating the generated recommendations from the recommender.