Cognitive neuro-linguistic behavior recognition system for multi-sensor data fusion

• US 9,639,521 B2
• Filed: 08/11/2014
• Issued: 05/02/2017
• Est. Priority Date: 08/09/2013
• Status: Active Grant

• Current Assignee: Intellective Ai, Inc.
• Original Assignee: Omni AI, Inc.
• Inventors: Seow, Ming-Jung, Cobb, Wesley Kenneth, Xu, Gang, Yang, Tao, Poffenberger, Aaron, Risinger, Lon W., Saitwal, Kishor Adinath, Solum, David M., Urech, Dennis G., Morgan, Charles Richard, Yantosca, Michael S., Hemsath, Alex David, Nguyen, Duy Trong
• Primary Examiner(s): Hang, Vu B
• Application Number:
  US14/457,082
• Publication Number:
  US 20150046155A1
• Time in Patent Office: 995 Days
• Field of Search: 704 10, 704 4, 704 9
• CPC Class Codes: G06F 40/226 Validation
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/0409 Adaptive resonance theory [ART] networks
• CPC Class Codes: G06N 3/042 Knowledge-based neural networks; Logical representations of neural networks
• CPC Class Codes: G06N 3/088 Non-supervised learning, e.g. competitive learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: H04L 63/1408 by monitoring network traffic monitoring network traffic per se H04L43/00
• CPC Class Codes: H04L 63/1425 Traffic logging, e.g. anomaly detection

Abstract

Embodiments presented herein describe techniques for generating a linguistic model of input data obtained from a data source (e.g., a video camera). According to one embodiment of the present disclosure, a sequence of symbols is generated based on an ordered stream of normalized vectors generated from the input data. A dictionary of words is generated from combinations of the ordered sequence of symbols based on a frequency at which combinations of symbols appear in the ordered sequence of symbols. A plurality of phrases is generated based an ordered sequence of words from the dictionary observed in the ordered sequence of symbols based on a frequency by which combinations of words in ordered sequence of words appear relative to one another.

Claims

1. A method for generating a neuro-linguistic model of input data obtained from one or more data sources, the method comprising:

generating, via a processor, a sequence of symbols based on an ordered stream of normalized vectors generated from the input data;

generating a dictionary of words from combinations of the ordered sequence of symbols based on a frequency at which combinations of symbols appear in the ordered sequence of symbols; and

generating a plurality of phrases based an ordered sequence of words from the dictionary observed in the ordered sequence of symbols based on a frequency by which combinations of words in ordered sequence of words appear relative to one another.

2. The method of claim 1, further comprising, determining, for at least one symbol, word, or phrase, an unusualness score based on a frequency of the at least one symbol, word, or phrase, as generated from the ordered stream of normalized vectors generated from the input data.

3. The method of claim 1, further comprising, identifying anomalous behavior present in subsequent symbols, words, and phrases generated from the ordered stream of normalized vectors generated from the input data, based on a comparison with the sequence of symbols, generated dictionary and generated plurality of words.

4. The method of claim 1, wherein words included in the dictionary include a set of words having a most statistical relevance relative to a complete set of words generated from combinations of the ordered sequence of symbols.

5. The method of claim 1, wherein each normalized vector represents an element of the input data in a range of 0 to 1, inclusive.

6. The method of claim 1, wherein one of the data sources is a sequence of video frames.

7. The method of claim 1, wherein generating the dictionary comprises building a dictionary of words up to a maximum length of symbols.

8. A non-transitory computer-readable storage medium storing instructions, which, when executed on a processor, performs an operation for generating a linguistic model of input data obtained from a data source, the operation comprising:

generating, via a processor, a sequence of symbols based on an ordered stream of normalized vectors generated from the input data;

generating a dictionary of words from combinations of the ordered sequence of symbols based on a frequency at which combinations of symbols appear in the ordered sequence of symbols; and

generating a plurality of phrases based an ordered sequence of words from the dictionary observed in the ordered sequence of symbols based on a frequency by which combinations of words in ordered sequence of words appear relative to one another.

9. The non-transitory computer-readable storage medium of claim 8, wherein the operation further comprises, determining, for at least one symbol, word, or phrase, an unusualness score based on a frequency of the at least one symbol, word, or phrase, as generated from the ordered stream of normalized vectors generated from the input data.

10. The non-transitory computer-readable storage medium of claim 8, wherein the operation further comprises, identifying anomalous behavior present in subsequent symbols, words, and phrases generated from the ordered stream of normalized vectors generated from the input data, based on a comparison with the sequence of symbols, generated dictionary and generated plurality of words.

11. The non-transitory computer-readable storage medium of claim 8, wherein the operation further comprises, wherein words included in the dictionary include a set of words having a most statistical relevance relative to a complete set of words generated from combinations of the ordered sequence of symbols.

12. The non-transitory computer-readable storage medium of claim 8, wherein each normalized vector represents an element of the input data in a range of 0 to 1, inclusive.

13. The non-transitory computer-readable storage medium of claim 8, wherein one of the data sources is a sequence of video frames.

14. The non-transitory computer-readable storage medium of claim 8, wherein generating the dictionary comprises building a dictionary of words up to a maximum length of symbols.

15. A system, comprising:

a processor; and

a memory storing one or more application programs configured to perform an operation for generating a linguistic model of input data obtained from a data source, the operation comprising;

generating a sequence of symbols based on an ordered stream of normalized vectors generated from the input data,

generating a dictionary of words from combinations of the ordered sequence of symbols based on a frequency at which combinations of symbols appear in the ordered sequence of symbols, and

generating a plurality of phrases based an ordered sequence of words from the dictionary observed in the ordered sequence of symbols based on a frequency by which combinations of words in ordered sequence of words appear relative to one another.

16. The system of claim 15, wherein the operation further comprises, determining, for at least one symbol, word, or phrase, an unusualness score based on a frequency of the at least one symbol, word, or phrase, as generated from the ordered stream of normalized vectors generated from the input data.

17. The system of claim 15, wherein the operation further comprises, identifying anomalous behavior present in subsequent symbols, words, and phrases generated from the ordered stream of normalized vectors generated from the input data, based on a comparison with the sequence of symbols, generated dictionary and generated plurality of words.

18. The system of claim 15, wherein the operation further comprises, wherein words included in the dictionary include a set of words having a most statistical relevance relative to a complete set of words generated from combinations of the ordered sequence of symbols.

19. The system of claim 15, wherein each normalized vector represents an element of the input data in a range of 0 to 1, inclusive.

20. The system of claim 15, wherein one of the data sources is a sequence of video frames.

21. The system of claim 15, wherein generating the dictionary comprises building a dictionary of words up to a maximum length of symbols.