Unusual score generators for a neuro-linguistic behavorial recognition system
Techniques are disclosed for generating anomaly scores for a neuro-linguistic model of input data obtained from one or more sources. According to one embodiment, generating anomaly scores includes receiving a stream of symbols generated from an ordered stream of normalized vectors generated from input data received from one or more sensor devices during a first time period. Upon receiving the stream of symbols, generating a set of words based on an occurrence of groups of symbols from the stream of symbols, determining a number of previous occurrences of a first word of the set of words, determining a number of previous occurrences of words of a same length as the first word, and determining a first anomaly score based on the number of previous occurrences of the first word and the number of previous occurrences of words of the same length as the first word.
1. A processor-implemented method, comprising:
receiving, at a processor, a plurality of words generated based on observations of a lexical analyzer;
generating, via the processor:
a syntax based on at least one word from the plurality of words, and
at least one alert directive associated with the at least one word from the plurality of words, the at least one alert directive encoding the at least one word as a behavioral alert based rule;
comparing the syntax to a plurality of syntaxes stored in a proto-perceptual memory to identify an unusual syntax score; and
generating an alert based on the at least one alert directive and the unusual syntax score.
2. The processor-implemented method of claim 1 , further comprising:
receiving, at the processor, an update from the proto-perceptual memory;
the generating the syntax further based on the update.
3. The processor-implemented method of claim 2 , wherein the update includes an update to a feature weight for at least one feature of the at least one word.
4. The processor-implemented method of claim 2 , wherein the update includes an update to a combined word list including the plurality of words.
5. The processor-implemented method of claim 2 , wherein the update includes an update to a combined word frequency list.
6. The processor-implemented method of claim 1 , further comprising:
iteratively updating the proto-perceptual memory; and
generating, via the processor, a plurality of further syntaxes based on the iterative updates to the proto-perceptual memory.
7. The processor-implemented method of claim 1 , wherein the unusual syntax score includes a syntactic measure of the syntax and a semantic measure of the syntax.
8. The processor-implemented method of claim 1 , wherein the output includes a connected graph including:
a plurality of nodes, each node from the plurality of nodes representing a word from the plurality of words, and
a plurality of edges, each edge from the plurality edges representing a relationship between a pair of words from the plurality of words.
9. The processor-implemented method of claim 1 , wherein each alert directive from the at least one alert directive includes an identifier, an alert pointer, match criteria, and an epilog.
10. A processor-implemented method, comprising:
observing, via a processor, a plurality of behaviors within a monitored system;
detecting, via the processor and during a first time period, that a behavior from the plurality of behaviors is abnormal;
generating an alert in response to detecting the behavior from the plurality of behaviors during the first time period;
receiving, at the processor and during a second time period after the first time period, a representation of user-defined match criteria associated with the behavior from the plurality of behaviors;
generating, via the processor, an alert directive based on the user-defined match criteria during the second time period;
detecting, via the processor and during a third time period after the second time period, the behavior from the plurality of behaviors; and
not generating an alert in response to detecting the behavior from the plurality of behaviors during the third time period, based on the alert directive.
11. The processor-implemented method of claim 10 , wherein the alert directive includes an identifier, an alert pointer, match criteria, and an epilog.
12. The processor-implemented method of claim 10 , wherein the detecting that the behavior from the plurality of behaviors is abnormal is based on a learning-based object classification type.
13. The processor-implemented method of claim 10 , wherein the generating the alert in response to detecting the behavior from the plurality of behaviors during the first time period is based on a learning-based object classification type.
14. The processor-implemented method of claim 10 , wherein the user-defined match criteria includes a tolerance range.
15. The processor-implemented method of claim 10 , wherein the detecting that the behavior from the plurality of behaviors is abnormal is based on neuro-linguistic data generated via perceptual associative learning.
16. A processor-implemented method, comprising:
observing, via a processor, a plurality of behaviors within a monitored system;
detecting, via the processor and during a first time period, that a behavior from the plurality of behaviors is normal;
not generating an alert in response to detecting the behavior from the plurality of behaviors during the first time period;
receiving, at the processor and during a second time period after the first time period, a representation of user-defined match criteria associated with the behavior from the plurality of behaviors;
generating, via the processor, an alert directive based on the user-defined match criteria;
detecting, via the processor and during a third time period after the second time period, the behavior from the plurality of behaviors; and
generating an alert in response to the detection of the behavior from the plurality of behaviors during the third time period, based on the alert directive.
17. The processor-implemented method of claim 16 , wherein the alert directive includes an identifier, an alert pointer, match criteria, and an epilog.
18. The processor-implemented method of claim 16 , wherein the detecting that the behavior from the plurality of behaviors is normal is based on a learning-based classification.
19. The processor-implemented method of claim 16 , wherein the user-defined match criteria includes a tolerance range.
20. The processor-implemented method of claim 16 , wherein the user-defined match criteria includes a representation of a location depicted within a video.