Perceptual associative memory for a neuro-linguistic behavior recognition system

Abstract

Techniques are disclosed for generating a syntax for a neuro-linguistic model of input data obtained from one or more sources. A stream of words of a dictionary built from a sequence of symbols are received. The symbols are generated from an ordered stream of normalized vectors generated from input data. Statistics for combinations of words co-occurring in the stream are evaluated. The statistics includes a frequency upon which the combinations of words co-occur. A model of combinations of words based on the evaluated statistics is updated. The model identifies statistically relevant words. A connected graph is generated. Each node in the connected graph represents one of the words in the stream. Edges connecting the nodes represent a probabilistic relationship between words in the stream. Phrases are identified based on the connected graph.

1 . (canceled) 
     
     
         2 . A method, comprising:
 receiving a plurality of video frames from a video source, the plurality of video frames including a representation of an object;   normalizing, via at least one processor, data in each video frame from the plurality of video frames to obtain normalized data for the plurality of video frames;   generating, via the at least one processor, a syntax for a neuro-linguistic model, the syntax including a stable model of phrases;   identifying, via the at least one processor, instances of at least one machine-readable phrase from the stable model of phrases and based on a connected graph;   calculating, via the at least one processor, an unusualness score for an observation of a first machine-readable phrase from the at least one machine-readable phrase identified in the connected graph; and   publishing, via the at least one processor, an alert associated with the observation of the first machine-readable phrase, the alert indicating an anomaly in the behavior of the object.   
     
     
         3 . The computer-implemented method of  claim 2 , wherein generating the syntax includes:
 generating, via the at least one processor, a plurality of machine-readable symbols from the normalized data, each machine-readable symbol from the plurality of machine-readable symbols being associated with a distinct cluster of the normalized data, and   building a dictionary of machine-readable words based on an observed sequence of the plurality of machine-readable symbols.   
     
     
         4 . The computer-implemented method of  claim 2 , wherein generating the syntax includes:
 evaluating, via the at least one processor, statistics for a plurality of combinations of machine-readable words co-occurring in a stream of machine-readable words, the statistics including a frequency at which combinations of machine-readable words from the plurality of combinations of machine-readable words co-occur; and   updating, via the at least one processor, a model of combinations of machine-readable words based on the evaluated statistics, the model identifying statistically relevant observations of co-occurring machine-readable words.   
     
     
         5 . The computer-implemented method of  claim 2 , wherein generating the syntax includes generating, via the at least one processor, a connected graph having a plurality of nodes and a plurality of edges, each node from the plurality of nodes representing one machine-readable word in a stream of machine-readable words, and each edge from the plurality of edges connecting the nodes representing a probabilistic measure of co-occurrence of pairs of statistically relevant words in the stream of machine-readable words. 
     
     
         6 . The computer-implemented method of  claim 2 , wherein generating the syntax includes generating a connected graph, via the at least one processor, the connected graph including a plurality of nodes and a plurality of edges, each edge from the plurality of edges weighted based on a statistical significance score between each pair of nodes from the plurality of nodes. 
     
     
         7 . The computer-implemented method of  claim 2 , further comprising:
 receiving a stream of machine-readable words; and   updating statistics of the co-occurring words based on the stream of machine-readable words.   
     
     
         8 . The computer-implemented method of  claim 2 , wherein generating the syntax includes generating a dictionary of machine-readable words based on an observed-sequence of the machine-readable symbols, the method further comprising at least one of:
 decreasing a statistical significance score of co-occurring machine-readable words, from the dictionary of machine-readable words, that are less frequently observed over time; or   increasing a statistical significance score of co-occurring machine-readable words, from the dictionary of machine-readable words, that are more frequently observed over time.   
     
     
         9 . A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to:
 receive a plurality of video frames from a video source, the plurality of video frames including a representation of an object;   normalize, via at least one processor, data in each video frame from the received plurality of video frames to obtain normalized data for the plurality of video frames;   generate, via the at least one processor, a syntax for a neuro-linguistic model, the syntax including a stable model of phrases;   identify, via the at least one processor, instances of at least one machine-readable phrase from the stable model of phrases and based on a connected graph;   calculate, via the at least one processor, an unusualness score for an observation of a first machine-readable phrase from the at least one machine-readable phrase identified in the connected graph; and   publish, via the at least one processor, an alert associated with the observation of the first machine-readable phrase, the alert indicating an anomaly in the behavior of the object.   
     
     
         10 . The non-transitory computer-readable storage medium of  claim 9 , wherein the instructions to generate the syntax include instructions to:
 generate a plurality of machine-readable symbols from the normalized data, each machine-readable symbol from the plurality of machine-readable symbols being associated with a distinct cluster of the normalized data, and   build a dictionary of machine-readable words based on an observed sequence of the plurality of machine-readable symbols.   
     
     
         11 . The non-transitory computer-readable storage medium of  claim 9 , wherein the instructions to generate the syntax include instructions to:
 evaluate statistics for a plurality of combinations of machine-readable words co-occurring in a stream of machine-readable words, the statistics including a frequency at which combinations of machine-readable words from the plurality of combinations of machine-readable words co-occur; and   update a model of combinations of machine-readable words based on the evaluated statistics, the model identifying statistically relevant observations of co-occurring machine-readable words.   
     
     
         12 . The non-transitory computer-readable storage medium of  claim 9 , wherein the instructions to generate the syntax include instructions to generate a connected graph having a plurality of nodes and a plurality of edges, each node from the plurality of nodes representing one machine-readable word in a stream of machine-readable words, and each edge from the plurality of edges connecting the nodes representing a probabilistic measure of co-occurrence of pairs of statistically relevant words in the stream of machine-readable words. 
     
     
         13 . The non-transitory computer-readable storage medium of  claim 9 , wherein the instructions to generate the syntax include instructions to generate a connected graph, the connected graph including a plurality of nodes and a plurality of edges, each edge from the plurality of edges weighted based on a statistical significance score between each pair of nodes from the plurality of nodes. 
     
     
         14 . The non-transitory computer-readable storage medium of  claim 9 , further storing instructions that, when executed by the processor, cause the processor to:
 receive a stream of machine-readable words; and   update statistics of the co-occurring words based on the stream of machine-readable words.   
     
     
         15 . The non-transitory computer-readable storage medium of  claim 9 , wherein the instructions to generate the syntax include instructions to generate a dictionary of machine-readable words based on an observed-sequence of the machine-readable symbols, the non-transitory computer-readable storage medium further storing instructions that, when executed by the processor, cause the processor to:
 decrease a statistical significance score of co-occurring machine-readable words, from the dictionary of machine-readable words, that are less frequently observed over time; or   increase a statistical significance score of co-occurring machine-readable words, from the dictionary of machine-readable words, that are more frequently observed over time.   
     
     
         16 . A system, comprising:
 a processor; and   a memory storing processor-executable instructions that, when executed by the processor, cause the processor to:
 receive a plurality of video frames from a video source, the plurality of video frames including a representation of an object; 
 normalize, via at least one processor, data in each video frame from the received plurality of video frames to obtain normalized data for the plurality of video frames; 
 generate, via the at least one processor, a syntax for a neuro-linguistic model, the syntax including a stable model of phrases; 
 identify, via the at least one processor, instances of at least one machine-readable phrase from the stable model of phrases and based on a connected graph; 
 calculate, via the at least one processor, an unusualness score for an observation of a first machine-readable phrase from the at least one machine-readable phrase identified in the connected graph; and 
 publish, via the at least one processor, an alert associated with the observation of the first machine-readable phrase, the alert indicating an anomaly in the behavior of the object. 
   
     
     
         17 . The system of  claim 16 , wherein the instructions to generate the syntax include instructions to:
 generate a plurality of machine-readable symbols from the normalized data, each machine-readable symbol from the plurality of machine-readable symbols being associated with a distinct cluster of the normalized data, and   build a dictionary of machine-readable words based on an observed sequence of the plurality of machine-readable symbols.   
     
     
         18 . The system of  claim 16 , wherein the instructions to generate the syntax include instructions to:
 evaluate statistics for a plurality of combinations of machine-readable words co-occurring in a stream of machine-readable words, the statistics including a frequency at which combinations of machine-readable words from the plurality of combinations of machine-readable words co-occur; and   update a model of combinations of machine-readable words based on the evaluated statistics, the model identifying statistically relevant observations of co-occurring machine-readable words.   
     
     
         19 . The system of  claim 16 , wherein the instructions to generate the syntax include instructions to generate a connected graph having a plurality of nodes and a plurality of edges, each node from the plurality of nodes representing one machine-readable word in a stream of machine-readable words, and each edge from the plurality of edges connecting the nodes representing a probabilistic measure of co-occurrence of pairs of statistically relevant words in the stream of machine-readable words. 
     
     
         20 . The system of  claim 16 , wherein the instructions to generate the syntax include instructions to generate a connected graph, the connected graph including a plurality of nodes and a plurality of edges, each edge from the plurality of edges weighted based on a statistical significance score between each pair of nodes from the plurality of nodes. 
     
     
         21 . The system of  claim 16 , wherein the memory further stores instructions that, when executed by the processor, cause the processor to:
 receive a stream of machine-readable words; and   update statistics of the co-occurring words based on the stream of machine-readable words.