Mapper component for a neuro-linguistic behavior recognition system
AssigneeIntellective Ai, Inc.
InventorsMing-Jung Seow, Gang Xu, Tao Yang, Wesley K. Cobb
Life of this patent
Estimating the term…
Abstract
Techniques are disclosed for generating a sequence of symbols based on input data for a neuro-linguistic model. The model may be used by a behavior recognition system to analyze the input data. A mapper component of a neuro-linguistic module in the behavior recognition system receives one or more normalized vectors generated from the input data. The mapper component generates one or more clusters based on a statistical distribution of the normalized vectors. The mapper component evaluates statistics and identifies statistically relevant clusters. The mapper component assigns a distinct symbol to each of the identified clusters.
Claims20
A method, comprising:
- receiving a normalized vector of feature values, each feature value from the normalized vector of feature values being calculated based on a feature from a plurality of features;
- for each feature value from the normalized vector of feature values:
- evaluating a distribution of a plurality of clusters in a cluster space associated with that feature from the plurality of features,
- updating the distribution of the plurality of clusters based on a mapping of that feature value to a first single cluster from the plurality of clusters, to produce an updated distribution of the plurality of clusters, and
- determining, based on the updated distribution of the plurality of clusters, whether to merge the plurality of clusters with a further cluster from the cluster space associated with the plurality of features;
- determining a symbol for a statistically significant cluster from the plurality of clusters;
- and
- causing transmission of the symbol to a behavior recognition system.
A computer-readable medium storing instructions to cause a processor to:
- receive a normalized vector of feature values, each feature value from the normalized vector of feature values being calculated based on a feature from a plurality of features;
- for each feature value from the normalized vector of feature values:
- evaluate a distribution of a plurality of clusters in a cluster space associated with that feature from the plurality of features,
- update the distribution of the plurality of clusters based on a mapping of that feature value to a first single cluster from the plurality of clusters, to produce an updated distribution of the plurality of clusters, and
- determine, based on the updated distribution of the plurality of clusters, whether to merge the plurality of clusters with a further cluster from the cluster space;
- determine a symbol for a statistically significant cluster from the plurality of clusters;
- and
- cause transmission of the symbol to a behavior recognition system.
A system, comprising:
- a processor;
- and
- a memory storing instructions to cause the processor to:
- receive a normalized vector of feature values, each feature value from the normalized vector of feature values being calculated based on a feature from a plurality of features;
- for each feature value from the normalized vector of feature values:
- evaluate a distribution of a plurality of clusters associated with that feature from the plurality of features,
- update the distribution of the plurality of clusters based on a mapping of that feature value to a first single cluster from the plurality of clusters, to produce an updated distribution of the plurality of clusters, and
- determine, based on the updated distribution of the plurality of clusters, whether to merge the plurality of clusters with a further cluster from the cluster space;
- determine a symbol for a statistically significant cluster from the plurality of clusters;
- and
- cause transmission of the symbol to a behavior recognition system.
Dependencies are inferred from the claim text.