Stream computing event models
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying events in a stream computing system using hierarchical analytic models. One of the methods includes receiving, by a stream computing system, data representing the values of one or more data attributes of an event in a stream of events. The values of each of the one or more data attributes are evaluated according to respective attribute-specific and class-specific criteria of a hierarchical analytic model in a predetermined order defined by the model. When a first value of a first data attribute satisfies one or more particular criteria for a first class, the first class of the plurality of classes is assigned to the event.
1. A computer-implemented method comprising:
obtaining a plurality of data objects that each include data corresponding to a respective event that has been classified into a particular event class using a hierarchical analytical model that defines one or more sets of attribute-specific criteria, wherein each data object (i) represents a unit of activity, and (ii) is associated with one or more attributes;
generating a plurality of event clusters of the data objects that have been classified into the particular class based on features derived from values of the one or more attributes that are associated with each respective data object;
identifying, for at least one of the generated event clusters, a differentiating feature that is (i) common to the clustered data objects in one cluster and (ii) not common to the clustered data objects in any of the other clusters; and
updating the hierarchical model, wherein updating the hierarchical model includes adding the differentiating feature and a set of one or more criteria for the differentiating feature to the hierarchical analytical model to classify incoming events.
2. The method of claim 1 , wherein generating the plurality of event clusters further comprises:
for each data object of the plurality of data objects:
generating a feature vector that represents the data object using the values of the one or more attributes of the data object as features; and
clustering the generated feature vectors based on the features of the generated feature vectors, wherein each of the clusters of the generated feature vectors represents a particular type of event.
3. The method of claim 1 , wherein generating the plurality of event clusters further comprises:
for each data object of the plurality of data objects:
generating a feature vector that represents the data object using the values of the one or more attributes of the data object as features; and
clustering the generated feature vectors based on the features of the generated feature vectors;
wherein the method further comprises:
evaluating a differentiating quality of the differentiating feature;
determining that the differentiating quality of the feature that is common to the clustered data objects satisfies a predetermined threshold; and
in response to determining that the differentiating quality of the feature that is common to the clustered data objects satisfies a predetermined threshold, adding the feature to the analytical model.
4. The method of claim 1 , further comprising:
obtaining data representing respective values of one or more data attributes of an event in a stream of events; and
classifying the event using the updated hierarchical model by determining that at least one of the respective values of the one or more data attributes of the event in the stream of events satisfies the set of criteria based on the differentiating feature.
5. A system comprising:
one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising:
obtaining a plurality of data objects that each include data corresponding to a respective event that has been classified into a particular event class using a hierarchical analytical model that defines one or more sets of attribute-specific criteria, wherein each data object (i) represents a unit of activity, and (ii) is associated with one or more attributes;
generating a plurality of event clusters of the data objects that have been classified into the particular class based on features derived from values of the one or more attributes that are associated with each respective data object;
identifying, for at least one of the generated event clusters, a differentiating feature that is (i) common to the clustered data objects in one cluster and (ii) not common to the clustered data objects in any of the other clusters; and
updating the hierarchical model, wherein updating the hierarchical model includes adding the differentiating feature and a set of one or more criteria for the differentiating feature to the hierarchical analytical model to classify incoming events.
6. The system of claim 5 , wherein generating the plurality of event clusters further comprises:
for each data object of the plurality of data objects:
generating a feature vector that represents the data object using the values of the one or more attributes of the data object as features; and
clustering the generated feature vectors based on the features of the generated feature vectors, wherein each of the clusters of the generated feature vectors represents a particular type of event.
7. The system of claim 5 , wherein generating the plurality of event clusters further comprises:
for each data object of the plurality of data objects:
generating a feature vector that represents the data object using the values of the one or more attributes of the data object as features; and
clustering the generated feature vectors based on the features of the generated feature vectors;
wherein the operations further comprise:
evaluating a differentiating quality of the differentiating feature;
determining that the differentiating quality of the feature that is common to the clustered data objects satisfies a predetermined threshold; and
in response to determining that the differentiating quality of the feature that is common to the clustered data objects satisfies a predetermined threshold, adding the feature to the analytical model.
8. The system of claim 5 , the operations further comprising:
obtaining data representing respective values of one or more data attributes of an event in a stream of events; and
classifying the event using the updated hierarchical model by determining that at least one of the respective values of the one or more data attributes of the event in the stream of events satisfies the set of criteria based on the differentiating feature.
9. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:
obtaining a plurality of data objects that each include data corresponding to a respective event that has been classified into a particular event class using a hierarchical analytical model that defines one or more sets of attribute-specific criteria, wherein each data object (i) represents a unit of activity, and (ii) is associated with one or more attributes;
generating a plurality of event clusters of the data objects that have been classified into the particular class based on features derived from values of the one or more attributes that are associated with each respective data object;
identifying, for at least one of the generated event clusters, a differentiating feature that is (i) common to the clustered data objects in one cluster and (ii) not common to the clustered data objects in any of the other clusters; and
updating the hierarchical model, wherein updating the hierarchical model includes adding the differentiating feature and a set of one or more criteria for the differentiating feature to the hierarchical analytical model to classify incoming events.
10. The computer-readable medium of claim 9 , wherein generating the plurality of event clusters further comprises:
for each data object of the plurality of data objects:
generating a feature vector that represents the data object using the values of the one or more attributes of the data object as features; and
clustering the generated feature vectors based on the features of the generated feature vectors, wherein each of the clusters of the generated feature vectors represents a particular type of event.
11. The computer-readable medium of claim 9 , wherein generating the plurality of event clusters further comprises:
for each data object of the plurality of data objects:
generating a feature vector that represents the data object using the values of the one or more attributes of the data object as features; and
clustering the generated feature vectors based on the features of the generated feature vectors;
wherein the operations further comprising:
evaluating a differentiating quality of the differentiating feature;
determining that the differentiating quality of the feature that is common to the clustered data objects satisfies a predetermined threshold; and
in response to determining that the differentiating quality of the feature that is common to the clustered data objects satisfies a predetermined threshold, adding the feature to the analytical model.
12. The computer-readable medium of claim 9 , the operations further comprising:
obtaining data representing respective values of one or more data attributes of an event in a stream of events; and
classifying the event using the updated hierarchical model by determining that at least one of the respective values of the one or more data attributes of the event in the stream of events satisfies the set of criteria based on the differentiating feature.