Hierarchical behavioral profile
In a hierarchical profile, each node represents at least one feature of behavioral data collected about an entity profiled, with the topmost node selected as the “statistically most informative” feature of the data. A profile can cover numerous domains and be predictively very powerful in each domain. A number of observations can be “aggregated” together into a single datapoint. In use, the structure of the profile is compared against current information associated with the entity to produce a recommendation or prediction. If the profile represents at least some data aggregation, then new observations are folded into the profile based on statistical weights of the aggregations. Because of the way the profile is created and updated, its hierarchical structure maps the collected observations. Therefore, as new observations are incorporated, if the new observations change the profile's structure significantly, then it can be hypothesized that something “interesting” has happened to the entity.
1. In an environment comprising a hierarchical profile for an entity and a context comprising a plurality of features with values, a method for performing an action, the method comprising:
setting a termination criterion for use when comparing the context with the hierarchical profile, the hierarchical profile comprising a hierarchy of statistically most informative features of collected behavioral data associated with the entity;
selecting a first feature of the context from the hierarchy of statistically most informative features of the context as determined by a structure of the hierarchical profile;
selecting a first node in the hierarchical profile that matches the selected first feature of the context, the first node matching the first feature when a difference between the first node and the first feature is below a threshold;
repeating, until a satisfaction of the termination criterion, the selecting steps with a heretofore unselected feature of the statistically most informative features of the context as determined by a structure of the hierarchical profile below the nodes so far selected; and
performing, responsive to the satisfaction of the termination criterion, an action, the performing based, at least in part, on the last matched node of the hierarchical profile.
2. The method of claim 1 wherein the entity is selected from the group consisting of: a person, a plurality of persons, a corporate entity, a social network of persons, a group of persons defined by a shared contextual attribute, and an entity defined by a collection rule.
3. The method of claim 1 wherein the termination criterion is selected from the group consisting of: all features of the context have been matched, a specified number of features of the content have been matched, and a specified fraction of the features of the content have been matched.
4. The method of claim 1 wherein the action is selected from the group consisting of: providing a recommendation, choosing a message to send, providing a prediction, and mapping a behavioral pattern.
5. A computing device configured for performing an action in an environment comprising a hierarchical profile for an entity and a context comprising a plurality of features with values, the computing device comprising:
a memory configured for storing the hierarchical profile; and
a processor operatively connected to the memory and configured for:
setting a termination criterion for use when comparing the context with the hierarchical profile, the hierarchical profile comprising a hierarchy of statistically most informative features of collected behavioral data associated with the entity;
selecting a first feature of the context from the hierarchy of statistically most informative features of the context as determined by a structure of the hierarchical profile;
selecting a first node in the hierarchical profile that matches the selected first feature of the context, the first node matching the first feature when a difference between the first node and the first feature is below a threshold;
repeating, until a satisfaction of the termination criterion, the selecting steps with a heretofore unselected feature of the statistically most informative features of the context as determined by a structure of the hierarchical profile below the nodes so far selected; and
performing, responsive to the satisfaction of the termination criterion, an action, the performing based, at least in part, on the last matched node of the hierarchical profile.
6. The computing device of claim 5 wherein the computing device is selected from the group consisting of: a compute server, a coordinated group of compute servers, and a personal electronic device.
7. In an environment comprising a hierarchical profile for an entity and a context comprising a plurality of features with values, a method for performing an action, the method comprising:
setting a termination criterion for use when comparing the context with the hierarchical profile, the hierarchical profile comprising a hierarchy of statistically most informative features of collected behavioral data associated with the entity;
selecting a first feature of the context from the hierarchy of statistically most informative features of the context as determined by a structure of the hierarchical profile;
selecting a first node in the hierarchical profile that matches the selected first feature of the context, the first node matching the first feature when a difference between the first node and the first feature is below a threshold; and
repeating, until a satisfaction of the termination criterion, the selecting steps with a heretofore unselected feature of the statistically most informative features of the context as determined by a structure of the hierarchical profile below the nodes so far selected;
selecting, responsive to the satisfaction of the termination criterion, a second node in the hierarchical profile that is a next-best matching node for the first feature of the context; and
performing an action, the performing based, at least in part, on the next-best matching node of the hierarchical profile.
8. The method of claim 7 wherein the entity is selected from the group consisting of: a person, a plurality of persons, a corporate entity, a social network of persons, a group of persons defined by a shared contextual attribute, and an entity defined by a collection rule.
9. The method of claim 7 wherein the termination criterion is selected from the group consisting of: all features of the context have been matched, a specified number of features of the content have been matched, and a specified fraction of the features of the content have been matched.
10. The method of claim 7 wherein the next-best matching node is selected from the group consisting of: a node that most closely matches the first feature of the context and a second node found whose difference from the first node in the context is below a second threshold.
11. The method of claim 7 wherein the action is selected from the group consisting of: providing a recommendation, choosing a message to send, providing a prediction, and mapping a behavioral pattern.
12. A computing device configured for performing an action in an environment comprising a hierarchical profile for an entity and a context comprising a plurality of features with values, the computing device comprising:
a memory configured for storing the hierarchical profile; and
a processor operatively connected to the memory and configured for:
setting a termination criterion for use when comparing the context with the hierarchical profile, the hierarchical profile comprising a hierarchy of statistically most informative features of collected behavioral data associated with the entity;
selecting a first feature of the context from the hierarchy of statistically most informative features of the context as determined by a structure of the hierarchical profile;
selecting a first node in the hierarchical profile that matches the selected first feature of the context, the first node matching the first feature when a difference between the first node and the first feature is below a threshold; and
repeating, until a satisfaction of the termination criterion, the selecting steps with a heretofore unselected feature of the statistically most informative features of the context as determined by a structure of the hierarchical profile below the nodes so far selected;
selecting, responsive to the satisfaction of the termination criterion, a second node in the hierarchical profile that is a next-best matching node for the first feature of the context; and
performing an action, the performing based, at least in part, on the next-best matching node of the hierarchical profile.
13. The computing device of claim 12 wherein the computing device is selected from the group consisting of: a compute server, a coordinated group of compute servers, and a personal electronic device.
14. In an environment comprising a hierarchical profile for an entity and a context comprising a plurality of features with values, a method for performing an action, the method comprising:
setting a termination criterion for use when comparing the context with the hierarchical profile, the hierarchical profile comprising a hierarchy of statistically most informative features of collected behavioral data associated with the entity;
selecting a first feature of the context from the hierarchy of statistically most informative features of the context as determined by a structure of the hierarchical profile;
selecting a first node in the hierarchical profile that matches the selected first feature of the context, the first node matching the first feature when a difference between the first node and the first feature is below a threshold; and
repeating, until a satisfaction of the termination criterion, the selecting steps with a heretofore unselected feature of the statistically most informative features of the context as determined by a structure of the hierarchical profile below the nodes so far selected;
selecting, responsive to the satisfaction of the termination criterion, and combination of nodes in the hierarchical profile that is a next-best matching combination of nodes for the first feature of the context; and
performing an action, the performing based, at least in part, on the next-best matching combination of nodes of the hierarchical profile.
15. The method of claim 14 wherein the entity is selected from the group consisting of: a person, a plurality of persons, a corporate entity, a social network of persons, a group of persons defined by a shared contextual attribute, and an entity defined by a collection rule.
16. The method of claim 14 wherein the termination criterion is selected from the group consisting of: all features of the context have been matched, a specified number of features of the content have been matched, and a specified fraction of the features of the content have been matched.
17. The method of claim 14 wherein the next-best matching combination of nodes comprises a plurality of nodes that most closely match the first feature of the context.
18. The method of claim 14 wherein the action is selected from the group consisting of: providing a recommendation, choosing a message to send, providing a prediction, and mapping a behavioral pattern.
19. A computing device configured for performing an action in an environment comprising a hierarchical profile for an entity and a context comprising a plurality of features with values, the computing device comprising:
a memory configured for storing the hierarchical profile; and
a processor operatively connected to the memory and configured for:
setting a termination criterion for use when comparing the context with the hierarchical profile, the hierarchical profile comprising a hierarchy of statistically most informative features of collected behavioral data associated with the entity;
selecting a first feature of the context from the hierarchy of statistically most informative features of the context as determined by a structure of the hierarchical profile;
selecting a first node in the hierarchical profile that matches the selected first feature of the context, the first node matching the first feature when a difference between the first node and the first feature is below a threshold; and
repeating, until a satisfaction of the termination criterion, the selecting steps with a heretofore unselected feature of the statistically most informative features of the context as determined by a structure of the hierarchical profile below the nodes so far selected;
selecting, responsive to the satisfaction of the termination criterion, a combination of nodes in the hierarchical profile that is a next-best matching combination of nodes for the first feature of the context; and
performing an action, the performing based, at least in part, on the next-best matching combination of nodes of the hierarchical profile.
20. The computing device of claim 19 wherein the computing device is selected from the group consisting of: a compute server, a coordinated group of compute servers, and a personal electronic device.