Method and system for finding a query-subset of events within a master-set of events
First Claim
1. A method for determining similarity between a first event set, the first event set comprising a first plurality of event types, and a second event set, the second event set comprising a second plurality of event types, the method comprising the steps of:
- randomly mapping the first event set to a multidimensional vector-Q;
randomly mapping the second event set to a multidimensional query vector-q; and
determining similarity of the multidimensional vector-Q with the multidimensional query vector-q according to;
∥
Q−
q∥
≦
SV, where SV=a predetermined similarity value.
4 Assignments
0 Petitions
Accused Products
Abstract
A method and system for determining similarity between a first event set, the first event set including a first plurality of event types, and a second event set, the second event set including a second plurality of event types, is provided. Observed events are randomly mapped to a multidimensional vector-Q and query events are mapped to a multidimensional query vector-q. Comparison of the vectors for a predetermined similarity according to: ∥Q-q∥≦SV, where SV=a predetermined similarity value determines similarity.
-
Citations
48 Claims
-
1. A method for determining similarity between a first event set, the first event set comprising a first plurality of event types, and a second event set, the second event set comprising a second plurality of event types, the method comprising the steps of:
-
randomly mapping the first event set to a multidimensional vector-Q;
randomly mapping the second event set to a multidimensional query vector-q; and
determining similarity of the multidimensional vector-Q with the multidimensional query vector-q according to;
∥
Q−
q∥
≦
SV, where SV=a predetermined similarity value. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11)
-
-
12. A method of finding a query-subset of events within an event set, the event set comprising a stream of ordered events, each ordered event corresponding to an event type e from a set of event types E, the method comprising the steps of:
-
dividing the stream of ordered events into a plurality of segments;
mapping each of the plurality of segments to a corresponding dimensional segment-vector;
mapping the query-subset of events to a dimensional query-vector; and
comparing the dimensional query-vector with at least one of the dimensional segment-vectors, and as a result of the comparison, making a determination whether the query-vector is similar to the compared segment-vector. - View Dependent Claims (13, 14, 15, 16, 17, 18, 19)
-
-
20. A method for finding similar situations in sequences of events in a data flow, the method comprising the steps of:
-
mapping (4), using a random projection, slices (2) of a sequence (1) of events to multidimensional (k) vectors (5) and mapping a query sequence (3) of events to a multidimensional (k) query vector (7);
searching (6) among the vectors (5) for such multidimensional vectors (8) for which the distance from the query vector (7) is small;
for each slice corresponding to a found vector (8) verifying (9) its similarity to the query sequence (3); and
producing as a result a set of slices (10) that are similar to the query sequence (3). - View Dependent Claims (21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33)
-
-
34. A system for finding a query-set of events within a master-set of observed events, wherein the events belong to an event set E, the system comprising:
-
a k-dimension random variable generator for generating random variables for each event within the event set E for each j=1 . . . k dimensions, where k is predetermined;
an observed event segmenter for segmenting the master-set of observed events to produce a plurality of observed event segments, (d11,s11 . . . d1m,s1m) . . . (dh1,sh1 . . . dhm,shm), where d=segmented observed event, and s=a parameter associated with the observed event;
a weighting function generator for generating a weighting function;
an observed event vectorizer for vectorizing each observed event segment (d11,s11 . . . d1m,s1m) . . . (dh1,sh1 . . . dhm,shm) according to the weighting function and the dimensional random variable corresponding to the segmented observed event d and dimension k;
a query event vectorizer for vectorizing the query set of events (Qe1,Qs1 . . . QewQsw,) according to the weighting function, the dimensional random variable corresponding to the query event Qe, and dimension k, wherein Qe=a query event, Qs=a parameter associated with the query event Qe; and
a comparator for comparing the vectorized query-set of events with each vectorized observed event segment and generating the observed event segment in accordance with the comparison results and predetermined similarity factors. - View Dependent Claims (35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47)
-
-
48. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform method steps determining similarity between a first event set, the first event set comprising a first plurality of event types, and a second event set, the second event set comprising a second plurality of event types, the method comprising the steps of:
-
mapping the first event set to a multidimensional vector-Q;
mapping the second event set to a multidimensional query vector-q; and
determining similarity of the multidimensional vector-Q with the multidimensional query vector-q according to;
∥
Q−
q∥
≦
SV, where SV=a predetermined similarity value.
-
Specification