Analysis of anomalies using ranking algorithm
An anomaly detection and analysis system generates analysis or summary of the anomalies detected from key performance indicators (KPIs). The system receives anomaly data reporting anomalies detected in key performance indicator (KPI) data. The system classifies the reported anomalies into a plurality of anomaly items, wherein anomalies from KPI data that share a set of features are assigned to one anomaly item. The system computes a ranking score for each anomaly item by assigning predefined weights for different anomaly types that are present in the anomaly item. The system sorts a list of anomaly items from the plurality of anomaly items into a sorted list of anomaly items according to the ranking scores computed for the plurality of anomaly items. The system sends the sorted list of anomaly items to a user device for presentation.
1. A computing device comprising:
one or more processors; and
a computer-readable medium storing a plurality of computer-executable components that are executable by the one or more processors to perform a plurality of actions, the plurality of actions comprising:
receiving anomaly data reporting anomalies detected in Key Performance Indicator (KPI) data;
classifying the reported anomalies into a plurality of anomaly items, wherein anomalies from KPI data that share a set of features are assigned to one anomaly item;
determining a number of devices from which the anomalies of each anomaly item are detected;
determining anomaly types that are present in each anomaly item;
based on a combination of anomalies that are present in each anomaly type, assigning a binary word to each anomaly type;
determining a weighted score for each anomaly type based on a value of the binary word assigned to the anomaly type;
based on (i) the number of devices from which the anomalies of each anomaly item are detected and (ii) the weighted score for each anomaly type, computing a ranking score for each anomaly item;
sorting a list of anomaly items from the plurality of anomaly items into a sorted list of anomaly items according to the ranking scores computed for the plurality of anomaly items; and
sending the sorted list of anomaly items to a user device for presentation.
2. The computing device of claim 1 , wherein different power-of-two numbers that correspond to different bit positions in the binary word are used as the predefined weights for the different anomaly types.
3. The computing device of claim 1 , wherein the ranking score of an anomaly item is computed as a weighted sum of device counts of the different anomaly types.
4. The computing device of claim 1 , wherein the set of features shared by the KPI data from which the anomalies of an anomaly item are detected comprises a device type, a software version, and a geographical location.
5. The computing device of claim 1 , wherein different anomaly types correspond to different mobile communications technologies.
6. The computing device of claim 1 , wherein each anomaly type corresponds to one or more devices that detected the anomaly of the anomaly type.
7. The computing device of claim 1 , wherein assigning the binary word to each anomaly type comprises:
determining a severity level of each anomaly type; and
assigning a respective place value of the binary word to each anomaly type based on the severity level of each anomaly type.
8. The computing device of claim 7 , wherein assigning the respective place value of the binary word to each anomaly type based on the severity level of each anomaly type comprises:
assigning anomaly types with a higher severity level to place values of a higher significant digit.
9. One or more non-transitory computer-readable media of a computing device storing computer-executable instructions that upon execution cause one or more processors to perform acts comprising:
receiving anomaly data reporting anomalies detected in Key Performance Indicator (KPI) data;
classifying the reported anomalies into a plurality of anomaly items, wherein anomalies from KPI data that share a set of features are assigned to one anomaly item;
determining a number of devices from which the anomalies of each anomaly item are detected;
determining anomaly types that are present in each anomaly item;
based on a combination of anomalies that are present in each anomaly type, assigning a binary word to each anomaly type;
determining a weighted score for each anomaly type based on a value of the binary word assigned to the anomaly type;
based on (i) the number of devices from which the anomalies of each anomaly item are detected and (ii) the weighted score for each anomaly type, computing a ranking score for each anomaly item;
sorting a list of anomaly items from the plurality of anomaly items into a sorted list of anomaly items according to the ranking scores computed for the plurality of anomaly items; and
sending the sorted list of anomaly items to a user device for presentation.
10. The one or more non-transitory computer-readable media of claim 9 , wherein different power-of-two numbers that correspond to different bit positions in the binary word are used as the predefined weights for the different anomaly types.
11. The one or more non-transitory computer-readable media of claim 9 , wherein the ranking score of an anomaly item is computed as a weighted sum of device counts of the different anomaly types.
12. The one or more non-transitory computer-readable media of claim 9 , wherein the set of features shared by the KPI data from which the anomalies of the anomaly item are detected comprises a device type, a software version, and a geographical location.
13. A computer-implemented method, comprising:
receiving anomaly data reporting anomalies detected in Key Performance Indicator (KPI) data;
classifying the reported anomalies into a plurality of anomaly items, wherein anomalies from KPI data that share a set of features are assigned to one anomaly item;
determining a number of devices from which the anomalies of each anomaly item are detected;
determining anomaly types that are present in each anomaly item;
based on a combination of anomalies that are present in each anomaly type, assigning a binary word to each anomaly type;
determining a weighted score for each anomaly type based on a value of the binary word assigned to the anomaly type;
based on (i) the number of devices from which the anomalies of each anomaly item are detected and (ii) the weighted score for each anomaly type, computing a ranking score for each anomaly item;
sorting a list of anomaly items from the plurality of anomaly items into a sorted list of anomaly items according to the ranking scores computed for the plurality of anomaly items; and
sending the sorted list of anomaly items to a user device for presentation.
14. The computer-implemented method of claim 13 , wherein different power-of-two numbers that correspond to different bit positions in the binary word are used as the predefined weights for the different anomaly types.
15. The computer-implemented method of claim 13 , wherein the ranking score of an anomaly item is computed as a weighted sum of device counts of the different anomaly types.
16. The computer-implemented method of claim 13 , wherein the set of features shared by the KPI data from which the anomalies of the anomaly item are detected comprises a device type, a software version, and a geographical location.
17. The computer-implemented method of claim 13 , wherein different anomaly types correspond to different mobile communications technologies.