GRAPH-BASED DATA ANALYSIS FOR SENSOR NETWORKS

• US 20180173184A1
• Filed: 12/16/2016
• Published: 06/21/2018
• Est. Priority Date: 12/16/2016
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP SE
• Inventors: Kienzle, Stefan
• Granted Patent: US 10,452,040 B2
• Time in Patent Office: Days
• CPC Class Codes: G05B 19/042 using digital processors G05B19/05 takes precedence
• CPC Class Codes: G05B 19/0425 Safety, monitoring
• CPC Class Codes: G05B 19/0428 Safety, monitoring G05B19/0423 takes precedence
• CPC Class Codes: G05B 19/4185 characterised by the network communication
• CPC Class Codes: G05B 2219/24103 Graphical display of proces as function of detected alarm signals

Abstract

Techniques are described for graph-based analysis of data generated on sensor networks, such as Internet-of-Things (IoT) networks. Data may be collected from various computing devices, or sensors, on a network. The data is discretized and analyzed to provide a graphical representation of at least a portion of the data. In some instances, the graph may be determined based on various relationships between nodes that correspond to discrete portions of the data, and the relationships between nodes may be time-based correlations between the data of the nodes. The graph accumulates, compresses, and organizes the data to enable efficient data visualization, analysis, alert generation, and/or other activities. A previously generated version of a graph may be compared to a current version to identify a changing situation, such as new usage of the monitored devices, failure or anomalous behavior of the devices, and so forth.

Claims

1. A computer-implemented method performed by at least one processor, the method comprising:

receiving, by the at least one processor, data generated by each of a plurality of devices;

determining, by the at least one processor, based on the data, a graph that includes nodes and edges connecting pairs of nodes, wherein;

each of the nodes corresponds to a different value, or a different range of values, of the data;

each of the edges connects a pair of nodes for which corresponding values, or ranges of values, are present in the data during a same time period; and

each of the edges is associated with a counter value that indicates a number of time periods during which the corresponding values, or ranges of values, are present in the data;

identifying, by the at least one processor, based on the graph, a typical operating mode of the plurality of devices, the typical operating mode including a set of values corresponding to nodes for which the connecting edges exhibit a highest counter value; and

storing, by the at least one processor, the typical operating mode in data storage.

2. The method of claim 1, wherein each of the plurality of devices generates a different type of the data.

3. The method of claim 1, wherein the plurality of devices are components of a machine and are configured to generate the data that describes a plurality of attributes of the machine.

4. The method of claim 1, further comprising:

discretizing, by the at least one processor, the data according to a plurality of time periods.

5. The method of claim 1, further comprising:

storing, by the at least one processor, the graph in the data storage.

6. The method of claim 1, further comprising:

receiving, by the at least one processor, updated data generated by each of the plurality of devices;

determining, by the at least one processor, based on the updated data, an updated version of the graph; and

in response to determining that the updated version of the graph exhibits the typical operating mode that differs compared to the stored typical operating mode, sending, by the at least one processor, at least one alert.

7. The method of claim 6, wherein the at least one alert is sent in response to determining that the updated version of the graph exhibits the typical operating mode that differs by at least a predetermined threshold value compared to the stored typical operating mode.

8. The method of claim 6, wherein the at least one alert indicates at least one current data value that is different than a corresponding data value included in the stored typical operating mode.

9. The method of claim 1, wherein the plurality of devices is a plurality of Internet-of-Things (IoT) devices.

10. A system, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor, the memory storing instructions which, when executed by the at least one processor, cause the at least one processor to perform operations comprising;

receiving data generated by each of a plurality of devices;

determining based on the data, a graph that includes nodes and edges connecting pairs of nodes, wherein;

each of the nodes corresponds to a different value, or a different range of values, of the data;

each of the edges connects a pair of nodes for which corresponding values, or ranges of values, are present in the data during a same time period; and

each of the edges is associated with a counter value that indicates a number of time periods during which the corresponding values, or ranges of values, are present in the data;

identifying, based on the graph, a typical operating mode of the plurality of devices, the typical operating mode including a set of values corresponding to nodes for which the connecting edges exhibit a highest counter value; and

storing the typical operating mode in data storage.

11. The system of claim 10, wherein each of the plurality of devices generates a different type of the data.

12. The system of claim 10, wherein the plurality of devices are components of a machine and are configured to generate the data that describes a plurality of attributes of the machine.

13. The system of claim 10, the operations further comprising:

discretizing the data according to a plurality of time periods.

14. The system of claim 10, the operations further comprising:

storing the graph in the data storage.

15. The system of claim 10, the operations further comprising:

receiving updated data generated by each of the plurality of devices;

determining, based on the updated data, an updated version of the graph; and

in response to determining that the updated version of the graph exhibits the typical operating mode that differs compared to the stored typical operating mode, sending at least one alert.

16. One or more computer-readable media storing instructions which, when executed by at least one processor, cause the at least one processor to perform operations comprising:

receiving data generated by each of a plurality of devices;

determining based on the data, a graph that includes nodes and edges connecting pairs of nodes, wherein;

each of the nodes corresponds to a different value, or a different range of values, of the data;

each of the edges connects a pair of nodes for which corresponding values, or ranges of values, are present in the data during a same time period; and

each of the edges is associated with a counter value that indicates a number of time periods during which the corresponding values, or ranges of values, are present in the data;

identifying, based on the graph, a typical operating mode of the plurality of devices, the typical operating mode including a set of values corresponding to nodes for which the connecting edges exhibit a highest counter value; and

storing the typical operating mode in data storage.

17. The one or more computer-readable media of claim 16, the operations further comprising:

receiving updated data generated by each of the plurality of devices;

determining based on the updated data, an updated version of the graph; and

in response to determining that the updated version of the graph exhibits the typical operating mode that differs compared to the stored typical operating mode, sending at least one alert.

18. The one or more computer-readable media of claim 17, wherein the at least one alert is sent in response to determining that the updated version of the graph exhibits the typical operating mode that differs by at least a predetermined threshold value compared to the stored typical operating mode.

19. The one or more computer-readable media of claim 17, wherein the at least one alert indicates at least one current data value that is different than a corresponding data value included in the stored typical operating mode.

20. The one or more computer-readable media of claim 16, wherein the plurality of devices is a plurality of Internet-of-Things (IoT) devices.