Asset management expert peer identification

1. A method comprising:

receiving, from a user at a user interface, a request for an expert peer for an asset type;

obtaining asset interaction data relevant to the request, the asset interaction data including a list of assets, and, for each asset on the list, values for each of a set of pre-defined interaction categories for each worker that has interacted with the asset;

for each asset on the list, respectively multiplying the interaction category values by a corresponding set of category weights to obtain a set of weighted interaction values;

obtaining an overall centrality measure by processing a network matrix, wherein obtaining the overall centrality measure further comprises:

for each worker, processing a sum of their weighted interaction values; and

calculating a degree centrality (k i ), which is a number of the assets on the list the worker has interacted with, and a tie strength centrality (S i ), which is a sum of all of the weighted interaction values for the worker, and combining k i and S i using a non-linear function,

selecting one of the workers as the expert peer based, at least in part, on their overall centrality measure, and identifying the expert peer to the user; and

outputting a visualization of the network matrix on the user interface, wherein the visualization of the network matrix illustrates connections in the user interface between the assets and the workers and are based on the overall centrality measure, wherein the connections are illustrated by lines with varying thicknesses in the user interface, and wherein a thicker line indicates a greater tie between the worker and the asset.

2. The method of claim 1 , wherein the asset interaction data is obtained from an enterprise asset management (EAM) system.

3. The method of claim 2 , wherein the EAM system stores work orders assigned to workers, and tracks work done by asset.

4. The method of claim 2 , wherein the user is a worker in an enterprise, and submits the request for the expert peer through the EAM system.

5. The method of claim 1 , wherein the set of categories includes or is derived from properties of an EAM system.

6. The method of claim 5 , wherein the set of categories includes one or more of:

asset owner, asset custodian, work log entries, labor transactions, required skills, common site, inventory usage and expert peer.

7. The method of claim 6 , wherein the expert peer category is most heavily weighted, and the asset owner and asset custodian categories are second most heavily weighted.

8. The method of claim 1 , wherein the non-linear function is

k i (1−α) * s i α ,

where α is a tuning factor.

9. The method of claim 8 , wherein 0<α<1.

10. A system, comprising:

a user interface (UI), configured to receive an expert peer request from a user for an asset type and output a visualization of a network matrix, wherein the visualization of the network matrix illustrates connections in the user interface between the assets and the workers and are based on the overall centrality measure, wherein the connections are illustrated by lines with varying thicknesses in the user interface, and wherein a thicker line indicates a greater tie between the worker and the asset;

a data retriever, coupled to the UI, configured to obtain asset interaction data relevant to the request, the asset interaction data including a list of assets, and, for each asset on the list, values for each of a set of pre-defined interaction categories for each worker that has interacted with the asset;

an expert peer processor, coupled to the data retriever and to the UI, configured to:

process the asset interaction data to calculate an overall centrality measure of each worker to the asset type;

select one of the workers as the expert peer based, at least in part, on his overall centrality measure; and

identify the expert peer to the user, and wherein the expert peer processor further comprises:

a weighted multiplier, coupled to the data retriever and to a memory, configured to, for each asset, and for each worker of the asset, respectively multiply the values for the interaction categories by a set of corresponding category weights to generate a set of weighted interaction values;

a memory, configured to store one or more sets of corresponding category weights;

a network matrix calculator, coupled to the weighted multiplier, configured to generate the network matrix of workers and assets from the sets of weighted interaction values for each asset; and

a centrality computer, coupled to the network matrix calculator, to generate, from the network matrix, the overall centrality measure for each worker.

11. The system of claim 10 , further comprising a scheduler, coupled to the peer expert processor and to the UI, configured to:

determine availability of the identified expert peer; and

in response to a determination that the expert peer is available, route the expert peer request to the identified expert peer.

12. The system of claim 11 , further comprising:

in response to a determination that the identified expert peer is unavailable:

select, as a substitute expert peer, a worker with the highest overall centrality measure who is available; and

route the expert peer request to the substitute expert peer.

13. A computer program product for fusion of vector data and raster data for a geographic location, the computer program product comprising:

a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to:

receive, from a user at a user interface, a request for an expert peer for an asset type;

obtain asset interaction data relevant to the request, the asset interaction data including a list of assets, and, for each asset on the list, values for each of a set of pre-defined interaction categories for each worker that has interacted with the asset;

for each asset on the list, respectively multiply the interaction category values by a corresponding set of category weights to obtain a set of weighted interaction values;

obtain an overall centrality measure for a worker the computer-readable program code is further executable to:

for each worker, process a sum of their weighted interaction values; and

calculate a degree centrality (k i ), which is a number of the assets on the list the worker has interacted with;

calculate a tie strength centrality (s i ), which is a sum of all of the weighted interaction values for the worker; and

combine k i and s i using a non-linear function,

select one of the workers as the expert peer based, at least in part, on their overall centrality measure, and identify the expert peer to the user; and

output a visualization of the network matrix on the user interface, wherein the visualization of the network matrix illustrates connections in the user interface between the assets and the workers and are based on the overall centrality measure, wherein the connections are illustrated by lines with varying thicknesses in the user interface, and wherein a thicker line indicates a greater tie between the worker and the asset.

14. The computer program product of claim 13 , wherein the set of categories includes, or is derived from, properties of an EAM system.

15. The computer program product of claim 13 , wherein the non-linear function is

k i (1−α) * s i α ,

where α is a tuning factor.

16. The computer program product of claim 15 , wherein at least one of:

α has a value between 0 and 1, or

α=0.5.