Intelligent data access for industrial internet of things devices using latent semantic indexing

1. A method for data retrieval, the method comprising:

receiving a request, from a computing device, for data associated with an industrial plant;

generating a session with the computing device;

gathering nodes from one or more servers associated with the industrial plant, wherein each of the nodes includes data associated with a particular feature of the industrial plant, wherein gathering the nodes comprises:

selecting one or more nodes from the gathered nodes, wherein selecting each of the one or more nodes is based on authorization information received from the generated session with the computing device and address space views from the generated session, wherein the authorization information indicates the nodes accessible to the computing device;

generating a contextual cache of the selected one or more nodes;

converting the generated contextual cache of the one or more nodes into individual files, wherein each file includes semantic constructs associated with each of the nodes;

processing the semantic constructs associated with each of the one or more nodes to remove noise;

generating a term frequency inverse document frequency matrix by transforming the processed semantic constructs from the individual files;

performing a cosine similarly analysis between the matrix and the received request for data;

deriving contextual links between the nodes and the received request for data to identify levels of similarity between the nodes and the request for data; and

ranking the nodes based on the identified levels of similarity.

2. The method of claim 1 , further comprising:

in response to ranking the nodes, retrieving the data that is associated with a highest ranked node from the particular feature of the industrial plant; and

transmitting the retrieved data to the computing device.

3. The method of claim 1 , wherein gathering the nodes comprises:

identifying the one or more servers associated with the industrial plant;

aggregating address-spaces of the identified one or more servers to gather the nodes that are associated with each of the one or more servers; and

selecting particular nodes from the aggregated address-spaces of the one or more servers, wherein selecting each of the particular nodes is based on authorization information received from the generated session with the computing device,

wherein the authorization information indicates the particular nodes accessible to the computing device.

4. The method of claim 1 , wherein each of the nodes communicates though Open Platform Communications (OPC) Unified Architecture (UA) transport encoding.

5. The method of claim 4 , wherein the each of the nodes is one of: a data access node, a history access node and an alarm and condition node.

6. The method of claim 1 , wherein deriving contextual links between the nodes and the received request for data comprises performing a latent semantic analysis.

7. The method of claim 1 , wherein the received request for data is a natural language voice input.

8. The method of claim 1 , wherein:

each of the nodes communicates though Open Platform Communications (OPC) Unified Architecture (UA) transport encoding, and

the each of the nodes is one of a data access node, a history access node or an alarm and condition node.

9. An electronic device for data retrieval, the electronic device comprising:

a communication unit configured to communicate with one or more server and a computing device; and

a processor operably connected to the communication unit, wherein the processor is configured to:

receive a request, from the computing device, for data associated with an industrial plant;

generate a session with the computing device;

gather nodes from one or more servers associated with the industrial plant, wherein each of the nodes includes data associated a particular feature of the industrial plant, wherein gathering the nodes comprises:

select one or more nodes from the gathered nodes, wherein selecting each of the one or more nodes is based on authorization information received from the generated session with the computing device and address space views from the generated session, wherein the authorization information indicates the nodes accessible to the computing device;

generate a contextual cache of the selected one or more nodes;

convert the generated contextual cache of the one or more nodes into individual files, wherein each file include semantic constructs associated with each of the nodes;

process the semantic constructs associated with each of the one or more nodes to remove noise;

generate a term frequency inverse document frequency matrix by transforming the processed semantic constructs from the individual files;

perform a cosine similarly analysis between the matrix and the received request for data;

derive contextual links between the nodes and the received request for data to identify levels of similarity between the nodes and the request for data; and

rank the nodes based on the identified levels of similarity.

10. The electronic device of claim 9 , wherein the processor is further configured to:

in response to ranking the nodes, retrieve the data that is associated with a highest ranked node from the particular feature of the industrial plant; and

transmit the retrieved data to the computing device.

11. The electronic device of claim 9 , wherein to gathering the nodes, the processor is further configured to:

identify the one or more servers associated with the industrial plant;

aggregate address-spaces of the one or more servers to gather the nodes that are associated with each of the one or more servers; and

select particular nodes from the aggregated address-spaces of the one or more servers, wherein selecting each of the particular nodes is based on authorization information received from the generated session with the computing device,

wherein the authorization information indicates the particular nodes accessible to the computing device.

12. The electronic device of claim 9 , wherein each of the nodes communicates though Open Platform Communications (OPC) Unified Architecture (UA) transport encodings.

13. The electronic device of claim 12 , wherein the each of the nodes is one of: a data access node, a history access node and an alarm and condition node.

14. The electronic device of claim 9 , wherein to derive contextual links between the nodes and the received request for data the processor is further configured to perform a latent semantic analysis.

15. The electronic device of claim 9 , wherein the received request for data is a natural language voice input.

16. The electronic device of claim 9 , wherein:

each of the nodes communicates though Open Platform Communications (OPC) Unified Architecture (UA) transport encodings, and

the each of the nodes is one of: a data access node, a history access node or an alarm and condition node.

17. A non-transitory computer readable medium embodying a computer program, the computer program comprising computer readable program code that when executed by a processor of an electronic device causes the processor to:

receive a request, from a computing device, for data associated with an industrial plant;

generate a session with the computing device;

gather nodes from one or more servers associated with the industrial plant, wherein each of the nodes includes data associated a particular feature of the industrial plant wherein to gather the nodes, the computer readable medium further comprises program code that, when executed at the processor, causes the processor to:

select one or more nodes from the gathered nodes, wherein selecting each of the one or more nodes is based on authorization information received from the generated session with the computing device and address space views from the generated session, wherein the authorization information indicates the nodes accessible to the computing device;

generate a contextual cache of the selected one or more nodes;

convert the generated contextual cache of the one or more nodes into individual files, wherein each file include semantic constructs associated with each of the nodes;

process the semantic constructs associated with each of the one or more nodes to remove noise;

generate a term frequency inverse document frequency matrix by transforming the processed semantic constructs from the individual files; and

perform a cosine similarly analysis between the matrix and the received request for data;

derive contextual links between the nodes and the received request for data to identify levels of similarity between the nodes and the request for data; and

rank the nodes based on the identified levels of similarity.

18. The non-transitory computer readable medium of claim 17 , wherein to gather the nodes, the computer readable medium further comprises program code that, when executed at the processor, causes the processor to:

identify the one or more servers associated with the industrial plant;

aggregate address-spaces of the one or more servers to gather the nodes that are associated with each of the one or more servers; and

select particular nodes from the aggregated address-spaces of the one or more servers, wherein selecting each of the particular nodes is based on authorization information received from the generated session with the computing device,

wherein the authorization information indicates the particular nodes accessible to the computing device.

19. The non-transitory computer readable medium of claim 17 , wherein:

each of the nodes communicates though Open Platform Communications (OPC) Unified Architecture (UA) transport encodings, and

the each of the nodes is one of: a data access node, a history access node and an alarm and condition node.

20. The non-transitory computer readable medium of claim 17 , wherein to deriving contextual links between the nodes and the received request for data, the computer readable medium further comprises program code that, when executed at the processor, causes the processor to perform a latent semantic analysis.