Knowledge driven solution inference

• US 10,332,012 B2
• Filed: 10/08/2015
• Issued: 06/25/2019
• Est. Priority Date: 10/08/2015
• Status: Active Grant

• Current Assignee: SAP SE
• Original Assignee: SAP SE
• Inventors: Reddy, Srinivasa Byaiah Ramachandra
• Primary Examiner(s): Chen, Alan
• Application Number:
  US14/877,939
• Publication Number:
  US 20170103329A1
• Time in Patent Office: 1,356 Days
• CPC Class Codes: G06F 16/00 Information retrieval; Database structures therefor; File system structures therefor
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 30/016 After-sales

Abstract

Various embodiments of systems and methods to provide a knowledge driven solution inference are described herein. In one aspect, unstructured data is retrieved from one or more information sources. Data segments corresponding to a plurality of categories are identified in the extracted unstructured data by natural language processing. Further, the data segments are grouped into a plurality of data clusters based on scores between the data segments. The structured knowledge base is generated by linking the associated plurality of data clusters. The knowledge driven solution inference is provided based on the generated knowledge base.

Claims

1. A non-transitory computer-readable medium storing instructions, which when executed by a computer cause the computer to:

extract, by an extraction engine, unstructured data from one or more information sources, wherein the extracted unstructured data is stored in a data repository;

identify, by the extraction engine and from the data repository, data segments corresponding to a plurality of categories in the extracted unstructured data by natural language processing;

group, by a clustering engine and from the data repository, the data segments into a plurality of data clusters based on scores between the data segments;

generate, by the clustering engine, a structured knowledge base by linking the plurality of data clusters, wherein the structured knowledge base includes at least one link between a first data segment in a first data cluster and a second data segment in a second data cluster, and wherein the first data cluster is a problem cluster and the second data cluster is a solution cluster; and

provide, by an inference engine, a knowledge driven solution inference based on the generated knowledge base.

2. The non-transitory computer-readable medium of claim 1, wherein providing the knowledge driven solution inference further comprises:

receiving an input query;

retrieving one or more solutions to the input query by matching the input query to the plurality of data clusters in the knowledge base; and

rendering the retrieved one or more solutions.

3. The non-transitory computer-readable medium of claim 2, further comprising instructions which when executed by the computer cause the computer to:

receive a follow up query based on the rendered one or more solutions; and

render a new solution in response to the follow up query.

4. The non-transitory computer-readable medium of claim 1, wherein the plurality of clusters comprises:

problem clusters, solution clusters, root cause clusters, and approach clusters.

5. The non-transitory computer-readable medium of claim 1, wherein linking the plurality of data clusters is based on semantic relationships between one or more nodes in the plurality of data clusters.

6. The non-transitory computer-readable medium of claim 1, wherein grouping the data segments comprises grouping the one or more nodes corresponding to the data segments based on a score between the data segments and a pre-defined threshold.

7. The non-transitory computer-readable medium of claim 1, wherein the data segments are represented as nodes and ranks of the nodes are assigned based on a number of other nodes linked to a node, a number of other nodes merged to the node, and a number of times the node is searched.

8. A computer implemented method to provide a knowledge driven solution inference, comprising:

extracting, by an extraction engine, unstructured data from one or more information sources, wherein the extracted unstructured data is stored in a data repository;

identifying, by the extraction engine and from the data repository, data segments corresponding to a plurality of categories in the extracted unstructured data by natural language processing;

grouping, by a clustering engine and from the data repository, the data segments into a plurality of data clusters based on scores between the data segments;

generating, by the clustering engine, a structured knowledge base by linking the plurality of data clusters, wherein the structured knowledge base includes at least one link between a first data segment in a first data cluster and a second data segment in a second data cluster, and wherein the first data cluster is a problem cluster and the second data cluster is a solution cluster; and

providing, by an inference engine, the knowledge driven solution inference based on the generated knowledge base.

9. The computer implemented method of claim 8, wherein providing the knowledge driven solution inference further comprises:

receiving an input query;

retrieving one or more solutions to the input query by matching the input query to the plurality of data clusters in the knowledge base; and

rendering the retrieved one or more solutions.

10. The computer implemented method of claim 9, further comprising:

receiving a follow up query based on the rendered one or more solutions; and

rendering a new solution in response to the follow up query.

11. The computer implemented method of claim 8, wherein the plurality of clusters comprises:

problem clusters, solution clusters, root cause clusters, and approach clusters.

12. The computer implemented method of claim 8, wherein linking the plurality of data clusters is based on semantic relationships between one or more nodes in the plurality of data clusters.

13. The computer implemented method of claim 8, wherein grouping the data segments comprises grouping the one or more nodes corresponding to the data segments based on a score between the data segments and a pre-defined threshold.

14. The computer implemented method of claim 8, wherein the data segments are represented as nodes and ranks of the nodes are assigned based on a number of other nodes linked to a node, a number of other nodes merged to the node, and a number of times the node is searched.

15. A computing system to provide a knowledge driven solution inference, comprising:

at least one processor; and

a computer-readable medium communicative with the at least one processor and storing instructions executable by the at least one processor, wherein the instructions instruct the at least one processor to;

extract, by an extraction engine, unstructured data from one or more information sources, wherein the extracted unstructured data is stored in a data repository;

identify, by the extraction engine and from the data repository, data segments corresponding to a plurality of categories in the extracted unstructured data by natural language processing;

group, by a clustering engine and from the data repository, the data segments into a plurality of data clusters based on scores between the data segments;

generate, by the clustering engine, a structured knowledge base by linking the plurality of data clusters, wherein the structured knowledge base includes at least one link between a first data segment in a first data cluster and a second data segment in a second data cluster, and wherein the first data cluster is a problem cluster and the second data cluster is a solution cluster; and

provide, by an inference engine, the knowledge driven solution inference based on the generated knowledge base.

16. The computing system of claim 15, wherein providing the knowledge driven solution inference further comprises:

receiving an input query;

retrieving one or more solutions to the input query by matching the input query to the plurality of data clusters in the knowledge base; and

rendering the retrieved one or more solutions.

17. The computing system of claim 16, further comprising:

receive a follow up query based on the rendered one or more solutions; and

render a new solution in response to the follow up query.

18. The computing system of claim 15, wherein linking the plurality of data clusters is based on semantic relationships between one or more nodes in the plurality of data clusters.

19. The computing system of claim 15, wherein grouping the data segments comprises grouping the one or more nodes corresponding to the data segments based on a score between the data segments and a pre-defined threshold.

20. The computing system of claim 15, wherein the data segments are represented as nodes and ranks of the nodes are assigned based on a number of other nodes linked to a node, a number of other nodes merged to the node, and a number of times the node is searched.