CASE-BASED REASONING

• US 20150112917A1
• Filed: 10/17/2013
• Published: 04/23/2015
• Est. Priority Date: 10/17/2013
• Status: Active Grant

• Current Assignee: Baker Hughes Incorporated (Baker Hughes Company)
• Original Assignee: Verdande Technology AS
• Inventors: Lorentzen, Hkon, Gundersen, Odd Erik, Bach, Kerstin, Srmo, Frode
• Granted Patent: US 9,613,362 B2
• Time in Patent Office: Days
• US Class Current: 706/47
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data

Abstract

Disclosed herein is a computer-implemented method of monitoring a situation by determining a set of one or more cases in case-based reasoning (CBR) the method comprising: receiving a data stream comprising information on a monitored situation; generating a plurality of parallel data streams from the received data stream; generating, for each of the parallel data streams, an overall similarity score between the parallel data stream and one of a plurality of cases, wherein each overall similarity score is generated from a comparison between one of the plurality of data streams and a different case; and determining a set of one or more cases in dependence on the generated overall similarity scores.

Claims

1. A computer-implemented method of monitoring a situation by determining a set of one or more cases in case-based reasoning (CBR), the method comprising:

receiving a data stream comprising information on a monitored situation;

using a computer, generating a plurality of parallel data streams from the received data stream;

using a computer, generating, for each of the parallel data streams, an overall similarity score between the parallel data stream and one of a plurality of cases, wherein each overall similarity score is generated from a comparison between one of the plurality of data streams and a different case; and

determining a set of one or more cases in dependence on the generated overall similarity scores.

2. The method according to claim 1, wherein each of the overall similarity scores is generated by one of a plurality of comparison agents and each of the comparison agents receives one of the plurality of data streams.

3. The method according to claim 2, the method further comprising each comparison agent generating an overall similarity score by:

receiving one of the plurality of data streams;

generating a further plurality of parallel data streams, wherein each of the generated further plurality of parallel data streams is dependent on the received one of the plurality of data streams;

generating, for each of said generated further plurality of parallel data streams, a similarity score in dependence on a comparison between information on a feature in the generated further data stream and stored information on the feature of a case, wherein each of the similarity scores of said generated further plurality of data streams is generated in dependence on a comparison with stored information on a different feature of the same case; and

generating an overall similarity score between the received one of the plurality of data streams and the case in dependence on the generated similarity scores.

4. The method according to claim 1, further comprising determining to include a case in the set of one or more cases if the overall similarity score for the case is above a predetermined threshold level.

5. The method according to claim 1, wherein the determined set of cases has a predetermined number of two or more cases, and the method comprises determining the predetermined number of cases for including in the set as the cases with the highest overall similarity scores.

6. The method according to claim 1, further comprising displaying information dependent on each of the determined one or more cases.

7. The method according to claim 1, wherein each case comprises information that describes a situation in one of the finance industry, healthcare industry or energy industry.

8. A CBR engine for monitoring a situation by determining a set of one or more cases, wherein the CBR engine is configured to perform the method of claim 1.

9. A non-transitory computer-readable storage medium storing a computer program that, when executed by a computing device, controls the computing device to perform the method of claim 1.