Granted Patent B2

US 12,411,592 · App. 18/546,791 · Granted Sep 9, 2025

Inventor: Hemantkumar Prakashbhai Makhijani (Pune, IN)

Assignee: Schlumberger Technology Corporation

G06F3/04842G06F16/583G06F16/538

Abstract

Claims (99)

1. A method comprising:

displaying, in a graphical user interface (GUI) of a display device, a first image generated from a first well log;

receiving, via the GUI, a selection of a portion of the first image, wherein the portion of the first image displays values of a first well log channel of the first well log;

obtaining, for the portion of the first image, first search metadata, wherein the first search metadata corresponds to a second well log channel of the first well log, and wherein the portion of the first image excludes values of the second well log channel;

deriving, from the portion of the first image, a search pattern comprising a constraint on a value of a search parameter, wherein the search parameter corresponds to the first well log channel;

performing, using the search pattern, a first search within the first image;

obtaining a first plurality of search results comprising a plurality of portions of the first image matching the search pattern;

marking, in the GUI, locations of the first plurality of search results within the first image;

receiving, via the GUI, a selection of a search result of the first plurality of search results; and

presenting, in the GUI, the search result.

2. The method of claim 1 , further comprising:

training a recommendation model using historical search patterns comprising a plurality of values of the search parameter, the historical search patterns each labeled with search metadata; and

before performing the first search, recommending, by the recommendation model and using the first search metadata, a modification to the search pattern that modifies the constraint on the value of the search parameter.

3. The method of claim 1 , wherein the first search metadata is obtained via the GUI, the method further comprising:

training a recommendation model using historical search patterns comprising a plurality of values of the search parameter, the historical search patterns each labeled with search metadata; and

before performing the first search, recommending, by the recommendation model and using the search pattern, a modification to the first search metadata.

4. The method of claim 1 , further comprising:

saving, in a search pattern repository, the search pattern and the first search metadata;

displaying, in the GUI, a second image generated from a second well log;

receiving, for the second image and via the GUI, second search metadata;

determining, by querying the search pattern repository with the second search metadata, that the second search metadata is similar to the first search metadata; and

in response to determining that the second search metadata is similar to the first search metadata:

retrieving, from the search pattern repository and using the first search metadata, the search pattern, and

making a proposal, via the GUI, to perform a second search within the second image using the search pattern.

5. The method of claim 4 , further comprising:

receiving, via the GUI, an acceptance of the proposal;

in response to receiving the acceptance, performing, using the search pattern, the second search of the second image; and

obtaining a second plurality of search results comprising a plurality of portions of the second image matching the search pattern.

6. The method of claim 4 , further comprising:

obtaining, from the search pattern repository, a plurality of search metadata comprising the first search metadata; and

calculating a plurality of similarity scores between the second search metadata and the plurality of search metadata, wherein the second search metadata is determined to be similar to the first search metadata using the plurality of similarity scores.

7. The method of claim 1 , wherein the first well log comprises one or more properties of a wellbore in a geological formation.

8. A computer system comprising:

a computer processor;

a data repository configured to store a plurality of images generated from a plurality of well logs, the plurality of images comprising a first image generated from a first well log of the plurality of well logs; and

memory accessible by the computer processor, the memory storing instructions for a search pattern engine that, when executed by the computer processor, cause the computer processor to:

display, in a graphical user interface (GUI) of a display device, the first image,

receive, via the GUI, a selection of a portion of the first image, wherein the portion of the first image displays values of a first well log channel of the first well log,

obtain, for the portion of the first image, first search metadata, wherein the first search metadata corresponds to a second well log channel of the first well log, and wherein the portion of the first image excludes values of the second well log channel,

derive, from the portion of the first image, a search pattern comprising a constraint on a value of a search parameter, wherein the search parameter corresponds to the first well log channel,

perform, using the search pattern, a first search within the first image,

obtain a first plurality of search results comprising a plurality of portions of the first image matching the search pattern,

mark, in the GUI, locations of the first plurality of search results within the first image,

transmit the first plurality of search results,

receive, via the GUI, a selection of a search result of the first plurality of search results, and

present, in the GUI, the search result.

9. The computer system of claim 8 , further comprising a recommendation model, wherein the search pattern engine is further configured to:

train the recommendation model using historical search patterns comprising a plurality of values of the search parameter, the historical search patterns each labeled with search metadata, and

before performing the first search, recommend, by the recommendation model and using the first search metadata, a modification to the search pattern that modifies the constraint on the value of the search parameter.

10. The computer system of claim 8 , further comprising a recommendation model, wherein the first search metadata is obtained via the GUI, and wherein the search pattern engine is further configured to:

train the recommendation model using historical search patterns comprising a plurality of values of the search parameter, the historical search patterns each labeled with search metadata, and

before performing the first search, recommend, by the recommendation model and using the search pattern, a modification to the first search metadata.

11. The computer system of claim 8 , wherein the search pattern engine is further configured to:

save, in a search pattern repository, the search pattern and the first search metadata,

display, in the GUI, a second image generated from a second well log,

receive, for the second image and via the GUI, second search metadata,

determine, by querying the search pattern repository with the second search metadata, that the second search metadata is similar to the first search metadata, and

in response to determining that the second search metadata is similar to the first search metadata:

retrieve, from the search pattern repository and using the first search metadata, the search pattern, and

make a proposal, via the GUI, to perform a second search within the second image using the search pattern.

12. The computer system of claim 11 , wherein the search pattern engine is further configured to:

receive, via the GUI, an acceptance of the proposal,

in response to receiving the acceptance, perform, using the search pattern, the second search of the second image, and

obtain a second plurality of search results comprising a plurality of portions of the second image matching the search pattern.

13. The computer system of claim 11 , wherein the search pattern engine is further configured to:

obtain, from the search pattern repository, a plurality of search metadata comprising the first search metadata, and

calculate a plurality of similarity scores between the second search metadata and the plurality of search metadata, wherein the second search metadata is determined to be similar to the first search metadata using the plurality of similarity scores.

14. The computer system of claim 8 , wherein the first well log comprises one or more properties of a wellbore in a geological formation.

15. A non-transitory computer readable storage medium comprising computer readable program code, when executed by a processor, causes a computer system to:

display, in a graphical user interface (GUI) of a display device, a first image generated from a first well log;

receive, via the GUI, a selection of a portion of the first image, wherein the portion of the first image displays values of a first well log channel of the first well log;

obtain, for the portion of the first image, first search metadata, wherein the first search metadata corresponds to a second well log channel of the first well log, and wherein the portion of the first image excludes values of the second well log channel;

derive, from the portion of the first image, a search pattern comprising a constraint on a value of a search parameter, wherein the search parameter corresponds to the first well log channel;

perform, using the search pattern, a first search within the first image;

obtain a first plurality of search results comprising a plurality of portions of the first image matching the search pattern;

mark, in the GUI, locations of the first plurality of search results within the first image;

receive, via the GUI, a selection of a search result of the first plurality of search results; and

present, in the GUI, the search result.

16. The non-transitory computer readable storage medium of claim 15 , wherein the computer readable program code, when executed by the processor, further causes the computer system to:

train a recommendation model using historical search patterns comprising a plurality of values of the search parameter, the historical search patterns each labeled with search metadata; and

before performing the first search, recommend, by the recommendation model and using the first search metadata, a modification to the search pattern that modifies the constraint on the value of the search parameter.

17. The non-transitory computer readable storage medium of claim 15 , wherein the computer readable program code, when executed by the processor, further causes the computer system to:

train a recommendation model using historical search patterns comprising a plurality of values of the search parameter, the historical search patterns each labeled with search metadata; and

before performing the first search, recommend, by the recommendation model and using the search pattern, a modification to the first search metadata.

18. The non-transitory computer readable storage medium of claim 15 , wherein the computer readable program code, when executed by the processor, further causes the computer system to:

save, in a search pattern repository, the search pattern and the first search metadata;

display, in the GUI, a second image generated from a second well log;

receive, for the second image and via the GUI, second search metadata;

determine, by querying the search pattern repository with the second search metadata, that the second search metadata is similar to the first search metadata; and

in response to determining that the second search metadata is similar to the first search metadata:

retrieve, from the search pattern repository and using the first search metadata, the search pattern, and

make a proposal, via the GUI, to perform a second search within the second image using the search pattern.

19. The non-transitory computer readable storage medium of claim 18 , wherein the computer readable program code, when executed by the processor, further causes the computer system to:

receive, via the GUI, an acceptance of the proposal;

in response to receiving the acceptance, perform, using the search pattern, the second search of the second image; and

obtain a second plurality of search results comprising a plurality of portions of the second image matching the search pattern.

20. The non-transitory computer readable storage medium of claim 18 , wherein the computer readable program code, when executed by the processor, further causes the computer system to:

obtain, from the search pattern repository, a plurality of search metadata comprising the first search metadata; and

calculate a plurality of similarity scores between the second search metadata and the plurality of search metadata, wherein the second search metadata is determined to be similar to the first search metadata using the plurality of similarity scores.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (21)