Granted Patent B2

US 12,307,381 · App. 17/481,714 · Granted May 20, 2025

Inventors: Manjit Singh Sodhi (Bangalore, IN); Raghuveer Prasad Nagar (Kota, IN); Jagadesh Ramaswamy Hulugundi (Bangalore, IN)

Assignee: International Business Machines Corporation

G06N5/02

Abstract

Claims (78)

1. A computer system implemented method for serving a first user, the method comprising:

gathering, by a computer system, records of sources that each have no website and that the computer system, therefore, deems to be nondigital sources, wherein the gathering includes the computer system receiving identifications of the nondigital sources based on transactions of other users with the respective sources;

training, by the computer system, an artificial intelligence model of images using the transactions of other users with the respective sources;

using image recognition to identify images of individual sources captured from a device of the first user and within the first user's view;

selecting, by the computer system, candidate sources for the first user from among the nondigital sources based on a geolocation of the first user and geolocations of the sources;

selecting, by the computer system, a final source from among the candidate sources, wherein the computer system selecting the final source includes an artificial intelligence model fitting attributes of the candidate sources to attributes valued by the first user; and

presenting the final source to the first user as a recommendation by the computer system.

2. The method of claim 1 , wherein the selecting candidate sources by the computer system includes:

determining a line of sight of the first user via input from sensors in glasses worn by the first user; and

selecting the candidate sources from among ones of the nondigital sources that are within the line of sight.

3. The method of claim 1 , wherein the selecting candidate sources by the computer system includes:

selecting the candidate sources from among ones of the nondigital sources that are within a predefined distance from the first user.

4. The method of claim 1 , wherein the artificial intelligence model fitting attributes of the candidate sources to attributes valued by the first user includes:

an artificial intelligence bagging model computing a fitness measure of the candidate source attributes relative to the source attributes valued by the first user, wherein the bagging model includes linear regression, random forest and support vector machine models.

5. The method of claim 1 , wherein the attributes valued by the user include transaction times at the sources and the method includes:

gathering, by the computer system, records of the transaction times of the other users at the sources;

wherein the selecting the final source includes:

retrieving the transaction times for the candidate sources;

determining a current time of day;

determining an appointed arrival time for the first user at the appointed destination; and

determining an amount of time it will take for the first user to travel to the appointed destination; and

selecting the final source based on whether the gathered transaction times for the final source are short enough to permit the first user to travel to the appointed destination by the appointed arrival time.

6. The method of claim 5 , wherein an instance occurs wherein the computer system determines that the first user has enough time to perform transactions at more than one of the candidate sources and still travel to the appointed destination by the appointed arrival time, and wherein for such an instance the method includes:

selecting, by the computer system, a second final source from among the candidate sources.

7. The method of claim 1 , including:

presenting the candidate sources and attributes of the candidate sources to the first user visually on glasses worn by the first user.

8. A computer system for serving a first user, the system comprising:

a processor; and

a computer readable storage medium connected to the processor, wherein the computer readable storage medium has stored thereon a program for controlling the processor, and wherein the processor is operative with the program to execute the program for:

gathering, by a computer system, records of sources that each have no website and that the computer system, therefore, deems to be nondigital sources, wherein the gathering includes the computer system receiving identifications of the nondigital sources based on transactions of other users with the respective sources;

training, by the computer system, an artificial intelligence model of images using the transactions of other users with the respective sources;

using image recognition to identify images of individual sources captured from a device of the first user and within the first user's view;

selecting, by the computer system, candidate sources from among the nondigital sources based on a geolocation of the first user and geolocations of the sources;

selecting, by the computer system, a final source from among the candidate sources, wherein the computer system selecting the final source includes an artificial intelligence model fitting attributes of the candidate sources to attributes valued by the first user; and

presenting the final source to the first user as a recommendation by the computer system.

9. The computer system of claim 8 , wherein the selecting candidate sources by the computer system includes:

determining a line of sight of the first user via input from sensors in glasses worn by the first user; and

selecting the candidate sources from among ones of the nondigital sources that are within the line of sight.

10. The computer system of claim 8 , wherein the selecting candidate sources by the computer system includes:

selecting the candidate sources from among ones of the nondigital sources that are within a predefined distance from the first user.

11. The computer system of claim 8 , wherein the artificial intelligence model fitting attributes of the candidate sources to attributes valued by the first user includes:

an artificial intelligence bagging model computing a fitness measure of the candidate source attributes relative to the source attributes valued by the first user, wherein the bagging model includes linear regression, random forest and support vector machine models.

12. The computer system of claim 8 , wherein the attributes valued by the user include transaction times at the sources and the processor is operative with the program to execute the program for:

gathering, by the computer system, records of the transaction times of the other users at the sources;

wherein the selecting the final source includes:

retrieving the transaction times for the candidate sources;

determining a current time of day;

determining an appointed arrival time for the first user at the appointed destination; and

determining an amount of time it will take for the first user to travel to the appointed destination; and

selecting the final source based on whether the gathered transaction times for the final source are short enough to permit the first user to travel to the appointed destination by the appointed arrival time.

13. The computer system of claim 12 , wherein an instance occurs wherein the computer system determines that the first user has enough time to perform transactions at more than one of the candidate sources and still travel to the appointed destination by the appointed arrival time, and wherein for such an instance the processor is operative with the program to execute the program for:

selecting, by the computer system, a second final source from among the candidate sources.

14. The computer system of claim 8 , including:

presenting the candidate sources and attributes of the candidate sources to the first user visually on glasses worn by the first user.

15. A computer program product for a computer system serving first user, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

gather, by a computer system, records of sources that each have no website and that the computer system, therefore, deems to be nondigital sources, wherein the gathering includes the computer system receiving identifications of the nondigital sources based on transactions of other users with the respective sources;

train, by the computer system, an artificial intelligence model of images using the transactions of other users with the respective sources;

using image recognition to identify images of individual sources captured from a device of the first user and within the first user's view;

select, by the computer system, candidate sources from among the nondigital sources based on a geolocation of the first user and geolocations of the sources;

select, by the computer system, a final source from among the candidate sources, wherein the computer system selecting the final source includes an artificial intelligence model fitting attributes of the candidate sources to attributes valued by the first user; and

present the final source to the first user as a recommendation by the computer system.

16. The computer program product of claim 15 , wherein the selecting candidate sources by the computer system includes:

determining a line of sight of the first user via input from sensors in glasses worn by the first user; and

selecting the candidate sources from among ones of the nondigital sources that are within the line of sight.

17. The computer program product of claim 15 , wherein the selecting candidate sources by the computer system includes:

selecting the candidate sources from among ones of the nondigital sources that are within a predefined distance from the first user.

18. The computer program product of claim 15 , wherein the artificial intelligence model fitting attributes of the candidate sources to attributes valued by the first user includes:

an artificial intelligence bagging model computing a fitness measure of the candidate source attributes relative to the source attributes valued by the first user, wherein the bagging model includes linear regression, random forest and support vector machine models.

19. The computer program product of claim 15 , wherein the attributes valued by the user include transaction times at the sources and the program instructions are executable by the processor to cause the processor to:

gather, by the computer system, records of the transaction times of the other users at the sources;

wherein the selecting the final source includes:

retrieving the transaction times for the candidate sources;

determining a current time of day;

determining an appointed arrival time for the first user at the appointed destination; and

determining an amount of time it will take for the first user to travel to the appointed destination; and

selecting the final source based on whether the gathered transaction times for the final source are short enough to permit the first user to travel to the appointed destination by the appointed arrival time.

20. The computer program product of claim 19 , wherein an instance occurs wherein the computer system determines that the first user has enough time to perform transactions at more than one of the candidate sources and still travel to the appointed destination by the appointed arrival time, and wherein for such an instance the program instructions are executable by the processor to cause the processor to:

select, by the computer system, a second final source from among the candidate sources.

Assignments (1)

Continuity (1)

References Cited (14)