Granted Patent B2

US 12,488,313 · App. 18/342,045 · Granted Dec 2, 2025

Inventors: Sudhanshu Sekher Sar (Bangalore, IN); Sarbajit K. Rakshit (Kolkata, IN); Sudheesh S. Kairali (Kozhikode, IN); Satyam Jakkula (Bangalore, IN)

Assignee: International Business Machines Corporation

G06Q10/087

Abstract

Claims (76)

1 . A computer-implemented method, comprising:

predicting, by one or more processors of a computer system, using execution of a first trained artificial intelligence model, a product demand of users located in a geographical region over a fixed time period, and delivery location clusters associated with the product demand within the geographical region, wherein

the predicting is based on feeding of input data associated with the users to the first trained artificial intelligence model;

inputting, by the one or more processors, the delivery location clusters into a regression model,

the regression model outputting recommended locations of temporary micro-warehouses within the geographical region based on the delivery location clusters;

training, by the one or more processors, a second artificial intelligence model based on a plurality of emission-based parameters, wherein the training of the second artificial intelligence model comprises:

learning, one or more parameters of the plurality of emission-based parameters that affect an aggregate carbon footprint caused by emissions resulting from transportation to and from the temporary micro-warehouses;

modifying, by the one or more processors, using the second trained artificial intelligence model, the recommended locations based on reducing the aggregate carbon footprint, wherein

the modified recommended locations correspond to optimized locations of the temporary micro-warehouses within the geographical region, and

the second trained artificial intelligence model uses the product demand output by the first trained artificial intelligence model, the recommended locations output from the regression model, and the plurality of emission-based parameters as inputs for the modifying of the recommended locations;

iteratively feeding, by the one or more processors, the optimized locations of the temporary micro-warehouses to the first trained artificial intelligence model along with the input data; and

re-executing the first trained artificial intelligence model based on the input data and the optimized locations of the temporary micro-warehouses, wherein

setting up of the temporary micro-warehouses is performed at the modified recommended locations, and

the temporary micro-warehouses are existing structures within the geographical region.

2 . The computer-implemented method of claim 1 , further comprising:

after the fixed time period expires, leveraging, by the one or more processors, the first trained artificial intelligence model to output a new product demand of the users located within the geographical region and new delivery location clusters;

inputting, by the one or more processors, the new delivery location clusters output by the first trained artificial intelligence model into the regression model, the regression model outputting updated recommended locations of new temporary micro-warehouses within the geographical region; and

using, by the one or more processors, the second trained artificial intelligence model to modify the updated recommended locations and output updated optimized locations based on reducing an aggregate carbon footprint caused by emissions resulting from transportation to and from the new temporary micro-warehouses, wherein the new product demand of the users located in the geographical region output by the first trained artificial intelligence model, the updated recommended locations output from the regression model, and the plurality of emission-based parameters are used as inputs for the second trained artificial intelligence model, wherein the updated optimized locations are different from the optimized locations.

3 . The computer-implemented method of claim 2 , further comprising:

mapping, by the one or more processors, the optimized locations of the temporary micro-warehouses within a mapping platform to display the optimized locations within the geographical region.

4 . The computer-implemented method of claim 3 , further comprising:

updating, by the one or more processors, the mapping platform with the updated optimized locations.

5 . The computer-implemented method of claim 1 , wherein the plurality of emission-based parameters includes road conditions, weather conditions, traffic conditions, an emission factor for a transport mode, a vehicle category of a user of the users, a type of vehicle, and customer preferences with respect to carbon emissions.

6 . The computer-implemented method of claim 1 , wherein the temporary micro-warehouses are capable of warehousing a product associated with the product demand.

7 . The computer-implemented method of claim 1 , wherein the fixed time period is selected from the group consisting of one or more days, one or more weeks, one or more months, and one or more years.

8 . A computer program product for optimizing locations of temporary micro-warehouses that minimize an aggregate carbon footprint within a geographical region, the computer program product comprising a computer readable hardware storage medium having program instructions embodied therewith, the program instructions readable by one or more processors of a computer system to cause the one or more processors to:

predict, by use a first trained artificial intelligence model, a product demand of users located in the geographical region over a fixed time period, and delivery location clusters associated with the product demand within the geographical region, wherein

the prediction is based on input data associated with the users fed to the first trained artificial intelligence model;

input the delivery location clusters into a regression model, wherein the regression model outputs recommended locations of the temporary micro-warehouses within the geographical region based on the delivery location clusters;

train a second artificial intelligence model based on a plurality of emission-based parameters, wherein the training of the second artificial intelligence model causes the one or more processors to:

learn, one or more parameters of the plurality of emission-based parameters that affect the aggregate carbon footprint caused by emissions that result from transportation to and from the temporary micro-warehouses;

modify, using the second trained artificial intelligence model, the recommended locations based on reduction of the aggregate carbon footprint, wherein

the modified recommended locations correspond to optimized locations of the temporary micro-warehouses within the geographical region, and

the second trained artificial intelligence model uses the product demand output by the first trained artificial intelligence model, the recommended locations output from the regression model, and the plurality of emission-based parameters as inputs for the modification of the recommended locations;

iteratively feed the optimized locations of the temporary micro-warehouses to the first trained artificial intelligence model along with the input data; and

re-execute the first trained artificial intelligence model based on the input data and the optimized locations of the temporary micro-warehouses, wherein

the temporary micro-warehouses are set up at the modified recommended locations, and

the temporary micro-warehouses are existing structures within the geographical region.

9 . The computer program product of claim 8 , wherein the program instructions further cause the one or more processors to:

after the fixed time period expires, leverage the first trained artificial intelligence model to output a new product demand of the users located within the geographical region and new delivery location clusters;

input the new delivery location clusters output by the first trained artificial intelligence model into the regression model, the regression model outputs updated recommended locations of new temporary micro-warehouses within the geographical region; and

use the second trained artificial intelligence model to modify the updated recommended locations and output updated optimized locations based on reduction of an aggregate carbon footprint caused by emissions from transportation to and from the new temporary micro-warehouses, wherein the new product demand of the users located in the geographical region output by the first trained artificial intelligence model, the updated recommended locations output from the regression model, and the plurality of emission-based parameters are used as inputs for the second trained artificial intelligence model, wherein the updated optimized locations are different from the optimized locations.

10 . The computer program product of claim 9 , wherein the program instructions further cause the one or more processors to:

map the optimized locations of the temporary micro-warehouses within a mapping platform to display the optimized locations within the geographical region.

11 . The computer program product of claim 10 , wherein the program instructions further cause the one or more processors to:

update the mapping platform with the updated optimized locations.

12 . The computer program product of claim 8 , wherein the plurality of emission-based parameters includes road conditions, weather conditions, traffic conditions, an emission factor for a transport mode, a vehicle category of a user of the users, a type of vehicle, and customer preferences with respect to carbon emissions.

13 . The computer program product of claim 8 , wherein the temporary micro-warehouses are capable of warehousing a product associated with the product demand.

14 . The computer program product of claim 8 , wherein the fixed time period is selected from the group consisting of one or more days, one or more weeks, one or more months, and one or more years.

15 . A computer system, comprising:

one or more computer processors;

one or more computer readable storage media; and

computer readable code stored collectively in the one or more computer readable storage media, with the computer readable code including data and instructions to cause the one or more computer processors to perform at least operations comprising:

predicting, using execution of a first trained artificial intelligence model, a product demand of users located in a geographical region over a fixed time period, and delivery location clusters associated with the product demand within the geographical region, wherein

the predicting is based on feeding of input data associated with the users to the first trained artificial intelligence model;

inputting the delivery location clusters into a regression model,

the regression model outputting recommended locations of temporary micro-warehouses within the geographical region based on the delivery location clusters;

training a second artificial intelligence model based on a plurality of emission-based parameters, wherein the training of the second artificial intelligence model comprises:

learning, one or more parameters of the plurality of emission-based parameters that affect an aggregate carbon footprint caused by emissions resulting from transportation to and from the temporary micro-warehouses;

modifying, using the second trained artificial intelligence model, the recommended locations based on reducing the aggregate carbon footprint, wherein

the modified recommended locations correspond to optimized locations of the temporary micro-warehouses within the geographical region, and

the second trained artificial intelligence model uses the product demand output by the first trained artificial intelligence model, the recommended locations output from the regression model, and the plurality of emission-based parameters as inputs for the modifying of the recommended locations;

iteratively feeding the optimized locations of the temporary micro-warehouses to the first trained artificial intelligence model along with the input data; and

re-executing the first trained artificial intelligence model based on the input data and the optimized locations of the temporary micro-warehouses, wherein

setting up of the temporary micro-warehouses is performed at the modified recommended locations, and

the temporary micro-warehouses are existing structures within the geographical region.

16 . The computer system of claim 15 , the operations further comprising:

after the fixed time period expires, leveraging the first trained artificial intelligence model to output a new product demand of the users located within the geographical region and new delivery location clusters;

inputting the new delivery location clusters output by the first trained artificial intelligence model into the regression model, the regression model outputting updated recommended locations of new temporary micro-warehouses within the geographical region; and

using the second trained artificial intelligence model to modify the updated recommended locations and output updated optimized locations based on reducing an aggregate carbon footprint caused by emissions resulting from transportation to and from the new temporary micro-warehouses, wherein the new product demand of the users located in the geographical region output by the first trained artificial intelligence model, the updated recommended locations output from the regression model, and the plurality of emission-based parameters are used as inputs for the second trained artificial intelligence model, wherein the updated optimized locations are different from the optimized locations.

17 . The computer system of claim 16 , the operations further comprising:

mapping the optimized locations of the temporary micro-warehouses within a mapping platform to display the optimized locations within the geographical region.

18 . The computer system of claim 17 , the operations further comprising:

updating the mapping platform with the updated optimized locations.

19 . The computer system of claim 15 , wherein the plurality of emission-based parameters includes road conditions, weather conditions, traffic conditions, an emission factor for a transport mode, a vehicle category of a user of the users, a type of vehicle, and customer preferences with respect to carbon emissions.

20 . The computer system of claim 15 , wherein the temporary micro-warehouses are capable of warehousing a product associated with the product demand.

Assignments (1)

Continuity (1)

References Cited (13)