Granted Patent B1

US 12,373,091 · App. 16/377,998 · Granted Jul 29, 2025

Inventors: Machiraju Pakasasana Rama Rao (Hyderabad, IN); Arun Raj Parwana Adiraju (Hyderabad, IN); Pawan Kumar Singh (Hyderabad, IN); Abhinav Kishore (Hyderabad, IN); Vineet Chaudhary (Hyderabad, IN)

Assignee: Blue Yonder Group, Inc.

G06F3/0487G06Q10/10G06F3/013G06F3/017G06F3/03543G06F3/0488G06F3/0489G06F3/167

Abstract

Claims (65)

1. A system for assortment planning for products, comprising an assortment planner communicatively coupled to an inventory system over a network, the assortment planner further comprising:

a computer coupled with a database and comprising a processor and memory, the computer configured to:

monitor two or more modes of user inputs using one or more sensors and one or more tactile interface devices;

detect at least two modes of user input and store the at least two modes of user inputs in the database;

evaluate the stored user inputs in the database and the at least two modes of user input by deriving an inference based on determining whether a multinomial model or a Bernoulli model provides a better predictive model of the stored user inputs and based on applying a singular threshold duration to a mode of the at least two modes of user input;

predict a system action based on the derived inference, wherein the system action is directed to assortment planning;

generate the system action based on the prediction derived from the inference and the one or more stored user inputs;

monitor user input in response to the generated system action;

execute the user input instead of the generated system action based on a prioritization;

evaluate the monitored user input to adjust the predictive model based at least in part on a number of negative responses to the generated system action;

generate a product assortment by indicating the products that will be included or excluded in the product assortment for a particular planning period based on data regarding sales, profitability, transferable demand or similarity, for any one or more products or assortments; and

calculate a purchase quantity of items in the product assortment and place an order based on the product assortment.

2. The system of claim 1 , wherein the computer is further configured to:

track a user's identity throughout subsequent user interactions;

detect an additional user input;

store the additional user input in the database;

evaluate the stored additional user input in the database and the at least two modes of user input to generate a subsequent system action tailored to the identified user; and

generate a subsequent system action based on predicting a user action and the user's determined identity.

3. The system of claim 2 , wherein the computer is further configured to identify, track, and generate system actions for multiple users simultaneously.

4. The system of claim 1 , wherein the system action comprises one or more of generating a personalized application, opening a workspace, and rendering data for display.

5. The system of claim 1 , wherein the one or more sensors comprise one or more of an imaging sensor, a radio receiver, and a microphone.

6. The system of claim 1 , wherein the user input comprises one or more of keyboard input, mouse input, touch input, voice input, gestures, and eye movement.

7. A computer-implemented method for assortment planning for products, comprising:

providing a system comprising an assortment planner communicatively coupled to an inventory system over a network, wherein the assortment planner comprises a database and a computer, the computer comprising a processor and memory;

monitoring, using one or more sensors and one or more tactile interface devices, two or more modes of user inputs to the system;

detecting at least two modes of user input and storing the at least two modes of user inputs in the database;

evaluating the stored user inputs in the database and the at least two modes of user input by deriving an inference based on determining whether a multinomial model or a Bernoulli model provides a better predictive model of the stored user inputs and based on applying a singular threshold duration to a mode of the at least two modes of user input;

predicting a system action based on the derived inference, wherein the system action is directed to assortment planning;

generating the system action based on the prediction derived from the inference and the one or more stored user inputs;

monitoring user input in response to the generated system action;

executing the user input instead of the generated system action based on a prioritization;

evaluating the monitored user input to adjust the predictive model based at least in part on a number of negative responses to the generated system action;

generating a product assortment by indicating the products that will be included or excluded in the product assortment for a particular planning period based on data regarding sales, profitability, transferable demand or similarity, for any one or more products or assortments; and

calculating a purchase quantity of items in the product assortment and placing an order based on the product assortment.

8. The computer-implemented method of claim 7 , further comprising:

tracking a user's identity throughout subsequent user interactions;

detecting an additional user input;

storing the additional user input in the database;

evaluating the stored additional user input in the database and the at least two modes of user input to generate a subsequent system action tailored to the identified user; and

generating a subsequent system action based on predicting a user action and the user's determined identity.

9. The computer-implemented method of claim 8 , further comprising:

identifying, tracking, and generating system actions for multiple users simultaneously.

10. The computer-implemented method of claim 7 , wherein the system action comprises one or more of generating a personalized application, opening a workspace, and rendering data for display.

11. The computer-implemented method of claim 7 , wherein the one or more sensors comprise one or more of an imaging sensor, a radio receiver, and a microphone.

12. The computer-implemented method of claim 7 , wherein the user input comprises on or more of keyboard input, mouse input, touch input, voice input, gestures, and eye movement.

13. A non-transitory computer-readable storage medium embodied with software for assortment planning for products, the software when executed configured to:

monitor, using one or more sensors and one or more tactile interface devices, two or more modes of user inputs to a system, the system comprising an assortment planner communicatively coupled to an inventory system over a network, wherein the assortment planner comprises a database and a computer, the computer comprising a processor and memory;

detect at least two modes of user input and store the at least two modes of user inputs in the database;

evaluate the stored user inputs in the database and the at least two modes of user input by deriving an inference based on determining whether a multinomial model or a Bernoulli model provides a better predictive model of the stored user inputs and based on applying a singular threshold duration to a mode of the at least two modes of user input;

predict a system action based on the derived inference, wherein the system action is directed to assortment planning;

generate the system action based on the prediction derived from the inference and the one or more stored user inputs;

monitor user input in response to the generated system action; execute the user input instead of the generated system action based on a prioritization;

evaluate the monitored user input to adjust the predictive model based at least in part on a number of negative responses to the generated system action;

generate a product assortment by indicating the products that will be included or excluded in the product assortment for a particular planning period based on data regarding sales, profitability, transferable demand or similarity, for any one or more products or assortments; and

calculate a purchase quantity of items in the product assortment and place an order based on the product assortment.

14. The non-transitory computer-readable storage medium of claim 13 , wherein the software is further configured to:

track a user's identity throughout subsequent user interactions;

detect an additional user input;

store the additional user input in the database;

evaluate the stored additional user input in the database and the at least two modes of user input to generate a subsequent system action tailored to the identified user; and

generate a subsequent system action based on predicting a user action and the user's determined identity.

15. The non-transitory computer-readable storage medium of claim 14 , wherein the software is further configured to identify, track, and generate system actions for multiple users simultaneously.

16. The non-transitory computer-readable storage medium of claim 13 , wherein the system action comprises one or more of generating a personalized application, opening a workspace, and rendering data for display.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the one or more sensors comprise one or more of an imaging sensor, a radio receiver, and a microphone.

18. The non-transitory computer-readable storage medium of claim 13 , wherein the user input comprises on or more of keyboard input, mouse input, touch input, voice input, gestures, and eye movement.

Assignments (5)

Continuity (1)

References Cited (85)