Granted Patent B2

US 12,572,957 · App. 18/498,352 · Granted Mar 10, 2026

Inventors: Hamid Majdabadi (Ottawa, CA); Jeremy R. Fox (Georgetown, TX); Zachary A. Silverstein (Georgetown, TX); Su Liu (Austin, TX)

Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION

G06Q30/0261G06F3/14

Abstract

Claims (61)

1 . A computer-based method of personalizing target content in an outdoor digital display, the method comprising:

receiving an opt-in from a user and digital out-of-home (DOOH) content from one or more Internet of Things (IoT)-enabled digital displays within a pre-defined range of the user, wherein the one or more IoT-enabled digital displays include a digital screen on a subway platform;

causing a mobile device of the user to connect to the one or more IoT-enabled digital displays within the pre-defined range including the digital screen on the subway platform;

identifying one or more target interest parameters associated with the user contained in a profile of the user, wherein identifying the one or more target interest parameters further comprises:

training a recurrent neural network (RNN) to detect the one or more target interest parameters, wherein the RNN is trained to detect a scheduled transaction of the user for which the user is enrolled in autopay; and

utilizing the trained RNN to generate the profile of the user that contains the one or more target interest parameters;

determining whether the DOOH content from at least one IoT-enabled digital display of the one or more IoT-enabled digital displays is relevant to the user based on the identified one or more target interest parameters, wherein the DOOH content from the at least one IoT-enabled digital display includes content displayed on the digital screen on the subway platform captured by a camera embedded in an augmented reality (AR) device of the user, wherein determining whether the DOOH content from the at least one IoT-enabled digital display is relevant to the user further comprises:

detecting, by a convolutional neural network (CNN), one or more objects in the DOOH content from the digital screen on the subway platform, wherein the CNN detects a coupon in the DOOH content associated with the scheduled transaction;

processing, by natural language processing (NLP), text in the DOOH content from the digital screen on the subway platform; and

comparing the detected one or more objects and the processed text in the DOOH content from the digital screen on the subway platform with the identified one or more target interest parameters, wherein the coupon is compared with the scheduled transaction; and

in response to determining the DOOH content from the at least one IoT-enabled digital display is relevant, displaying the DOOH content from the at least one IoT-enabled digital display that is relevant to the user on the connected mobile device of the user, wherein the connected mobile device of the user displaying the relevant DOOH content includes the AR device of the user, wherein displaying the DOOH content from the at least one IoT-enabled digital display that is relevant to the user on the connected mobile device of the user further comprises:

adapting the displayed DOOH content on the connected mobile device of the user including the AR device of the user based on one or more preferences of the user contained in the profile of the user, wherein adapting the displayed DOOH content includes changing a brightness and a color of the DOOH content on the connected mobile device of the user.

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

capturing feedback from the user about the displayed DOOH content; and

updating the profile of the user based on the captured feedback.

3 . The computer-based method of claim 2 , wherein capturing the feedback from the user about the displayed DOOH content further comprises:

capturing negative feedback in a form a thumbs-down by the user.

4 . The computer-based method of claim 2 , wherein capturing the feedback from the user about the displayed DOOH content further comprises:

capturing positive feedback in a form a thumbs-up by the user.

5 . The computer-based method of claim 1 , wherein the target interest parameter is selected from a group consisting of the scheduled transaction, an upcoming reminder, a preference, and an online activity.

6 . A computer system, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable storage medium, and program instructions stored on at least one of the one or more computer-readable storage medium for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:

receiving an opt-in from a user and digital out-of-home (DOOH) content from one or more Internet of Things (IoT)-enabled digital displays within a pre-defined range of the user, wherein the one or more IoT-enabled digital displays include a digital screen on a subway platform;

causing a mobile device of the user to connect to the one or more IoT-enabled digital displays within the pre-defined range including the digital screen on the subway platform;

identifying one or more target interest parameters associated with the user contained in a profile of the user, wherein identifying the one or more target interest parameters further comprises:

training a recurrent neural network (RNN) to detect the one or more target interest parameters, wherein the RNN is trained to detect a scheduled transaction of the user for which the user is enrolled in autopay; and

utilizing the trained RNN to generate the profile of the user that contains the one or more target interest parameters;

determining whether the DOOH content from at least one IoT-enabled digital display of the one or more IoT-enabled digital displays is relevant to the user based on the identified one or more target interest parameters, wherein the DOOH content from the at least one IoT-enabled digital display includes content displayed on the digital screen on the subway platform captured by a camera embedded in an augmented reality (AR) device of the user, wherein determining whether the DOOH content from the at least one IoT-enabled digital display is relevant to the user further comprises:

detecting, by a convolutional neural network (CNN), one or more objects in the DOOH content from the digital screen on the subway platform, wherein the CNN detects a coupon in the DOOH content associated with the scheduled transaction;

processing, by natural language processing (NLP), text in the DOOH content from the digital screen on the subway platform; and

comparing the detected one or more objects and the processed text in the DOOH content from the digital screen on the subway platform with the identified one or more target interest parameters, wherein the coupon is compared with the scheduled transaction; and

in response to determining the DOOH content from the at least one IoT-enabled digital display is relevant, displaying the DOOH content from the at least one IoT-enabled digital display that is relevant to the user on the connected mobile device of the user, wherein the connected mobile device of the user displaying the relevant DOOH content includes the AR device of the user, wherein displaying the DOOH content from the at least one IoT-enabled digital display that is relevant to the user on the connected mobile device of the user further comprises:

adapting the displayed DOOH content on the connected mobile device of the user including the AR device of the user based on one or more preferences of the user contained in the profile of the user, wherein adapting the displayed DOOH content includes changing a brightness and a color of the DOOH content on the connected mobile device of the user.

7 . The computer system of claim 6 , the method further comprising:

capturing feedback from the user about the displayed DOOH content; and

updating the profile of the user based on the captured feedback.

8 . The computer system of claim 7 , wherein capturing the feedback from the user about the displayed DOOH content further comprises:

capturing negative feedback in a form a thumbs-down by the user.

9 . The computer system of claim 7 , wherein capturing the feedback from the user about the displayed DOOH content further comprises:

capturing positive feedback in a form a thumbs-up by the user.

10 . The computer system of claim 6 , wherein the target interest parameter is selected from a group consisting of the scheduled transaction, an upcoming reminder, a preference, and an online activity.

11 . A computer program product, the computer program product comprising:

one or more computer-readable storage medium and program instructions stored on at least one of the one or more computer-readable storage medium, the program instructions executable by a processor capable of performing a method, the method comprising:

receiving an opt-in from a user and digital out-of-home (DOOH) content from one or more Internet of Things (IoT)-enabled digital displays within a pre-defined range of the user, wherein the one or more IoT-enabled digital displays include a digital screen on a subway platform;

causing a mobile device of the user to connect to the one or more IoT-enabled digital displays within the pre-defined range including the digital screen on the subway platform;

identifying one or more target interest parameters associated with the user contained in a profile of the user, wherein identifying the one or more target interest parameters further comprises:

training a recurrent neural network (RNN) to detect the one or more target interest parameters, wherein the RNN is trained to detect a scheduled transaction of the user for which the user is enrolled in autopay; and

utilizing the trained RNN to generate the profile of the user that contains the one or more target interest parameters;

determining whether the DOOH content from at least one IoT-enabled digital display of the one or more IoT-enabled digital displays is relevant to the user based on the identified one or more target interest parameters, wherein the DOOH content from the at least one IoT-enabled digital display includes content displayed on the digital screen on the subway platform captured by a camera embedded in an augmented reality (AR) device of the user, wherein determining whether the DOOH content from the at least one IoT-enabled digital display is relevant to the user further comprises:

detecting, by a convolutional neural network (CNN), one or more objects in the DOOH content from the digital screen on the subway platform, wherein the CNN detects a coupon in the DOOH content associated with the scheduled transaction;

processing, by natural language processing (NLP), text in the DOOH content from the digital screen on the subway platform; and

comparing the detected one or more objects and the processed text in the DOOH content from the digital screen on the subway platform with the identified one or more target interest parameters, wherein the coupon is compared with the scheduled transaction; and

in response to determining the DOOH content from the at least one IoT-enabled digital display is relevant, displaying the DOOH content from the at least one IoT-enabled digital display that is relevant to the user on the connected mobile device of the user, wherein the connected mobile device of the user displaying the relevant DOOH content includes the AR device of the user, wherein displaying the DOOH content from the at least one IoT-enabled digital display that is relevant to the user on the connected mobile device of the user further comprises:

adapting the displayed DOOH content on the connected mobile device of the user including the AR device of the user based on one or more preferences of the user contained in the profile of the user, wherein adapting the displayed DOOH content includes changing a brightness and a color of the DOOH content on the connected mobile device of the user.

12 . The computer program product of claim 11 , the method further comprising:

capturing feedback from the user about the displayed DOOH content; and

updating the profile of the user based on the captured feedback.

13 . The computer program product of claim 12 , wherein capturing the feedback from the user about the displayed DOOH content further comprises:

capturing negative feedback in a form a thumbs-down by the user.

14 . The computer program product of claim 12 , wherein capturing the feedback from the user about the displayed DOOH content further comprises:

capturing positive feedback in a form a thumbs-up by the user.

Assignments (1)

Continuity (1)

References Cited (33)