Granted Patent B2

US 12,647,421 · App. 18/378,062 · Granted Jun 2, 2026

Inventors: Syed Najumudeen (Hyderabad, IN); Dalydas Karanath (Thrissur, IN); Aravinth Selvamani (Chennai, IN)

Assignee: BANK OF AMERICA CORPORATION

H04L63/10

Abstract

Claims (47)

1 . A system for maintaining security of virtual objects in a distributed network, the system comprising:

a first artificial intelligence engine configured to determine motives of users associated with avatars in a virtual world;

a second artificial intelligence engine configured to determine access paths of the avatars in the virtual world;

a third artificial intelligence engine configured to generate visual content based on attributes of the users, the motives of the users, and the access paths of the avatars;

a processing device; and

a non-transitory storage device comprising computer program code stored thereon, wherein the computer program code comprises computer instructions configured to cause the processing device to:

determine, in response to an avatar entering the virtual world and using the first artificial intelligence engine, motives of a user associated with the avatar;

determine, based on the motives of the user and using the second artificial intelligence engine, access paths of the avatar in the virtual world, wherein the second artificial intelligence engine comprises a neuro meta intelligent framework (NMIF);

generate, based on attributes of the user, the motives of the user, the access paths of the avatar, and using the third artificial intelligence engine, user-specific visual content to be rendered in the virtual world for viewing by the user, wherein the attributes of the user comprise privileges of the user, and wherein the user-specific visual content (i) omits information that the user is not privileged to view and (ii) comprises normalizing visual content that, when rendered by the user device, makes the virtual world appear normal to the user despite the omitted information;

cause a user device associated with the user to render the user-specific visual content in the virtual world;

detect a diversion from the access paths by the avatar;

determine, based on detecting the diversion and using the first artificial intelligence engine, updated motives of the user;

determine, based on the attributes of the user and based on the updated motives of the user, whether the diversion from the access paths is permissible; and

restrict, based on determining that the diversion from the access paths is not permissible, movement of the avatar within the virtual world.

2 . The system of claim 1 , wherein the omitted information comprises at least one of an object in the virtual world, confidential information, another avatar in the virtual world, or another access path.

3 . The system of claim 1 , wherein the omitted information is viewable by other users associated with other avatars in the virtual world.

4 . The system of claim 1 , wherein the computer program code comprises computer instructions configured to cause the processing device to, when determining the motives of the user, determine the motives of the user based on metadata associated with the avatar in a database.

5 . The system of claim 1 , wherein the computer program code comprises computer instructions configured to cause the processing device to update, based on the attributes of the user, the updated motives of the user, updated access paths of the avatar, and using the third artificial intelligence engine, the visual content to be rendered in the virtual world for viewing by the user.

6 . The system of claim 5 , wherein the computer program code comprises computer instructions configured to cause the processing device to cause the user device associated with the user to render the updated visual content in the virtual world.

7 . The system of claim 1 , wherein the system comprises the user device, wherein the user device comprises a display, and wherein the computer program code comprises computer instructions configured to cause the processing device to, when causing the user device associated with the user to render the user-specific visual content in the virtual world, render the user-specific visual content in the virtual world on the display.

8 . The system of claim 7 , wherein the user device comprises a control interface, and wherein the computer program code comprises computer instructions configured to cause the processing device to, when causing the user device associated with the user to render the user-specific visual content in the virtual world, provide haptic feedback to the user via the control interface as the user interacts with the virtual world.

9 . A computer program product for maintaining security of virtual objects in a distributed network, the computer program product comprising a non-transitory computer-readable medium comprising code causing an apparatus to:

determine, in response to an avatar entering a virtual world and using a first artificial intelligence engine, motives of a user associated with the avatar, wherein the first artificial intelligence engine is configured to determine motives of users associated with avatars in the virtual world;

determine, based on the motives of the user and using a second artificial intelligence engine, access paths of the avatar in the virtual world, wherein the second artificial intelligence engine is configured to determine access paths of the avatars in the virtual world, and wherein the second artificial intelligence engine comprises a neuro meta intelligent framework (NMIF);

generate, based on attributes of the user, the motives of the user, the access paths of the avatar, and using a third artificial intelligence engine, user-specific visual content to be rendered in the virtual world for viewing by the user, wherein the third artificial intelligence engine is configured to generate visual content based on attributes of the users, the motives of the users, and the access paths of the avatars, wherein the attributes of the user comprise privileges of the user, and wherein the user-specific visual content (i) omits information that the user is not privileged to view and (ii) comprises normalizing visual content that, when rendered by the user device, makes the virtual world appear normal to the user despite the omitted information;

cause a user device associated with the user to render the user-specific visual content in the virtual world;

detect a diversion from the access paths by the avatar;

determine, based on detecting the diversion and using the first artificial intelligence engine, updated motives of the user;

determine, based on the attributes of the user and based on the updated motives of the user, whether the diversion from the access paths is permissible; and

restrict, based on determining that the diversion from the access paths is not permissible, movement of the avatar within the virtual world.

10 . The computer program product of claim 9 , wherein the omitted information comprises at least one of an object in the virtual world, confidential information, another avatar in the virtual world, or another access path.

11 . The computer program product of claim 9 , wherein the omitted information is viewable by other users associated with other avatars in the virtual world.

12 . The computer program product of claim 9 , wherein the non-transitory computer-readable medium comprises code causing the apparatus to, when determining the motives of the user, determine the motives of the user based on metadata associated with the avatar in a database.

13 . The computer program product of claim 9 , wherein the non-transitory computer-readable medium comprises code causing the apparatus to, when determining whether the diversion from the access paths is permissible, filter, based on the attributes of the user and based on the updated motives of the user, all possible paths to determine whether the diversion from the access paths is permissible.

14 . A method for maintaining security of virtual objects in a distributed network, the method comprising:

determining, in response to an avatar entering a virtual world and using a first artificial intelligence engine, motives of a user associated with the avatar, wherein the first artificial intelligence engine is configured to determine motives of users associated with avatars in the virtual world;

determining, based on the motives of the user and using a second artificial intelligence engine, access paths of the avatar in the virtual world, wherein the second artificial intelligence engine is configured to determine access paths of the avatars in the virtual world, and wherein the second artificial intelligence engine comprises a neuro meta intelligent framework (NMIF;

generating, based on attributes of the user, the motives of the user, the access paths of the avatar, and using a third artificial intelligence engine, user-specific visual content to be rendered in the virtual world for viewing by the user, wherein the third artificial intelligence engine is configured to generate visual content based on attributes of the users, the motives of the users, and the access paths of the avatars, wherein the attributes of the user comprise privileges of the user, and wherein the user-specific visual content (i) omits information that the user is not privileged to view and (ii) comprises normalizing visual content that, when rendered by the user device, makes the virtual world appear normal to the user despite the omitted information;

causing a user device associated with the user to render the user-specific visual content in the virtual world;

detecting a diversion from the access paths by the avatar;

determining, based on detecting the diversion and using the first artificial intelligence engine, updated motives of the user;

determining, based on the attributes of the user and based on the updated motives of the user, whether the diversion from the access paths is permissible; and

restricting, based on determining that the diversion from the access paths is not permissible, movement of the avatar within the virtual world.

15 . The system of claim 1 , wherein the NMIF comprises a convolution neural network (CNN) comprising N layers, and wherein the computer program code comprises computer instructions configured to cause the processing device to:

build, via the CNN and based on the updated motives of the user and based on a frame being viewed by the avatar, a sequence of all possible access paths of the avatar; and

output the sequence of all possible access paths of the avatar from a Softmax layer of the N layers of the CNN.

16 . The system of claim 15 , wherein the computer program code comprises computer instructions configured to cause the processing device to, when determining whether the diversion from the access paths is permissible, filter, based on the attributes of the user and based on the updated motives of the user, permissible access paths of the sequence of all possible paths to determine whether the diversion from the access paths is permissible.

Assignments (1)

Continuity (1)

References Cited (49)