Filtering group messages

Patent metadata

Field	Value
Publication number	US-11843569-B2
Application number	US-202217937998-A
Country	US
Kind code	B2
Filing date	Oct 4, 2022
Priority date	Oct 6, 2019
Publication date	Dec 12, 2023
Grant date	Dec 12, 2023

Abstract

An example system includes a processor to train an artificial intelligence (AI) model on a training set of images on a client device associated with a particular user. Images in the training set of images are selected using face recognition from a digital camera roll on the client device based on a set of faces chosen by the particular user of the client device. All of images in the training set of images include a detected face from the set of chosen faces. The processor is to filter a group message received from a second device based on the trained AI model.

First claim

What is claimed is:

1. A system, comprising a processor to:
train an artificial intelligence (AI) model on a training set of images on a client device associated with a particular user, wherein images in the training set of images are selected using face recognition from a digital camera roll on the client device based on a set of faces chosen by the particular user of the client device, wherein all of images in the training set of images used to_train the AI model comprise a detected face from the set of chosen faces; and
filter, at the client device, a group message received from a second device via a social messaging server based on the trained AI model, wherein the client device and the second device correspond to users of a same group of a social messaging application, and wherein the received group message is deleted from the client device without being displayed at the client device in response to detecting that not any of the set of chosen faces is detected.

2. The system of claim 1 , wherein the filtered group message is prevented from being displayed to the user in response to detecting that the filtered group message is incompatible with rules of the AI model.

3. The system of claim 1 , wherein filtering the group message comprises deleting the group message from the client device.

4. The system of claim 1 , wherein the processor is to save a group message to storage in response to detecting that the group message is compatible with rules of the trained AI model.

5. The system of claim 1 , wherein the second device comprises a social messaging server.

6. The system of claim 1 , wherein the AI model is also trained on user-provided text expressions.

7. The system of claim 1 , wherein the client device comprises an edge device communicatively coupled to a cloud service executed by the processor.

8. A computer-implemented method, comprising:
training, via a processor at a client device, an artificial intelligence (AI) model on a training set of images on the client device associated with a particular user, wherein images in the training set of images are selected using face recognition from a digital camera roll on the client device based on a set of faces chosen by the particular user of the client device, wherein all of images in the training set of images used to train the AI model comprise a detected face from the set of chosen faces; and
filtering, via the processor, a group message received from a second device via a social messaging server based on the trained AI model, wherein the client device and the second device correspond to users of a same group of a social messaging application, and wherein the received group message is deleted from the client device without being displayed at the client device in response to detecting that not any of the set of chosen faces is detected.

9. The computer-implemented method of claim 8 , comprising preventing the filtered group message from being displayed to the user in response to detecting that the filtered group message is incompatible with rules of the AI model.

10. The computer-implemented method of claim 8 , wherein filtering the group message comprises deleting the filtered group message from the client device.

11. The computer-implemented method of claim 8 , comprising saving the group message to storage in response to detecting that the group message is compatible with rules of the trained AI model.

12. The computer-implemented method of claim 8 , wherein training the AI model comprises training the AI model using media associated with a particular group, wherein group messages from the particular group are filtered using the AI model.

13. The computer-implemented method of claim 8 , comprising presenting media to a user via the client device and receiving a selection of relevant media from the user.

14. The computer-implemented method of claim 8 , comprising presenting filtered group messages via the client device in response to detecting that the filtered group messages are compatible with rules of the trained AI model.

15. A computer program product for filtering group messages, the computer program product comprising a computer-readable storage medium having program code embodied therewith, the program code executable by a processor to cause the processor to:
train an artificial intelligence (AI) model on a training set of images on a client device associated with a particular user, wherein images in the training set of images are selected using face recognition from a digital camera roll on the client device based on a set of faces chosen by the particular user of the client device, wherein all of images in the training set of images used to train the AI model comprise a detected face from the set of chosen faces; and
filter, at the client device, a group message received from a second device via a social messaging server based on the trained AI model, wherein the client device and the second device correspond to users of a same group of a social messaging application, and wherein the received group message is deleted from the client device without being displayed at the client device in response to detecting that not any of the set of chosen faces is detected.

16. The computer program product of claim 15 , further comprising program code executable by the processor to prevent the filtered group message from being displayed to the user in response to detecting that the filtered group message is incompatible with rules of the AI model.

17. The computer program product of claim 15 , further comprising program code executable by the processor to delete the group message from the client device in response to detecting that the group message is incompatible with rules of the AI model.

18. The computer program product of claim 15 , further comprising program code executable by the processor to train the AI model using media associated with a particular group, wherein group messages from the particular group are to be filtered using the AI model.

19. The computer program product of claim 15 , further comprising program code executable by the processor to present media to the user via the client device and receive a selection of relevant media from the user.

20. The computer program product of claim 15 , further comprising program code executable by the processor to present filtered group messages via the client device in response to detecting that the filtered group messages are compatible with rules of the trained AI model.

Assignees

• IBM

Inventors

• Sharon Gil
• Guy Nili

Classifications

• H04L51/212 Primary

  using filtering or selective blocking · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06V40/172

  Classification, e.g. identification · CPC title

• G06V40/174

  Facial expression recognition · CPC title