US 12,135,932 B2
System and method for generating emoji mashups with machine learning
Titus Woo, San Francisco, CA (US); Wei Ting Kuo, San Jose, CA (US); Xueguang Lu, San Jose, CA (US); and Venkatesh Komma, Charlotte, NC (US)
Assigned to PAYPAL, INC., San Jose, CA (US)
Filed by PAYPAL, INC., San Jose, CA (US)
Filed on Aug. 29, 2023, as Appl. No. 18/458,082.
Application 18/458,082 is a continuation of application No. 17/893,015, filed on Aug. 22, 2022, granted, now 11,783,113.
Application 17/893,015 is a continuation of application No. 16/821,891, filed on Mar. 17, 2020, granted, now 11,423,596, issued on Aug. 23, 2022.
Application 16/821,891 is a continuation of application No. 15/790,799, filed on Oct. 23, 2017, granted, now 10,593,087, issued on Mar. 17, 2020.
Prior Publication US 2024/0061991 A1, Feb. 22, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 40/109 (2020.01); G06F 40/166 (2020.01); G06F 40/274 (2020.01); G06N 20/00 (2019.01); G06T 11/60 (2006.01); G06V 10/44 (2022.01); G06F 3/0482 (2013.01); G06F 40/242 (2020.01); G06F 40/30 (2020.01)
CPC G06F 40/109 (2020.01) [G06F 40/166 (2020.01); G06F 40/274 (2020.01); G06N 20/00 (2019.01); G06T 11/60 (2013.01); G06V 10/44 (2022.01); G06F 3/0482 (2013.01); G06F 40/242 (2020.01); G06F 40/30 (2020.01); G06T 2200/24 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computing system comprising:
a non-transitory memory storing instructions; and
one or more hardware processors coupled to the non-transitory memory and configured to read the instructions from the non-transitory memory to cause the computing system to perform operations comprising:
receiving a selection of two emojis for a digital message generated by a first user in a mobile application and transmissible to a second user via the mobile application;
determining emoji image data for the two emojis, wherein the emoji image data comprises at least one object dimension of each of the two emojis when presented in a user interface of the mobile application;
determining context information for a usage of the two emojis in the digital message based on content of the digital message;
determining, using a machine learning model trained using past emoji usage data and an object detection of emojis from the past emoji usage data, a merger of the two emojis based on the emoji image data and the context information;
generating, based on the merger and the emoji image data, a new emoji from the two emojis, wherein the new emoji comprises a single emoji image corresponding to a mashup of the two emojis using the at least one object dimension of each of the two emojis to combine the two emojis in the single emoji image; and
presenting, via the user interface in the mobile application, the new emoji as usable in the content of the digital message.