IP Library › Granted Patent US 12,572,738
Granted Patent B2
US 12,572,738 · App. 18/428,431 · Granted Mar 10, 2026

Emoji understanding in online experiences

Inventors: Dishan Gupta (Campbell, CA); Ajinkya Gorakhnath Kale (San Jose, CA); Stefan Boyd Schoenmackers (El Paso, TX); Amit Srivastava (San Jose, CA)
Assignee: eBay Inc.
G06F40/274G06F40/279G06V30/194
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,572,738
App. No.
18/428,431
Filed
Jan 31, 2024
Granted
Mar 10, 2026
Kind
B2
Art Unit
2658
USPC
704/9
Abstract

Understanding emojis in the context of online experiences is described. In at least some embodiments, text input is received and a vector representation of the text input is computed. Based on the vector representation, one or more emojis that correspond to the vector representation of the text input are ascertained and a response is formulated that includes at least one of the one or more emojis. In other embodiments, input from a client machine is received. The input includes at least one emoji. A computed vector representation of the emoji is used to look for vector representations of words or phrases that are close to the computed vector representation of the emoji. At least one of the words or phrases is selected and at least one task is performed using the selected word(s) or phrase(s).

Claims (34)

1 . A method comprising:

receiving, by a network-based provider and over a network, user input including one or more emojis;

using, by the network-based provider, a computed vector representation representing the one or more emojis, in which the computed vector representation representing the one or more emojis is generated by a trained model configured to update parameters of the trained model based on additional data, to determine computed vector representations representing words or phrases that are close to the computed vector representation representing the one or more emojis;

selecting, by the network-based provider, at least one of the words or phrases of the vector representations representing the words or phrases that are close to the computed vector representation representing the one or more emojis; and

based on the at least one of the words or phrases selected of the vector representations representing the words or phrases that are close to the computed vector representation representing the one or more emojis, performing, by the network-based provider, a task for display by a user interface, in which the task is associated with the at least one of the words or phrases selected.

2 . The method as described in claim 1 , wherein the one or more emojis are received via a message provided by a user using a network application on a client machine.

3 . The method as described in claim 2 , wherein the message is associated with an experience.

4 . The method of claim 2 , wherein the network application is a listing application.

5 . The method as described in claim 1 , wherein the network-based provider provides online experiences.

6 . The method as described in claim 1 , wherein the task is a formulated response message.

7 . The method as described in claim 6 , wherein the formulated response message includes at least one additional emoji.

8 . A computing device comprising:

a processing system; and

a computer-readable storage medium having instructions stored that, responsive to execution by the processing system, causes the processing system to perform operations comprising:

receiving user input including one or more emojis;

using a computed vector representation representing the one or more emojis to determine computed vector representations representing words or phrases that are close to the computed vector representation representing the one or more emojis;

selecting at least one of the words or phrases of the vector representations representing the words or phrases that are close to the computed vector representation representing the one or more emojis; and

based on the at least one of the words or phrases selected of the vector representations representing the words or phrases that are close to the computed vector representation representing the one or more emojis, performing a task for display by a user interface, in which the task is associated with the at least one of the words or phrases selected.

9 . The computing device as described in claim 8 , wherein the one or more emojis are received via a message provided by a user using a network application on a client machine.

10 . The computing device as described in claim 9 , wherein the message is associated with an interactive shopping experience.

11 . The computing device as described in claim 9 , wherein the message includes text along with the one or more emojis.

12 . The computing device as described in claim 9 , wherein the message corresponds to a search.

13 . The computing device as described in claim 8 , wherein the task is a formulated response message.

14 . The computing device as described in claim 13 , wherein the formulated response message is communicated via a bot.

15 . The computing device as described in claim 8 , wherein the computed vector representation representing the one or more emojis is generated by a trained model configured to re-train the trained model based on additional data.

16 . A non-transitory computer-readable storage medium encoding computer executable instructions that, when executed by a processing unit, perform operations comprising:

receiving user input including one or more emojis;

using a computed vector representation representing the one or more emojis to determine computed vector representations representing words or phrases that are close to the computed vector representation representing the one or more emojis;

selecting at least one of the words or phrases that are close to the computed vector representation representing the one or more emojis; and

based on the at least one of the words or phrases selected of the vector representations representing the words or phrases that are close to the computed vector representation representing the one or more emojis, performing a task for display by a user interface, in which the task is associated with the at least one of the words or phrases selected.

17 . The non-transitory computer-readable storage medium as described in claim 16 , wherein the one or more emojis are received via a message provided by a user using a network application on a client machine.

18 . The non-transitory computer-readable storage medium as described in claim 17 , wherein the message includes text along with the one or more emojis.

19 . The non-transitory computer-readable storage medium as described in claim 18 , wherein the task is a formulated response message.

20 . The non-transitory computer-readable storage medium as described in claim 16 , wherein the task is a search.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 7, 2024
From: GUPTA, DISHAN; KALE, AJINKYA GORAKHNATH; SCHOENMACKERS, STEFAN BOYD; SRIVASTAVA, AMIT
To: EBAY INC.
Reel/Frame 066400/0617 →
Continuity (4)
Continuation 18120557 · Mar 13, 2023
Continuation 16799681 · Feb 24, 2020
Continuation 15665133 · Jul 31, 2017
Related Publication 20240169151A1 · May 23, 2024
References Cited (77)
US 9792903B2 · Kim et al. · 2017 [cited by applicant]
US 10311144B2 · Bellegarda et al. · 2019 [cited by applicant]
US 10387571B2 · Baldwin et al. · 2019 [cited by applicant]
US 10404636B2 · Rodriguez et al. · 2019 [cited by applicant]
US 10635695B2 · Seth et al. · 2020 [cited by applicant]
US 10650095B2 · Gupta et al. · 2020 [cited by applicant]
US 11070879B2 · Wu et al. · 2021 [cited by applicant]
US 11240179B2 · Mishra et al. · 2022 [cited by applicant]
US 11636265B2 · Gupta et al. · 2023 [cited by applicant]
US 11928428B2 · Gupta et al. · 2024 [cited by applicant]
US 20090164914A1 · Chen · 2009 [cited by applicant]
US 20110093272A1 · Isobe et al. · 2011 [cited by applicant]
US 20110273455A1 · Powar et al. · 2011 [cited by applicant]
US 20140088954A1 · Shirzadi et al. · 2014 [cited by applicant]
US 20150100537A1 · Grieves et al. · 2015 [cited by applicant]
US 20150121248A1 · Levin et al. · 2015 [cited by applicant]
US 20150154251A1 · Cockcroft et al. · 2015 [cited by applicant]
US 20150286371A1 · Degani · 2015 [cited by applicant]
US 20160343062A1 · Morton et al. · 2016 [cited by applicant]
US 20170052946A1 · Gu et al. · 2017 [cited by applicant]
US 20170118189A1 · Venkatakrishnan et al. · 2017 [cited by applicant]
US 20170134313A1 · Poupart et al. · 2017 [cited by applicant]
US 20170185581A1 · Bojja et al. · 2017 [cited by applicant]
US 20170213138A1 · Bojja et al. · 2017 [cited by applicant]
US 20180021087A1 · Anderson et al. · 2018 [cited by applicant]
US 20180024726A1 · Hviding · 2018 [cited by examiner]
US 20180061400A1 · Carbune et al. · 2018 [cited by applicant]
US 20180189628A1 · Kaufmann · 2018 [cited by examiner]
US 20180210874A1 · Fuxman et al. · 2018 [cited by applicant]
US 20180300542A1 · Waddell · 2018 [cited by examiner]
US 20190034412A1 · Gupta et al. · 2019 [cited by applicant]
US 20200210645A1 · Gupta et al. · 2020 [cited by applicant]
US 20230214590A1 · Gupta et al. · 2023 [cited by applicant]
CN 104050287 · 2014 [cited by applicant]
CN 104063427 · 2014 [cited by applicant]
CN 105160033 · 2015 [cited by applicant]
KR 100474014 · 2005 [cited by applicant]
KR 1004740140000 · 2005 [cited by applicant]
KR 20150068457 · 2015 [cited by applicant]
KR 1020160093694 · 2016 [cited by applicant]
KR 20160142865 · 2016 [cited by applicant]
KR 1020160142865 · 2016 [cited by applicant]
KR 1020150068457 · 2025 [cited by applicant]
WO WO2019027772 · 2019 [cited by applicant]
, “Dango-Emoji & Deep Learning”, Retrieved from the Internet: https://web.archive.org/web/20170719141718/https://getdango.com/emoji-and-deep-learning/, Jul. 19, 2017, 11 Pages. [cited by applicant]
, “Final Office Action”, U.S. Appl. No. 15/665,133, filed Mar. 4, 2019, 11 pages. [cited by applicant]
, “Final Office Action”, U.S. Appl. No. 15/665,133, filed Oct. 10, 2019, 12 pages. [cited by applicant]
, “Final Office Action”, U.S. Appl. No. 16/799,681, filed Mar. 29, 2022, 17 pages. [cited by applicant]
, “International Preliminary Report on Patentability”, Application No. PCT/US2018/043765, Feb. 13, 2020, 8 pages. [cited by applicant]
, “International Search Report and Written Opinion”, Application No. PCT/US2018/043765, Oct. 10, 2018, 12 pages. [cited by applicant]
, “Non-Final Office Action”, U.S. Appl. No. 15/665,133, filed Sep. 20, 2018, 11 pages. [cited by applicant]
, “Non-Final Office Action”, U.S. Appl. No. 15/665,133, filed May 15, 2019, 12 pages. [cited by applicant]
, “Notice of Allowance”, U.S. Appl. No. 15/665,133, filed Jan. 10, 2020, 8 pages. [cited by applicant]
, “Response to Final Office Action”, U.S. Appl. No. 15/665,133, filed Dec. 9, 2019, 14 pages. [cited by applicant]
, “Response to Final Office Action”, U.S. Appl. No. 16/799,681, filed Mar. 27, 2019, 28 pages. [cited by applicant]
, “Response to Non-Final Office Action”, U.S. Appl. No. 15/665,133, filed Aug. 9, 2019, 12 pages. [cited by applicant]
, “Response to Non-Final Office Action”, U.S. Appl. No. 15/665,133, filed Dec. 20, 2018, 40 pages. [cited by applicant]
, “Teaching Robots to Feel: Emoji & Deep Learning”, https://web.archive.org/web/20180906210258/https://getdango.com/emoji-and-deep-learning/, Jul. 19, 2017, 12 pages. [cited by applicant]
10-2020-7002616, , “Notice Of Allowance received for Korean Patent Application No. 10-2020-7002616, mailed on Sep. 28, 2021”, Sep. 28, 2021, 4 Pages. [cited by applicant]
10-2020-7002616, , “Office Action received for Korean Patent Application No. 10-2020-7002616 mailed on Mar. 19, 2021”, Mar. 19, 2021, 7 Pages. [cited by applicant]
10-2020-7002616, , “Voluntary Amendment filed for Korean Patent Application No. 10-2020-7002616 on Jan. 28, 2020”, Jan. 28, 2020, 34 Pages. [cited by applicant]
10-2021-7042971, , “Notice of Allowance”, KR Application No. 10-2021-7042971, Sep. 28, 2022, 8 pages. [cited by applicant]
10-2021-7042971, , “Office Action received for Chinese Patent Application No. 10-2021-7042971 mailed on Feb. 28, 2022”, Feb. 28, 2022, 6 Pages. [cited by applicant]
U.S. Appl. No. 16/799,681, , “Non Final Office Action Received for U.S. Appl. No. 16/799,681, mailed on Oct. 27, 2021”, Oct. 27, 2021, 14 pages. [cited by applicant]
U.S. Appl. No. 16/799,681, , “Non-Final Office Action”, U.S. Appl. No. 16/799,681, filed Jun. 22, 2022, 20 pages. [cited by applicant]
U.S. Appl. No. 16/799,681, , “Notice of Allowance”, U.S. Appl. No. 16/799,681, filed Dec. 14, 2022, 9 pages. [cited by applicant]
U.S. Appl. No. 18/120,557, , “Non-Final Office Action”, U.S. Appl. No. 18/120,557, 14 pages. [cited by applicant]
U.S. Appl. No. 18/120,557, , “Notice of Allowance”, U.S. Appl. No. 18/120,557, filed Jan. 9, 2024, 8 pages. [cited by applicant]
U.S. Appl. No. 18/120,557, , “Notice of Allowance”, U.S. Appl. No. 18/120,557, filed Oct. 31, 2023, 8 pages. [cited by applicant]
201880038506.8, , “Foreign Office Action”, CN Application No. 201880038506.8, Apr. 1, 2023, 6 pages. [cited by applicant]
201880038506.8, , “Notice of Allowance”, CN Application No. 201880038506.8, Aug. 30, 2023, 4 pages. [cited by applicant]
Ai, Wei et al., “Untangling Emoji Popularity through Semantic Embeddings”, Proceedings of the Eleventh International AAAI Conference on Web and Social Media (ICWSM 2017), 10 pages. [cited by applicant]
Cappallo, Spencer et al., “Image2Emoji: Zero-shot Emoji Prediction for Visual Media”, Oct. 13, 2015, 4 pages. [cited by applicant]
Dong, Jianfeng et al., “Word2VisualVec: Cross-Media Retrieval by Visual Feature Prediction”, retrieved from https://www.researchgate.net/publication/301648180, Apr. 2016, 11 pages. [cited by applicant]
Eisner, Ben et al., “emoji2vec: Learning Emoji Representations from their Description”, Nov. 20, 2016, 7 pages. [cited by applicant]
Pennington, Jeffrey et al., “GloVe: Global Vectors for Word Representation”, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) [retrieved on Sep. 7, 2022], Retrieved from the… [cited by applicant]
Wijeratne, Sanjaya et al., “A Semantics-Based Measure of Emoji Similarity”, Jul. 14, 2017, 18 pages. [cited by applicant]