IP Library › Granted Patent US 12,737,434
Granted Patent B2
US 12,737,434 · App. 18/640,263 · Granted Sep 15, 2026

Techniques for aggregating insights of textual data using hierarchical clustering

Inventors: Inbal Horev (Tel Aviv, IL); Rahm Fehr (Tel Aviv, IL); Inbal Ben Yehuda (Tel Aviv, IL); Shlomi Medalion (Lod, IL); Hadas Shick (Beit Guvrin, IL); Noy Cohen (Tel Aviv, IL); Eldad Shilo (Herzliya, IL)
Assignee: Gong.io Ltd.
G06F18/231G06Q30/01
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 12,737,434
App. No.
18/640,263
Granted
Sep 15, 2026
Kind
B2
Abstract

A system and method for discovering and aggregating themes. The method includes applying a trained clustering model to a plurality of textual data, wherein the trained clustering model determines at least one cluster of textual data based on a meaning of the textual data, wherein textual data of the at least one cluster is a portion of the plurality of textual data; generating a name, using a trained naming model, for each of the at least one cluster, wherein the generated name indicates a theme that represents the meaning of the textual data of the at least one cluster; analyzing the at least one cluster to determine a distribution metric of the at least one cluster; and generating a notification based on the determined distribution metric and the respective at least one cluster.

Claims (49)

1 . A method for discovering and aggregating themes, further comprising:

applying a trained clustering model to a plurality of textual data, wherein the trained clustering model determines at least one cluster of textual data based on a meaning of the textual data, wherein textual data of the at least one cluster is a portion of the plurality of textual data;

generating a name, using a trained naming model, for each of the at least one cluster based on textual units in the respective at least one cluster, wherein the generated name indicates a theme that represents the meaning of the textual data of the at least one cluster;

analyzing the at least one cluster to determine a distribution metric of the at least one cluster; and

generating a notification, with respect to at least one theme, based on a plurality of rules applied to the determined distribution metric and the at least one cluster associated with the at least one theme.

2 . The method of claim 1 , further comprising:

segmenting the textual data of the plurality of textual data into textual units; and

rephrasing the textual units to generate normalized formats of the textual units.

3 . The method of claim 1 , wherein the trained clustering model is a hierarchical clustering model that determines at least one sub-cluster for each of the determined at least one cluster.

4 . The method of claim 1 , further comprising:

aggregating the determined distribution metric and at least one other distribution metric of the at least one cluster, wherein the at least one other distribution metric is previously determined for the respective at least one cluster; and

identifying a trend in the theme by comparing the aggregated determined distribution metric and the at least one other distribution metric.

5 . The method of claim 4 , further comprising:

triggering the generation of the notification upon determination that the identified change is beyond a predetermined threshold value.

6 . The method of claim 1 , wherein the distribution metric is a numerical value that indicates a quality of the at least one cluster, and wherein the distribution metric is at least one of: Silhouette scores, Dunn index, McClain-Rao index, and C-index.

7 . The method of claim 1 , wherein the textual data is collected from at least one of: videoconferences, telephonic conversations, emails, text messages, chats, and customer relationship management (CRM) data.

8 . The method of claim 1 , wherein the textual data of the at least one cluster is related to at least one of: sales and customer relationships.

9 . The method of claim 1 , further comprising:

receiving an external input data from an external source; and

filtering the plurality of textual data by mapping to the external input data, wherein a portion of the plurality of textual data that is not mapped is filtered out.

10 . The method of claim 1 , wherein the trained clustering model applies any one of: hierarchical Latent Dirichlet Allocation (LDA), Bidirectional Encoder Representations from Transformers leveraged topic modeling (BERTopic), or hierarchical Density-based spatial clustering of applications (DBSCAN).

11 . A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process, the process comprising:

applying a trained clustering model to a plurality of textual data, wherein the trained clustering model determines at least one cluster of textual data based on a meaning of the textual data, wherein textual data of the at least one cluster is a portion of the plurality of textual data;

generating a name, using a trained naming model, for each of the at least one cluster based on textual units in the respective at least one cluster, wherein the generated name indicates a theme that represents the meaning of the textual data of the at least one cluster;

analyzing the at least one cluster to determine a distribution metric of the at least one cluster; and

generating a notification, with respect to at least one theme, based on a plurality of rules applied to the determined distribution metric and the at least one cluster associated with the at least one theme.

12 . A system for discovering and aggregating themes, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

apply a trained clustering model to a plurality of textual data, wherein the trained clustering model determines at least one cluster of textual data based on a meaning of the textual data, wherein textual data of the at least one cluster is a portion of the plurality of textual data;

generate a name, using a trained naming model, for each of the at least one cluster based on textual units in the respective at least one cluster, wherein the generated name indicates a theme that represents the meaning of the textual data of the at least one cluster;

analyze the at least one cluster to determine a distribution metric of the at least one cluster; and

generate a notification, with respect to at least one theme, based on a plurality of rules applied to the determined distribution metric and the at least one cluster associated with the at least one theme.

13 . The system of claim 12 , wherein the system is further configured to:

segment the textual data of the plurality of textual data into textual units; and

rephrase the textual units to generate normalized formats of the textual units.

14 . The system of claim 12 , wherein the trained clustering model is a hierarchical clustering model that determines at least one sub-cluster for each of the determined at least one cluster.

15 . The system of claim 12 , wherein the system is further configured to:

aggregate the determined distribution metric and at least one other distribution metric of the at least one cluster, wherein the at least one other distribution metric is previously determined for the respective at least one cluster; and

identify a trend in the theme by comparing the aggregated determined distribution metric and the at least one other distribution metric.

16 . The system of claim 15 , wherein the system is further configured to:

trigger the generation of the notification upon determination that the identified change is beyond a predetermined threshold value.

17 . The system of claim 12 , wherein the distribution metric is a numerical value that indicates a quality of the at least one cluster, and wherein the distribution metric is at least one of: Silhouette scores, Dunn index, McClain-Rao index, and C-index.

18 . The system of claim 12 , wherein the textual data is collected from at least one of: videoconferences, telephonic conversations, emails, text messages, chats, and customer relationship management (CRM) data.

19 . The system of claim 12 , wherein the textual data of the at least one cluster is related to at least one of: sales and customer relationships.

20 . The system of claim 12 , wherein the system is further configured to:

receive an external input data from an external source; and

filter the plurality of textual data by mapping to the external input data, wherein a portion of the plurality of textual data that is not mapped is filtered out.

21 . The system of claim 12 , wherein the trained clustering model applies any one of: hierarchical Latent Dirichlet Allocation (LDA), Bidirectional Encoder Representations from Transformers leveraged topic modeling (BERTopic), or hierarchical Density-based spatial clustering of applications (DBSCAN).

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 28, 2024
From: HOREV, INBAL; FEHR, RAHM; BEN YEHUDA, INBAL; MEDALION, SHLOMI; SHICK, HADAS; COHEN, NOY; SHILO, ELDAD
To: GONG.IO LTD.
Reel/Frame 067540/0364 →
Continuity (2)
Provisional Application 63497593 · Apr 21, 2023
Related Publication 20240354375A1 · Oct 24, 2024
References Cited (52)
US 6101480A · Conmy et al. · 2000 [cited by applicant]
US 6219639B1 · Bakis et al. · 2001 [cited by applicant]
US 7574409B2 · Patinkin · 2009 [cited by applicant]
US 8214242B2 · Agapi et al. · 2012 [cited by applicant]
US 8706678B2 · Stefik · 2014 [cited by applicant]
US 9479736B1 · Karakotsios · 2016 [cited by applicant]
US 10282759B1 · King et al. · 2019 [cited by applicant]
US 10318927B2 · Champaneria · 2019 [cited by applicant]
US 10642889B2 · Reshef et al. · 2020 [cited by applicant]
US 12118324B1 · Zhang et al. · 2024 [cited by applicant]
US 12141677B2 · Silver et al. · 2024 [cited by applicant]
US 12182728B1 · Wick et al. · 2024 [cited by applicant]
US 12190864B1 · Xiao et al. · 2025 [cited by applicant]
US 12229522B2 · Gajek et al. · 2025 [cited by applicant]
US 20090119095A1 · Beggelman et al. · 2009 [cited by applicant]
US 20090125998A1 · Levy · 2009 [cited by applicant]
US 20140214402A1 · Diao et al. · 2014 [cited by applicant]
US 20170083507A1 · Ho et al. · 2017 [cited by applicant]
US 20180176508A1 · Pell · 2018 [cited by applicant]
US 20190318743A1 · Reshef et al. · 2019 [cited by applicant]
US 20200012886A1 · Walters · 2020 [cited by examiner]
US 20200265102A1 · Ho et al. · 2020 [cited by applicant]
US 20200293427A1 · Walters · 2020 [cited by examiner]
US 20210027772A1 · Horev et al. · 2021 [cited by applicant]
US 20210103608A1 · Ganti · 2021 [cited by examiner]
US 20210286832A1 · Prasad Tanniru · 2021 [cited by examiner]
US 20210406735A1 · Nahamoo et al. · 2021 [cited by applicant]
US 20220092028A1 · Layton et al. · 2022 [cited by applicant]
US 20220115019A1 · Bradley et al. · 2022 [cited by applicant]
US 20220138388A1 · Wang et al. · 2022 [cited by applicant]
US 20220189489A1 · Peeler et al. · 2022 [cited by applicant]
US 20220245340A1 · Yang et al. · 2022 [cited by applicant]
US 20230112096A1 · Choi · 2023 [cited by examiner]
US 20230153177A1 · Walters · 2023 [cited by examiner]
US 20230162733A1 · Moorsom et al. · 2023 [cited by applicant]
US 20230169276A1 · Cook · 2023 [cited by applicant]
US 20230297786A1 · Park et al. · 2023 [cited by applicant]
US 20230360640A1 · Asi et al. · 2023 [cited by applicant]
US 20230376697A1 · Chow et al. · 2023 [cited by applicant]
US 20240273292A1 · Lakshmin · 2024 [cited by examiner]
US 20240289366A1 · Hranj et al. · 2024 [cited by applicant]
US 20240330589A1 · Kotaru · 2024 [cited by applicant]
US 20240355318A1 · Beaver · 2024 [cited by applicant]
US 20240403333A1 · Bertschinger · 2024 [cited by examiner]
US 20240428017A1 · Shoham et al. · 2024 [cited by applicant]
US 20250124053A1 · Beltran · 2025 [cited by examiner]
US 20250181834A1 · Joshi · 2025 [cited by examiner]
EP 3432155A1 · 2019 [cited by applicant]
WO 2019016119A1 · 2019 [cited by applicant]
Great Learning Team. “Understanding Latent Dirichlet Allocation (LDA)”. Oct. 16, 2020. https://www.mygreatlearning.com/blog/understanding-latent-dirichlet-allocation/. [cited by applicant]
Su, Hongjin, et al., “One Embedder, Any Task: Instruction-Finetuned Text Embeddings”, 2022, pp. 1-9, Date accessed Apr. 19, 2024. [cited by applicant]
Su, Hongjin, et al., “One Embedder, Any Task: Instruction-Finetuned Text Embeddings”, May 30, 2023, pp. 1-18, Date Accessed Apr. 19, 2024. [cited by applicant]