IP Library › Granted Patent US 12,248,754
Granted Patent B2
US 12,248,754 · App. 17/933,385 · Granted Mar 11, 2025

Database systems with automated structural metadata assignment

Inventors: Yixin Mao (San Francisco, CA); Zachary Alexander (San Francisco, CA); Tian Xie (San Francisco, CA); Wenhao Liu (San Francisco, CA)
G06F40/35G06F16/3329G06F16/345G06F16/358G06F16/383G10L15/083G10L15/1815G10L15/20G10L15/22G10L15/26H04L51/02
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 12,248,754
App. No.
17/933,385
Filed
Sep 19, 2022
Granted
Mar 11, 2025
Kind
B2
Art Unit
2695
USPC
704/9
Abstract

Database systems and methods are provided for assigning structural metadata to records and creating automations using the structural metadata. One method of assigning structural metadata to a record associated with a conversation involves obtaining a plurality of utterances associated with the conversation, identifying, from among the plurality of utterances, a representative utterance for semantic content of the conversation, assigning the conversation to a group of semantically similar conversations based on the representative utterance, and automatically updating the record associated with the conversation at a database system to include metadata identifying the group of semantically similar conversations.

Claims (53)

1. A method of assigning structural metadata to a record associated with a conversation, the method comprising:

obtaining a plurality of utterances associated with the conversation, the plurality of utterances including at least a first set of one or more utterances corresponding to a first actor and a second set of one or more utterances corresponding to a second actor;

identifying, from among the plurality of utterances, a representative utterance for semantic content of the conversation from within the first set of one or more utterances of the conversation, wherein the representative utterance comprises a verb and noun indicative of an intent of the first actor that initiated the conversation;

automatically updating a first field of the record associated with the conversation at a database system to include text of the representative utterance from within the conversation;

assigning the conversation to a group of semantically similar conversations from among a plurality of groups of semantically similar conversations based on a relationship between the representative utterance and a reference representative utterance providing a semantic representation of the group of semantically similar conversations; and

automatically updating a second field of the record associated with the conversation at the database system to include metadata identifying the group of semantically similar conversations.

2. The method of claim 1 , wherein:

obtaining the plurality of utterances comprises obtaining the plurality of utterances from a transcript of the conversation; and

the record of the conversation maintains an association between the transcript of the conversation, the first field comprising the text of the representative utterance from within the conversation and the second field comprising the metadata identifying the group of semantically similar conversations.

3. The method of claim 1 , further comprising generating a numerical representation of the representative utterance, wherein assigning the conversation to the group of semantically similar conversations comprises assigning the conversation to the group of semantically similar conversations based on the numerical representation.

4. The method of claim 3 , wherein generating the numerical representation comprises converting content of the representative utterance into a numerical vector representation by inputting the content of the representative utterance into an encoder model.

5. The method of claim 4 , wherein assigning the conversation to the group of semantically similar conversations based on the numerical representation comprises clustering the representative utterance into a cluster group of semantically similar conversations based on a relationship between the numerical vector representation of the representative utterance and one or more numerical vector representations of respective representative utterances associated with respective conversations of the cluster group of semantically similar conversations.

6. The method of claim 5 , wherein the metadata comprises an identifier associated with the cluster group of semantically similar conversations.

7. The method of claim 1 , wherein assigning the conversation to the group of semantically similar conversations based on the representative utterance comprises:

assigning the conversation to a cluster group of semantically similar conversations based on a relationship between the representative utterance and representative utterances associated with respective conversations of the cluster group of semantically similar conversations; assigning the cluster group of semantically similar conversations to a semantic group of a plurality of semantic groups; and

automatically updating a third field of the record to include metadata comprising an identifier associated with the semantic group of the plurality of semantic groups.

8. The method of claim 7 , wherein each semantic group of the plurality of semantic groups is distinct relative to other semantic groups of the plurality of semantic groups.

9. The method of claim 7 , wherein each semantic group of the plurality of semantic groups encompasses a plurality of cluster groups of semantically similar conversations.

10. The method of claim 9 , wherein each cluster group of the plurality of cluster groups of semantically similar conversations is distinct relative to other cluster groups of the plurality of cluster groups.

11. The method of claim 7 , further comprising generating a numerical vector representation of the representative utterance, wherein assigning the conversation to the cluster group of semantically similar conversations comprises assigning the conversation to the cluster group of semantically similar conversations based on a relationship between the numerical vector representation of the representative utterance and one or more numerical vector representations of respective representative utterances associated with respective conversations of the cluster group of semantically similar conversations.

12. The method of claim 11 , wherein assigning the cluster group of semantically similar conversations to the semantic group comprises:

identifying the reference representative utterance for the cluster group of semantically similar conversations;

generating a numerical representation of the reference representative utterance for the cluster group; and

assigning the cluster group to the semantic group based on a relationship between the numerical representation of the reference representative utterance for the cluster group and a second numerical representation of the semantic group.

13. The method of claim 12 , wherein the reference representative utterance for the cluster group comprises a center representative utterance identified from among a plurality of representative utterances associated with respective conversations of the cluster group of semantically similar conversations.

14. The method of claim 12 , wherein the reference representative utterance for the cluster group comprises an autogenerated name associated with the cluster group of semantically similar conversations.

15. The method of claim 1 , wherein:

identifying the representative utterance comprises:

selecting a subset of utterances associated with the first actor, the subset comprising a predetermined number of utterances associated with the first actor; and

sequentially determining, from the subset, an earliest utterance indicative of the intent of the conversation by the first actor; and

the representative utterance comprises the earliest utterance indicative of the intent of the conversation by the first actor.

16. The method of claim 1 , further comprising identifying the reference representative utterance providing the semantic representation of the group of semantically similar conversations as a respective representative utterance for semantic content of a respective conversation of the group of semantically similar conversations corresponding to a numerical vector that represents a center, a median or a mean of the group of semantically similar conversations, wherein the reference representative utterance comprises a respective verb and noun indicative of a respective intent of a third actor that initiated the respective conversation.

17. At least one non-transitory machine-readable storage medium that provides instructions that, when executed by at least one processor, are configurable to cause the at least one processor to:

obtain a plurality of utterances associated with a conversation, the plurality of utterances including at least a first set of one or more utterances corresponding to a first actor and a second set of one or more utterances corresponding to a second actor;

identify, from among the plurality of utterances, a representative utterance for semantic content of the conversation from within the first set of one or more utterances of the conversation, wherein the representative utterance comprises a verb and noun indicative of an intent of the first actor that initiated the conversation;

automatically update a first field of a record associated with the conversation at a database system to include text of the representative utterance from within the conversation;

assign the conversation to a group of semantically similar conversations from among a plurality of groups of semantically similar conversations based on a relationship between the representative utterance and a reference representative utterance providing a semantic representation of the group of semantically similar conversations; and

automatically update a second field of record associated with the conversation at the database system to include metadata identifying the group of semantically similar conversations.

18. The at least one non-transitory machine-readable storage medium of claim 17 , wherein the instructions are configurable to cause the at least one processor to:

assign the conversation to a cluster group of semantically similar conversations based on a relationship between the representative utterance and representative utterances associated with respective conversations of the cluster group of semantically similar conversations;

assign the cluster group of semantically similar conversations to a semantic group of a plurality of semantic groups; and

automatically update a third field of the record to include metadata comprising an identifier associated with the semantic group of the plurality of semantic groups.

19. The at least one non-transitory machine-readable storage medium of claim 18 , wherein the instructions cause the at least one processor to:

convert content of the representative utterance into a numerical vector representation; and

assign the conversation to the group of semantically similar conversations based on a relationship of the numerical vector representation of the representative utterance and one or more numerical vector representations of respective representative utterances associated with respective conversations of the cluster group of semantically similar conversations.

20. A computing system comprising:

at least one non-transitory machine-readable storage medium that stores software; and

at least one processor, coupled to the at least one non-transitory machine-readable storage medium, to execute the software that implements a conversation mining service and that is configurable to perform operations comprising:

obtaining a plurality of utterances associated with a conversation, the plurality of utterances including at least a first set of one or more utterances corresponding to a first actor and a second set of one or more utterances corresponding to a second actor;

identifying, from among the plurality of utterances, a representative utterance for semantic content of the conversation from within the first set of one or more utterances of the conversation, wherein the representative utterance comprises a verb and noun indicative of an intent of the first actor that initiated the conversation;

automatically updating a first field of a record associated with the conversation at a database system to include text of the representative utterance from within the conversation;

assigning the conversation to a group of semantically similar conversations from among a plurality of groups of semantically similar conversations based on a relationship between the representative utterance and a reference representative utterance providing a semantic representation of the group of semantically similar conversations; and

automatically update a second field of the record associated with the conversation at the database system to include metadata identifying the group of semantically similar conversations assigned to the conversation.

Assignments (2)
CHANGE OF NAME Recorded Aug 4, 2026
From: SALESFORCE.COM, INC.
To: SALESFORCE, INC.
Reel/Frame 076118/0548 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 13, 2022
From: MAO, YIXIN; ALEXANDER, ZACHARY; XIE, TIAN; LIU, WENHAO
To: SALESFORCE.COM, INC.
Reel/Frame 062068/0955 →
Continuity (2)
Provisional Application 63261397 · Sep 20, 2021
Related Publication 20230090924A1 · Mar 23, 2023
References Cited (171)
US 5577188A · Zhu · 1996 [cited by applicant]
US 5608872A · Schwartz et al. · 1997 [cited by applicant]
US 5649104A · Carleton et al. · 1997 [cited by applicant]
US 5715450A · Ambrose et al. · 1998 [cited by applicant]
US 5761419A · Schwartz et al. · 1998 [cited by applicant]
US 5819038A · Carleton et al. · 1998 [cited by applicant]
US 5821937A · Tonelli et al. · 1998 [cited by applicant]
US 5831610A · Tonelli et al. · 1998 [cited by applicant]
US 5873096A · Lim et al. · 1999 [cited by applicant]
US 5918159A · Fomukong et al. · 1999 [cited by applicant]
US 5963953A · Cram et al. · 1999 [cited by applicant]
US 6092083A · Brodersen et al. · 2000 [cited by applicant]
US 6161149A · Achacoso et al. · 2000 [cited by applicant]
US 6169534B1 · Raffel et al. · 2001 [cited by applicant]
US 6178425B1 · Brodersen et al. · 2001 [cited by applicant]
US 6189011B1 · Lim et al. · 2001 [cited by applicant]
US 6216135B1 · Brodersen et al. · 2001 [cited by applicant]
US 6233617B1 · Rothwein et al. · 2001 [cited by applicant]
US 6266669B1 · Brodersen et al. · 2001 [cited by applicant]
US 6295530B1 · Ritchie et al. · 2001 [cited by applicant]
US 6324568B1 · Diec et al. · 2001 [cited by applicant]
US 6324693B1 · Brodersen et al. · 2001 [cited by applicant]
US 6336137B1 · Lee et al. · 2002 [cited by applicant]
US D454139S · Feldcamp et al. · 2002 [cited by applicant]
US 6367077B1 · Brodersen et al. · 2002 [cited by applicant]
US 6393605B1 · Loomans · 2002 [cited by applicant]
US 6405220B1 · Brodersen et al. · 2002 [cited by applicant]
US 6434550B1 · Warner et al. · 2002 [cited by applicant]
US 6446089B1 · Brodersen et al. · 2002 [cited by applicant]
US 6535909B1 · Rust · 2003 [cited by applicant]
US 6549908B1 · Loomans · 2003 [cited by applicant]
US 6553563B2 · Ambrose et al. · 2003 [cited by applicant]
US 6560461B1 · Fomukong et al. · 2003 [cited by applicant]
US 6574635B2 · Stauber et al. · 2003 [cited by applicant]
US 6577726B1 · Huang et al. · 2003 [cited by applicant]
US 6601087B1 · Zhu et al. · 2003 [cited by applicant]
US 6604117B2 · Lim et al. · 2003 [cited by applicant]
US 6604128B2 · Diec · 2003 [cited by applicant]
US 6609150B2 · Lee et al. · 2003 [cited by applicant]
US 6621834B1 · Scherpbier et al. · 2003 [cited by applicant]
US 6654032B1 · Zhu et al. · 2003 [cited by applicant]
US 6665648B2 · Brodersen et al. · 2003 [cited by applicant]
US 6665655B1 · Warner et al. · 2003 [cited by applicant]
US 6684438B2 · Brodersen et al. · 2004 [cited by applicant]
US 6711565B1 · Subramaniam et al. · 2004 [cited by applicant]
US 6724399B1 · Katchour et al. · 2004 [cited by applicant]
US 6728702B1 · Subramaniam et al. · 2004 [cited by applicant]
US 6728960B1 · Loomans et al. · 2004 [cited by applicant]
US 6732095B1 · Warshavsky et al. · 2004 [cited by applicant]
US 6732100B1 · Brodersen et al. · 2004 [cited by applicant]
US 6732111B2 · Brodersen et al. · 2004 [cited by applicant]
US 6754681B2 · Brodersen et al. · 2004 [cited by applicant]
US 6763351B1 · Subramaniam et al. · 2004 [cited by applicant]
US 6763501B1 · Zhu et al. · 2004 [cited by applicant]
US 6768904B2 · Kim · 2004 [cited by applicant]
US 6772229B1 · Achacoso et al. · 2004 [cited by applicant]
US 6782383B2 · Subramaniam et al. · 2004 [cited by applicant]
US 6804330B1 · Jones et al. · 2004 [cited by applicant]
US 6826565B2 · Ritchie et al. · 2004 [cited by applicant]
US 6826582B1 · Chatterjee et al. · 2004 [cited by applicant]
US 6826745B2 · Coker · 2004 [cited by applicant]
US 6829655B1 · Huang et al. · 2004 [cited by applicant]
US 6842748B1 · Warner et al. · 2005 [cited by applicant]
US 6850895B2 · Brodersen et al. · 2005 [cited by applicant]
US 6850949B2 · Warner et al. · 2005 [cited by applicant]
US 7062502B1 · Kesler · 2006 [cited by applicant]
US 7069231B1 · Cinarkaya et al. · 2006 [cited by applicant]
US 7181758B1 · Chan · 2007 [cited by applicant]
US 7289976B2 · Kihneman et al. · 2007 [cited by applicant]
US 7340411B2 · Cook · 2008 [cited by applicant]
US 7356482B2 · Frankland et al. · 2008 [cited by applicant]
US 7401094B1 · Kesler · 2008 [cited by applicant]
US 7412455B2 · Dillon · 2008 [cited by applicant]
US 7508789B2 · Chan · 2009 [cited by applicant]
US 7620655B2 · Larsson et al. · 2009 [cited by applicant]
US 7698160B2 · Beaven et al. · 2010 [cited by applicant]
US 7730478B2 · Weissman · 2010 [cited by applicant]
US 7779475B2 · Jakobson et al. · 2010 [cited by applicant]
US 8014943B2 · Jakobson · 2011 [cited by applicant]
US 8015495B2 · Achacoso et al. · 2011 [cited by applicant]
US 8032297B2 · Jakobson · 2011 [cited by applicant]
US 8082301B2 · Ahlgren et al. · 2011 [cited by applicant]
US 8095413B1 · Beaven · 2012 [cited by applicant]
US 8095594B2 · Beaven et al. · 2012 [cited by applicant]
US 8209308B2 · Rueben et al. · 2012 [cited by applicant]
US 8275836B2 · Beaven et al. · 2012 [cited by applicant]
US 8380511B2 · Cave · 2013 [cited by applicant]
US 8457545B2 · Chan · 2013 [cited by applicant]
US 8484111B2 · Frankland et al. · 2013 [cited by applicant]
US 8490025B2 · Jakobson et al. · 2013 [cited by applicant]
US 8504945B2 · Jakobson et al. · 2013 [cited by applicant]
US 8510045B2 · Rueben et al. · 2013 [cited by applicant]
US 8510664B2 · Rueben et al. · 2013 [cited by applicant]
US 8566301B2 · Rueben et al. · 2013 [cited by applicant]
US 8646103B2 · Jakobson et al. · 2014 [cited by applicant]
US 10930272B1 · Orkin · 2021 [cited by applicant]
US 11507756B2 · Lima · 2022 [cited by applicant]
US 11551677B2 · Roy · 2023 [cited by applicant]
US 11568856B2 · Ho · 2023 [cited by applicant]
US 20010044791A1 · Richter et al. · 2001 [cited by applicant]
US 20020072951A1 · Lee et al. · 2002 [cited by applicant]
US 20020082892A1 · Raffel · 2002 [cited by applicant]
US 20020129352A1 · Brodersen et al. · 2002 [cited by applicant]
US 20020140731A1 · Subramanian et al. · 2002 [cited by applicant]
US 20020143997A1 · Huang et al. · 2002 [cited by applicant]
US 20020162090A1 · Parnell et al. · 2002 [cited by applicant]
US 20020165742A1 · Robbins · 2002 [cited by applicant]
US 20030004971A1 · Gong · 2003 [cited by applicant]
US 20030018705A1 · Chen et al. · 2003 [cited by applicant]
US 20030018830A1 · Chen et al. · 2003 [cited by applicant]
US 20030066031A1 · Laane et al. · 2003 [cited by applicant]
US 20030066032A1 · Ramachandran et al. · 2003 [cited by applicant]
US 20030069936A1 · Warner · 2003 [cited by applicant]
US 20030070000A1 · Coker et al. · 2003 [cited by applicant]
US 20030070004A1 · Mukundan et al. · 2003 [cited by applicant]
US 20030070005A1 · Mukundan et al. · 2003 [cited by applicant]
US 20030074418A1 · Coker et al. · 2003 [cited by applicant]
US 20030120675A1 · Stauber et al. · 2003 [cited by applicant]
US 20030151633A1 · George et al. · 2003 [cited by applicant]
US 20030159136A1 · Huang et al. · 2003 [cited by applicant]
US 20030187921A1 · Diec et al. · 2003 [cited by applicant]
US 20030189600A1 · Gune et al. · 2003 [cited by applicant]
US 20030204427A1 · Gune et al. · 2003 [cited by applicant]
US 20030206192A1 · Chen et al. · 2003 [cited by applicant]
US 20030225730A1 · Warner et al. · 2003 [cited by applicant]
US 20040001092A1 · Rothwein et al. · 2004 [cited by applicant]
US 20040010489A1 · Rio et al. · 2004 [cited by applicant]
US 20040015981A1 · Coker et al. · 2004 [cited by applicant]
US 20040027388A1 · Berg et al. · 2004 [cited by applicant]
US 20040128001A1 · Levin et al. · 2004 [cited by applicant]
US 20040186860A1 · Lee et al. · 2004 [cited by applicant]
US 20040193510A1 · Catahan et al. · 2004 [cited by applicant]
US 20040199489A1 · Barnes-Leon et al. · 2004 [cited by applicant]
US 20040199536A1 · Barnes-Leon et al. · 2004 [cited by applicant]
US 20040199543A1 · Braud et al. · 2004 [cited by applicant]
US 20040249854A1 · Barnes-Leon et al. · 2004 [cited by applicant]
US 20040260534A1 · Pak et al. · 2004 [cited by applicant]
US 20040260659A1 · Chan et al. · 2004 [cited by applicant]
US 20040268299A1 · Lei et al. · 2004 [cited by applicant]
US 20050050555A1 · Exley et al. · 2005 [cited by applicant]
US 20050091098A1 · Brodersen et al. · 2005 [cited by applicant]
US 20050251383A1 · Murray · 2005 [cited by examiner]
US 20060021019A1 · Hinton et al. · 2006 [cited by applicant]
US 20080249972A1 · Dillon · 2008 [cited by applicant]
US 20090063414A1 · White et al. · 2009 [cited by applicant]
US 20090100342A1 · Jakobson · 2009 [cited by applicant]
US 20090177744A1 · Marlow et al. · 2009 [cited by applicant]
US 20110238408A1 · Larcheveque · 2011 [cited by examiner]
US 20110247051A1 · Bulumulla et al. · 2011 [cited by applicant]
US 20120042218A1 · Cinarkaya et al. · 2012 [cited by applicant]
US 20120218958A1 · Rangaiah · 2012 [cited by applicant]
US 20120233137A1 · Jakobson et al. · 2012 [cited by applicant]
US 20130212497A1 · Zelenko et al. · 2013 [cited by applicant]
US 20130218948A1 · Jakobson · 2013 [cited by applicant]
US 20130218949A1 · Jakobson · 2013 [cited by applicant]
US 20130218966A1 · Jakobson · 2013 [cited by applicant]
US 20130247216A1 · Cinarkaya et al. · 2013 [cited by applicant]
US 20160012818A1 · Faizakof · 2016 [cited by examiner]
US 20200143265A1 · Jonnalagadda · 2020 [cited by examiner]
US 20200152183A1 · Wang · 2020 [cited by applicant]
US 20210342554A1 · Martin · 2021 [cited by applicant]
US 20210390127A1 · Fox · 2021 [cited by applicant]
US 20220156296A1 · de Oliveira · 2022 [cited by applicant]
US 20220156460A1 · Lainez · 2022 [cited by applicant]
US 20220222437A1 · Lauber · 2022 [cited by applicant]
US 20230054726A1 · Roy · 2023 [cited by applicant]
Cambridge University Press, Dropping common terms: stop words, Apr. 7, 2009, 1 page. [cited by applicant]
Nils Reimers, et al., Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks, Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universitat Darmstadt, Aug. 27, 2019, 11 pa… [cited by applicant]
Mike Lewis, et al., BART: Denoising Sequence-to-Sequence Pre-Training for Natural Language Generation, Translation and Comprehension, Jul. 2020. [cited by applicant]
CYLNLP/DialogSum, DialogSum: A Real-life Scenerio Dialogue Summarization Dataset—Findings of ACL 2021, 4 pages. [cited by applicant]
Scikit-Learn Developers (BSD License), 2.1. Gaussian mixture models, https://scikit-learn.org/stable/modules/mixture.html, 2007, 6 pages. [cited by applicant]
Cited By (1)
US 12,597,413