IP Library Granted Patent US 12,493,749
Granted Patent B2
US 12,493,749 · App. 18/219,457 · Granted Dec 9, 2025

Method for providing service based on integrated chatbot and system thereof

Inventors: Ju Seon Hong (Seoul, KR); Jae Hyuck Jang (Seoul, KR); Seong Su Kim (Seoul, KR)
Assignee: SAMSUNG SDS CO., LTD.
G06F40/35G06F16/3325G06F16/3329G06F16/3334
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 12,493,749
App. No.
18/219,457
Granted
Dec 9, 2025
Kind
B2
Abstract

Provided is a method performed by a computing system for providing an integrated chatbot-based service. The method includes receiving, by an integrated chatbot, a query from a user device; extracting a main keyword from the query; transmitting the extracted main keyword to a first chatbot and a second chatbot; receiving, from the first chatbot and the second chatbot, a content search result corresponding to the extracted main keyword; and providing a response to the query to the user device based on the received content search result.

Claims (48)

1 . A method performed by a computing system for providing an integrated chatbot-based service, the method comprising:

receiving, by an integrated chatbot, a query from a user device;

extracting a keyword from the query;

extracting a main keyword by removing, from among the extracted keyword, a keyword that does not match a content keyword previously extracted and stored from content respectively associated with a first chatbot and a second chatbot;

transmitting the extracted main keyword to the first chatbot and the second chatbot;

receiving a content search result corresponding to the extracted main keyword from the first chatbot and the second chatbot; and

providing a response to the query to the user device based on the received content search result.

2 . The method of claim 1 , wherein the content keyword is extracted from content of the first chatbot and the second chatbot based on an occurrence frequency of a keyword.

3 . The method of claim 1 , further comprising:

providing a fall-back message to the user device immediately in response to determining that the main keyword does not exist as a result of the removing of the keyword.

4 . The method of claim 1 , wherein the providing the response comprises:

providing the content search result to the user device when a number of contents included in the content search result is within a predetermined range.

5 . The method of claim 1 , wherein the providing the response comprises:

recommending a search term related to the main keyword when a number of contents included in the content search result exceeds a reference value.

6 . The method of claim 5 , wherein the recommending the search term comprises:

calculating a relevancy score based on a co-occurrence frequency of each content keyword of content keywords appearing in content included in the content search result and the main keyword; and

selecting a content keyword whose relevancy score is equal to or greater than a reference value from among the content keywords; and

configuring a search term recommendation list based on the selected content keyword.

7 . The method of claim 6 , wherein the configuring the search term recommendation list comprises:

configuring the search term recommendation list by arranging the selected content keyword in order of a higher relevancy score.

8 . The method of claim 6 , wherein the relevancy score is calculated based on the co-occurrence frequency and an occurrence frequency of a content keyword.

9 . The method of claim 1 , wherein the providing the response comprises:

recommending, when content does not exist in the content search result and a number of the extracted main keyword is plural, removal of some of the extracted main keywords.

10 . The method of claim 9 , wherein the recommending the removal of some of the extracted main keywords comprises,

providing a removal recommendation list of some keywords by removing one keyword from among the extracted main keywords in order of lower weight and recommending content re-search using remaining main keywords except for the one removed keyword.

11 . The method of claim 10 , wherein the providing the removal recommendation list further comprises:

providing, if content is not searched as a result of the content re-search, a removal recommendation list of some keywords by removing two keywords from among the extracted main keywords in order of lower weight and recommending content re-search using remaining main keywords except for the two removed keywords.

12 . The method of claim 10 , wherein the weight is a value derived using a TF-IDF (Term Frequency-Inverse Document Frequency) algorithm,

wherein the Document corresponds to content.

13 . The method of claim 1 , wherein providing the response comprises,

sorting the content search result according to a predetermined priority to provide it to the user device.

14 . The method of claim 13 , wherein the predetermined priority is based on at least one of a relevancy with a currently ongoing event and a number of views of the searched content.

15 . A system for providing an integrated chatbot-based service comprising:

a memory configured to store one or more instructions; and

one or more processors configured to execute the stored one or more instructions to perform:

receiving a query from a user device;

extracting a keyword from the query;

extracting a main keyword by removing, from among the extracted keyword, a keyword that does not match a content keyword previously extracted and stored from content respectively associated with a first chatbot and a second chatbot;

transmitting the extracted main keyword to the first chatbot and the second chatbot;

receiving, from the first chatbot and the second chatbot, a content search result corresponding to the extracted main keyword; and

providing a response to the user device based on the received content search result.

16 . A non-transitory computer readable recording medium storing computer program executable by at least one processor to perform:

receiving, by an integrated chatbot, a query from a user device;

extracting a keyword from the query;

extracting a main keyword by removing, from among the extracted keyword, a keyword that does not match a content keyword previously extracted and stored from content respectively associated with a first chatbot and a second chatbot;

transmitting the extracted main keyword to the first chatbot and the second chatbot;

receiving, from the first chatbot and the second chatbot, a content search result corresponding to the extracted main keyword; and

providing a response to the query to the user device based on the received content search result.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 7, 2023
From: HONG, JU SEON; JANG, JAE HYUCK; KIM, SEONG SU
To: SAMSUNG SDS CO., LTD.
Reel/Frame 064188/0145 →
Priority Claims (1)
KR 10-2022-0084758 · Jul 11, 2022 · national
Continuity (1)
Related Publication 20250013674A1 · Jan 9, 2025
References Cited (32)
US 8589429B1 · Thirumalai · 2013 [cited by examiner]
US 10102545B2 · Lee · 2018 [cited by examiner]
US 10706098B1 · Ramesh · 2020 [cited by examiner]
US 20060074997A1 · Chiu · 2006 [cited by examiner]
US 20070288431A1 · Reitter · 2007 [cited by examiner]
US 20130046584A1 · Yu · 2013 [cited by examiner]
US 20160217142A1 · Ye · 2016 [cited by examiner]
US 20180025726A1 · Gatti de Bayser · 2018 [cited by examiner]
US 20200104415A1 · Satti · 2020 [cited by examiner]
US 20200372055A1 · Joko · 2020 [cited by examiner]
US 20210081615A1 · McRitchie · 2021 [cited by examiner]
US 20210144107A1 · Liang · 2021 [cited by examiner]
US 20210304253A1 · Kumbi · 2021 [cited by examiner]
US 20210397416A1 · Rajesh · 2021 [cited by examiner]
US 20220272054A1 · Gao · 2022 [cited by examiner]
US 20220335050A1 · Koussa · 2022 [cited by examiner]
US 20220343257A1 · Mohanty · 2022 [cited by examiner]
US 20220351058A1 · Yannam · 2022 [cited by examiner]
US 20220358922A1 · Srivastava · 2022 [cited by examiner]
US 20230412530A1 · Schuetz · 2023 [cited by examiner]
JP 2021149633A · 2021 [cited by applicant]
KR 102107303B1 · 2020 [cited by applicant]
KR 102119404B1 · 2020 [cited by applicant]
KR 102146031B1 · 2020 [cited by applicant]
KR 1020210061126A · 2021 [cited by applicant]
KR 102271361B1 · 2021 [cited by applicant]
KR 102278020B1 · 2021 [cited by applicant]
KR 102324215B1 · 2021 [cited by applicant]
KR 102357620B1 · 2022 [cited by applicant]
Gerald Salton et al., “Introduction to Modern Information Retrieval”, McGraw-Hill, 1983, 15 pages. [cited by applicant]
Christopher D. Manning et al., “An Introduction to Information Retrieval”, Cambridge University Press, Apr. 2009, 581 pages. [cited by applicant]
Gerald Salton et al., “Term-weighting approaches in automatic text retrieval”, Information Processing & Management, vol. 24, Issue 5,1988, pp. 513-523. [cited by applicant]