新韩卡以「敏感数据内部AI＋一般问询走AWS Bedrock」双模架构升级客服聊天机器人，属运营宣传式访谈，无业绩或订单增量

Shinhan Card Splits AI by Data Sensitivity to Ease Call Center Load - Seoul Economic Daily
Skip to main content
Seoul Economic Daily
Seoul Economic Daily
KST
Seoul Economic Daily
Korea's Leading Business News Since 1960
한국어
Menu
Saved Articles
Newsletters
AI KEY
Settings
|
Summary
|
Save
A
A
A
Ahn Sung-hee, head of Shinhan Card's AX Research Institute, poses during an interview with Seoul Economic Daily on Nov. 14. Photo courtesy of Shinhan Card
Shinhan Financial Group has built a dual structure for handling personal data. Tasks requiring sensitive customer information on its integrated app Shinhan SuperSOL and its card app SOL Pay are processed by in-house artificial intelligence. Less sensitive information is automatically routed to AI running on an external cloud. With privacy protection strengthened this way, AI is expected to be able to handle everything from a card payment at a hospital to filing an indemnity insurance claim in one step.
An Sung-hee, head of Shinhan Card's AX Research Institute, said on the 14th that "if older customers and those less comfortable with digital services ask for an indemnity insurance claim in plain language on the website or through the chatbot, a service can connect them to the claim filing process based on their card transaction records." Tasks that actually require access to personal data are handled by a small language model installed in the company's internal data center. General inquiries, by contrast, run on generative AI models from Amazon Web Services' Bedrock. "If a customer asks for their weekend card transactions, the internal AI looks up the transaction data and handles requests to send it by email or fax," An said. "But if they ask for a recommendation on a card with airfare discounts, they are connected to the card recommendation agent." She added: "From the customer's point of view it is a single chatbot, but different AI models and servers respond depending on the nature of the question. Questions that require customer information are separated out so the internal AI handles them."
While the AI processing paths are separated by task, the resources running them are integrated. Shinhan Card has applied Amazon EKS Hybrid Nodes to operate graphics processing units in its internal data center together with GPUs on the AWS cloud. It is the first firm in the financial sector to apply this structure to a customer-facing service. "This is a way to use the latest AI models while complying with network separation rules," An said. "When AI demand spikes, processing capacity can also be expanded."
After the chatbot upgrade, inquiries and monthly active users as of July rose 54% and 85%, respectively, from the monthly average of the two years before March this year. The completion rate was 33% higher than in March, and transfers to human agents fell about 6% from the previous year's average. "Going forward, we will use affiliate data so customers can complete the financial tasks they need without interruption," An said.
#
ShinhanCard
#
AWS
#
GenerativeAI
#
Fintech
#
AIChatbot
#
DataPrivacy
Companies in this story
Shinhan Financial
055550.KS · Finance
AI KEY Company Analysis →
Original reporting by
Jung Ji-won
for Seoul Economic Daily.
AI-translated from Korean. Quotes from foreign sources are based on Korean-language reports and may not reflect exact original wording.
View Korean original
↗
Translation Policy
Watch · Seoul Economic Daily
More →
2:20
KB Securities Sees Samsung Back at No.1, SK Hynix at No.3 Next Year | September 14 2026 | Securities Daily
2:20
Most Read This Week
1
-
5
‹
›
1
JBL Launches Xtreme 5 Bluetooth Speaker With Stronger Bass
2
Hyundai, POSCO Break Ground on $5.8 Billion U.S. Steel Mill
3
China Pumps 300 Billion Yuan Into Eight Financial Firms
4
Korea to Offer 20,000 Homes at 1,000 Won a Day for Young Adults
5
Samsung, SK hynix Memory Stockpiles Fall Below 10 Days
← Back to Home
AI KEY
Preview
↗
Korean Corporate Intelligence Hub
KOSPI · KOSDAQ · 12 sectors
A live, cap-weighted view of every KOSPI and KOSDAQ sector, with same-day Korean reporting distilled by company — built for foreign investors, correspondents and analysts who need to scan Korea before the next session.
Click to explore AI KEY
→
Open AI KEY in full screen
↗
Korea Company Atlas
Preview
↗
Market Ontology · The Feedback Loop
KFTC 2025 · 92 groups · 121,954 articles
An English ontology of the Korean market — how companies, the media, the government and the National Assembly move each other in a loop. Korea's named controlling persons and designated business groups are a mechanism, not a risk to be priced blind.
Click to explore the atlas
→
Open Atlas in full screen
↗
SIGNAL
Now live
↗
English Edition · Capital Markets
M&A · IPO · PE · Fund Flows
SIGNAL English Edition is live — Korea's deal desk reporting in English. M&A, IPOs, private equity and fund flows, covered daily for global institutional investors. Browse free; subscriber-only scoops at the 50% intro rate.
Click to explore SIGNAL
→
Open SIGNAL in full screen
↗