Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
打造新電商搜尋體驗- 搜尋意圖辨識
Search
LINE Developers Taiwan
PRO
August 28, 2025
0
9
打造新電商搜尋體驗- 搜尋意圖辨識
LINE Developers Taiwan
PRO
August 28, 2025
Tweet
Share
More Decks by LINE Developers Taiwan
See All by LINE Developers Taiwan
jcconf_datadev_prod
line_developers_tw
PRO
0
4
jcconf_SPM_prod
line_developers_tw
PRO
0
3
jcconf_LINEPay_prod
line_developers_tw
PRO
0
4
Live Activities in LINE
line_developers_tw
PRO
0
12
Neumorphism x Liquid Glass
line_developers_tw
PRO
0
11
猜你喜歡 – 打造高度擴展的個人化電商推薦
line_developers_tw
PRO
0
26
比價群組
line_developers_tw
PRO
0
21
從混亂到優雅,讓專案不再失控:ATDD 與 Clean Architecture 的後端實戰之路
line_developers_tw
PRO
0
12
2049智能共存:透過LINE Bot Agent迎接後人類時代
line_developers_tw
PRO
0
43
Featured
See All Featured
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
9
960
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
507
140k
Balancing Empowerment & Direction
lara
4
680
The Cult of Friendly URLs
andyhume
79
6.6k
Docker and Python
trallard
46
3.6k
The Art of Programming - Codeland 2020
erikaheidi
56
14k
Raft: Consensus for Rubyists
vanstee
139
7.1k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
54
3k
Building an army of robots
kneath
306
46k
Designing for Performance
lara
610
69k
Optimising Largest Contentful Paint
csswizardry
37
3.4k
How To Stay Up To Date on Web Technology
chriscoyier
791
250k
Transcript
None
打造新電商搜尋體驗 搜尋意圖辨識 Speaker: Dan Chen
01 02 03 04 如何做搜尋意圖 Prompt vs Finetune LLM 驗證
什麼是搜尋意圖 05 總結 CONTENT
Dan Chen LINE Taiwan EC Dev - Data Scientis All
about Recommendation ….
Dan Chen LINE Taiwan EC Dev - Data Scientis Work
Experience Side Project Intern Work - Consultant (Startup / traditional industries) - DS4G (domestic violence / social housing / elderly issues) - TWiDS / WiDS - Publish TF2.0 books
真實的需求與目的 01 什麼是搜尋意圖?
搜尋意圖是… 特點項目文字 特點項目 特點項目文字 特點項目 關鍵字語句背後 用戶的真實需求與目的 提升用戶體驗 提升平均訂單價值 縮短購買決策週期
特點項目文字 特點項目 顧客 油性肌膚 No Results 生日快樂 星座 *https://www.flaticon.com/
過去機器學習到LLM世代 02 如何做搜尋意圖
Unsupervised Supervised 雖然預測速度快, 但不夠精準 需要大量工人智慧
- Requirement 1. Low latency 2. High precision Dictionary-based
該選擇什麼策略 03 Prompt vs Finetune
Prompt Fine-tune - What is ? - Ref: AI Engineering
Published by O'Reilly Media, Inc. *https://www.flaticon.com/
Prompt Fine-tune - When use? - Ref: AI Engineering Published
by O'Reilly Media, Inc. *https://www.flaticon.com/
如何驗證LLM 04 LLM驗證
*https://www.flaticon.com/ 驗證方法 1. Weak Supervise 2. Cross validation with different
model 3. Self-consistency/Ensemble 4. Synthetic Data
*https://www.flaticon.com/ 開源Performance比較 Breeze Taiwan llama gpt-OSS
*https://www.flaticon.com/ 建立 Reliable Sample
05 Conclusion
None
None