『您的瀏覽器不支援JavaScript功能,若網頁功能無法正常使用時,請開啟瀏覽器JavaScript狀態』

跳到主要內容區塊

工業技術研究院

:::

技術名稱: 全配通創新服務決策支援系統

技術簡介

全配通創新服務決策支援系統包含兩項支援模組:1、取貨站選址決策支援模組與2、推薦導購商品篩選模組。由於全配通服務為新型態線上線下整合式創新服務,取貨站設址考量迥異於傳統展店選址應用。本系統中之設址技術結合政府開放資料、設計以ROI為考量之多設址目標,並提供相對應之設址計算演算法。同時,導購商品篩選模組則是建立消費者購物偏好模型,精確瞄準消費者潛在購物需求,透過消費者之消費偏好預測,此模組能動態調整推薦引擎所產生之推薦商品順序,為原有推薦系統增色不少。

Abstract

Two decision support modules including 1) the site selection module for pickup stations and 2) product recommendation ranking module are involved in the Omni-order to Omni-collect decision support system. Since the Omni-Channel retailing service is a new type of services, integrating online and offline behaviors, the needs of pickup station selection are different from those of the traditional site selection (for opening a shop). In this decision support system, the site selection technique rooted in open data designs two objective functions based on ROI and also provides the corresponding algorithms for achieving them. On the other hand, the product recommendation ranking module manages to construct the user preference modules for aiming at the needs of customers. Based on the user preference modules, this ranking module can predict the customer preferences for individuals and then rank the recommended products dynamically and personally, enhancing the recommender system.

技術規格

此系統之選址決策模組以新竹縣市竹科生活圈為目標城市,結合企業內部交易資料支援2種以ROI為準則定義之選址目標函數及其對應之最佳化多選址演算法,可複製擴散至其他城市之選址決策。

Technical Specification

The site selection module uses Hsinchu County and Hsinchu City as an example and combines the transactional data of an enterprise to provide two ROI-based site selection objective functions and the corresponding solutions. It can be applied to the other cities for site selection decision making.

技術特色

1、取貨站選址決策模組:結合社經資料庫(人口數、所得、家戶數、教育程度)、GIS圖資、公車路線、停車場、各級學校、不動產實價登入等外部開放資料,並搭配企業內部交易資料,將目標城市切割成候選地理小區,分析並評估各地理小區之區域特徵。基於上述區域特徵導入天際線查詢處理技術,為單一選址需求快速篩選候選區域,以因應不同專家或決策者的屬性權重值考量;亦發展多選址技術,根據企業內部交易資料設定最佳化決策目標函數,藉以支援發展規模化部署策略。 2、推薦導購商品篩選模組:此模組可整合於個人化推薦系統中,透過企業內部offline的POS資料將消費者依據消費行為分群,並建立消費者偏好模型,當消費者線上購物時,即時預測其消費偏好,動態將推薦引擎所產生之推薦物,依使用者消費偏好排序,以達精準推薦。

應用範圍

取貨站選址決策模組主要用於取貨站的設址評估,能提供單一設址與多設址選址決策建議,除取貨站設址外,若能結合其他企業內部資料與競業資料,亦可應用於展店選址與關店決策輔助。推薦導購商品篩選模組能與一般電商使用之推薦引擎整合,調整推薦物於Web頁面之配置順序,增強推薦效度。

接受技術者具備基礎建議(設備)

本系統之模組以python、Java與R語言開發而成,所使用之資料庫為postgreSQL結合postGIS,一台具網路功能之商用電腦或伺服器(i5 4核心、32GB RAM或以上)並運行centOS6.5作業系統為此系統的基礎運行環境。

接受技術者具備基礎建議(專業)

本系統以python、Java與R語言開發而成,接受技術者需有使用空間資料庫如postgreSQL/postGIS經驗,同時需有web service經驗能透過Restful API與部分模組與原有系統串接。

技術分類 U-服務系統開發

聯絡資訊

聯絡人:羅國書 智慧物流與供應鏈整合組

電話:+886-3-5913405 或 Email:JonesLo@itri.org.tw

客服專線:+886-800-45-8899

傳真:+886-3-5820315

[{"text":"企業網","weight":13.0},{"text":"材化所","weight":11.5},{"text":"機械所","weight":10.0},{"text":"綠能所","weight":9.4},{"text":"生醫所","weight":8.0},{"text":"半導體","weight":6.2},{"text":"南分院","weight":5.0},{"text":"太陽能","weight":5.0},{"text":"課程","weight":5.0},{"text":"遠紅外線","weight":5.0},{"text":"雷射","weight":4.0},{"text":"LED","weight":4.0},{"text":"LED可見光","weight":3.0},{"text":"5G","weight":3.0},{"text":"工研人","weight":3.0},{"text":"電光所","weight":3.0},{"text":"綠能與環境研究所","weight":3.0},{"text":"機械","weight":3.0},{"text":"資通所","weight":2.0},{"text":"面板","weight":2.0},{"text":"文字轉語音","weight":2.0},{"text":"實習","weight":2.0},{"text":"無人機","weight":2.0},{"text":"生醫","weight":2.0},{"text":"3D","weight":2.0},{"text":"v2x","weight":2.0},{"text":"員工","weight":2.0},{"text":"地圖","weight":2.0},{"text":"太陽光電","weight":2.0},{"text":"材料與化工研究所","weight":1.0}]