Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the breadcrumb-navxt domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /var/www/html/wp-includes/functions.php on line 6114 Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the cookie-law-info domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /var/www/html/wp-includes/functions.php on line 6114 Warning: Cannot modify header information - headers already sent by (output started at /var/www/html/wp-includes/functions.php:6114) in /var/www/html/wp-content/plugins/wp-force-ssl/wp-force-ssl.php on line 929 Intumit SmartBERT for Enterprise-level AI Assistant : Integrates Microsoft Teams to Support as IT & ERP Internal Assistant || Intumit用SmartBERT模型打造企業級AI助理,整合微軟Teams要成為企業內部IT和ERP小幫手 | Digital Transformation (DX) with AI | LLM | ChatGPT

Digital Transformation (DX) with AI | LLM | ChatGPT

Press Release

Intumit SmartBERT for Enterprise-level AI Assistant : Integrates Microsoft Teams to Support as IT & ERP Internal Assistant || Intumit用SmartBERT模型打造企業級AI助理,整合微軟Teams要成為企業內部IT和ERP小幫手

Intumit (碩網資訊) 昨(1日)發布一套企業級AI助理解決方案SmartWork,這款聊天機器人是由1萬多筆資料和自家改良的SmartBERT模型訓練而成,將以應用程式的形式,提供在微軟協同社群平臺Teams上,供企業客戶下載使用。SmartWork不只能針對企業內部文書作業處理(如Microsoft 365應用程式)等提供疑難雜症解答,Intumit還進一步提供客製化服務,將AI助理與企業內部的ERP、客戶管理系統和訂單系統串接,扮演IT Help Desk角色,來處理內部員工請假差勤、IT設備使用、預約會議以及餐點訂送等問題。

Intumit技術長江明洋表示,Intumit20多年來專攻自然語言處理服務,自2013年開始發展自家核心AI引擎,首先自行開發了中文斷詞工具,然後發展詞向量生成,今年則利用自然語言界公認表現最好的BERT模型,開發出自家的SmartBERT模型,來打造這次導入微軟Teams的AI助理SmartWork。SmartWork利用了微軟Office資料庫中的問答集、技術社群和支援文件、使用者行為等資料訓練而成,資料量達1萬多筆,可支援中、英、日等三種語言。

(圖片來源:iThome)

相關新聞請參考以下媒體報導: