Fujitsu Develops Video Analytics AI Agent to Support Safe, Secure, and Efficient Frontline Workplaces
Fujitsu Develops Video Analytics AI Agent to Support Safe, Secure, and Efficient Frontline Workplaces
The AI agent will be evaluated by FieldWorkArena, an evaluation environment newly developed by Fujitsu, under the supervision of New technology achieves world-leading accuracy while significantly extending video duration processing capability
新技術實現了世界領先的準確性，同時顯著延長了視頻處理持續時間的能力
KAWASAKI, Japan, Dec. 12, 2024 /PRNewswire/ -- Fujitsu today announced the development of a video analytics AI agent for frontline workplaces. The AI agent uses spatial video and image data from workplace camera footage, as well as written information, to draft reports and make recommendations for workplace improvements. The AI agent will be positioned as a core technology of Fujitsu's AI service "Fujitsu Kozuchi". Fujitsu will provide a trial environment for the AI agent in fiscal year 2024 and commence in-house implementation from January 2025.
日本川崎，2024年12月12日 /PRNewswire/ -- 富士通今天宣佈開發了一種面向前線工作場所的視頻分析人工智能代理。該人工智能代理利用工作場所攝像頭畫面的空間視頻和圖像數據，以及書面信息，來起草報告並提出工作場所改進的建議。該人工智能代理將作爲富士通人工智能服務"富士通Kozuchi"的核心技術。富士通將在2024財年提供該人工智能代理的試用環境，並從2025年1月開始實施內部使用。
The AI agent is based on a multimodal large language model (LLM). The AI agent trains itself to recognize 3D images of the workplace using information from written documentation (i.e., safety rules, etc). Context memory technology uses written information to selectively retain only the relevant data, enabling the analysis of long-duration video content with world-leading accuracy.
該人工智能代理基於多模態大型語言模型（LLM）。該人工智能代理通過書面文檔（如安全規章等）中的信息訓練自己識別工作場所的3D圖像。上下文記憶技術利用書面信息選擇性保留僅相關的數據，從而使以世界領先的準確性分析長時間的視頻內容成爲可能。
The AI agent will be evaluated by FieldWorkArena, an evaluation environment newly developed by Fujitsu, under the supervision of Carnegie Mellon University. FieldWorkArena will be made available for the researcher community from December 2024, with tasks being added to GitHub and the Fujitsu Research Portal in December 2024.
該人工智能代理將在富士通新開發的評估環境FieldWorkArena中進行評估，評估將在卡內基梅隆大學的監督下進行。FieldWorkArena將在2024年12月向研究社區提供，任務將於2024年12月添加到GitHub和富士通研究門戶中。
Training to operate in the frontline workplace based on written documentation
基於書面文檔的前線工作場所操作訓練
This technology augments the AI agent's video data comprehension capabilities using information from written documentation to help the LLM understand what it cannot from video content alone.
該技術增強了人工智能代理的視頻數據理解能力，利用書面文檔中的信息幫助LLM理解其無法僅從視頻內容中獲得的信息。
Efficiently retaining context data from video content
高效保留視頻內容中的上下文數據
This technology allows for the user to provide a prompt for a specific type of behavior to focus on in a video, i.e., "safe behavior in humans."
該技術允許用戶提供關於視頻中特定類型行爲的提示，即"人類的安全行爲。"
FieldWorkArena
實地工作領域
Under the supervision of Carnegie Mellon University's Associate Professor Graham Neubig and Assistant Professor Yonatan Bisk, Fujitsu has developed the FieldWorkArena, an evaluation environment for its video analytics AI agent service. The FieldWorkArena includes a bank of images and video content from actual frontline workplaces including plants and warehouses, documents such as rules and instruction manuals, simulations of business systems, and sets of tasks for the AI agent to solve.
在卡內基梅隆大學副教授Graham Neubig和助理教授Yonatan Bisk的指導下，富士通開發了FieldWorkArena，這是其視頻分析人工智能代理服務的評估環境。FieldWorkArena包含來自實際前線工作場所（例如工廠和倉庫）的圖像和視頻內容的資源庫，規則和操作手冊等文檔，業務系統的模擬，以及AI代理需要解決的一系列任務。
For full release click here
點擊這裏查看完整發布
SOURCE Fujitsu Limited
來源 富士通有限公司
WANT YOUR COMPANY'S NEWS FEATURED ON PRNEWSWIRE.COM?
想讓貴公司的資訊在PRNEWSWIRE.COM上特色展示嗎？
譯文內容由第三人軟體翻譯。
