2025 05/14 12:57:13
来源：新华网
火山引擎发布豆包多款大模型，以多模态AI矩阵加速行业智能化进程
2025-05-14 12:57:13 来源：新华网
5月13日，火山引擎在“FORCE LINK AI创新巡展·上海站”上，正式发布豆包·视频生成模型Seedance 1.0 lite、豆包1.5·视觉深度思考模型，并升级豆包·音乐模型。此次发布通过构建更全面的AI模型矩阵和智能体工具，进一步推动企业从业务到智能体的全链路应用落地，助力多行业智能化转型。
发布豆包·视频生成模型Seedance 1.0 lite，
原文链接：http://www.news.cn/tech/20250514/6b7ffcfae5b7418d9b7d901196e6d6f9/c.html
实质上是产品、订单、物料、工艺、现场与资金没有围绕同一条经营主线运行。
本文系统梳理YonSuite在高科技离散制造领域的六大核心业务关联、三类典型应用场景、客户实践数据及AI升级路径，帮助企业理解从研发协同到质量
溯的全链路数智化如何落地。
一、高新离散制造的管理复杂度正在重新定义ERP
传统制造以规模化、标准化和稳定批量为主要特征，管理重点是把既定计划执行得更稳定。高新离散制造的经营逻辑则不同：
对比维度 传统制造 高
具箱”：物联网传感器能实时监测浸泡罐的温度、pH值，数据上传至云端后，AI算法自动调整浸泡参数；机器视觉系统能识别黄豆的霉变颗粒，剔除精度达
正常运转，订单不降反增。从行业生态看，智能化催生了“共享工厂”“云制造”等新模式：中小作坊无需投入巨资购买设备，可通过租赁智能化生产
，设备利用率从60%提升至90%，单位生产成本降低了25%。这种趋势让我看到：豆制品行业的智能化，不是“大企业的专利”，而是中小企业的“普惠机遇
Source: PubMed Frontiers in nutrition
2025;12 1553942.
AI-driven transformation in food manufacturing: a pathway to sustainable efficiency and quality assurance.
Kushagra Agrawal, Polat Goktas, Maike Holtkemper, Christian Beecks, Navneet Kumar
Author Information
Kushagra Agrawal: School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, India.
Polat Goktas: UCD School of Computer Science and CeADAR, University College Dublin, Belfield, Dublin, Ireland.
Maike Holtkemper: Faculty of Mathematics and Computer Science, FernUniversität in Hagen, Hagen, Germany.
Christian Beecks:
原文链接：https://ngdc.cncb.ac.cn/openlb/publication/OLB-PM-40181942
值
CAGR (2026-2033)
3.3%
预期增长率
主要应用: Restaurant, Food Factory, Others
主要类型: Processed Tofu, Unprocessed Tofu
关键人物: Hain Celestial, House Foods Group, MORINAGA, Pulmuone, VITASOY
重点地区: North America (U.S, Canada, Mexico), Europe (Germany, United Kingdom, Franc
成式人工智能有望通过改变产品开发、供应链管理和消费者参与来显着影响豆腐市场。人工智能驱动的配方工具使制造商能够以前所未有的精度优化大豆蛋白混合物的质地、风味和营养成分，从而缩短研发周期并促进创新。例如
原文链接：https://www.verifiedmarketreports.com/zh/product/tofu-market/
DOI: 10.1111/1541-4337.70640
Corpus ID: 291768426
AI-Enabled Shrinkage Analysis and Morphology Control in Food Processing: Mechanisms, Multimodal Perception, Modeling, and Intelligent Regulation.
Published in Comprehensive Reviews in Food… 1 September 2026
Agricultural and Food Sciences, Computer Science, Engineering
TLDR
This review systematically summarizes the current progress of AI-enabled shrinkage characterization, predictive modeling, and intelligent regulation in food processing and provides a comprehensive theoretical and technological framework for the intelligent transformation of
表论文210余篇，SCI收录101 篇。编著教材和著作16 部，英文专著2 部。申请国家专利75 件，授权42 件。
Machine learning combined with sensory evaluation and multi-sensor technology to evaluate the overall quality of commercial soybean paste in China
Jinhui Jiangab, Shuaiqi Jiab, Guoyang Panab, Xinyu Taoab, Feiyu Anab, Qu Liuab, Junrui Wuac, Rina Wuab*
aCollege of Food Science, Shenyang Agricultural University, Shenyang 110866, China
bEngineering Research Center of Food Fermentation Technology, Shenyang 110161, China
cKey Laboratory of Microbial Fermentation Techn
本文作者：食品科学杂志
Front Nutr. 2025 Mar 13;12:1553942. doi: 10.3389/fnut.2025.1553942
AI-driven transformation in food manufacturing: a pathway to sustainable efficiency and quality assurance
Kushagra Agrawal
1 School of Computer Engineering, KIIT Deemed to be University, Bhubaneswar, India
1,† , Polat Goktas
Polat Goktas
2 UCD School of Computer Science and CeADAR, University College Dublin, Belfield, Dublin, Ireland
2,† , Maike Holtkemper
Maike Holtkemper
3 Faculty of Mathematics and Computer Science, FernUniversität in Hagen, Hagen, Germany
3 , Christian Beecks
Christian Beecks
3 Faculty of Mathematics a
中，AI技术的应用显著提升了整个供应链的效率和透明度。以某大型茄汁黄豆罐头生产企业为例，该公司通过引入AI系统，实现了对原料采购、生产制造、物流配送等环节的全面监控和管理。AI系统通过对历史数据的分析，预测市
场需求，优化原料采购计划，减少库存积压，降低成本。据数据显示，实施AI后，原料采购的准确率提高了25%，库存周转率提升了15%。 具体来说，AI技术在原料采购环节的应用体现在对供应商的评估和选择上。通过分析供应商的历
原文链接：https://www.docin.com/touch_new/preview_new.do?id=4859390645
rocess conditions, and finished tofu attributes. When supported by reliable historical data, machine-learning tools may assist with recipe adjustment, anomaly detection, predictive maintenance, and early identification of deviations in texture, yield, or coagulation behavior.
The practical value of AI depends on instrumentation, data quality, cybersecurity, and operator oversight. Sensors must capture relevant variables such as temperature, flow, dosing, pressure, and equipment condition. Human validation remains essential because soy-milk composition, coagulant chemistry, and product specific