[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-806":3,"related-806":81},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":8,"secondary_topics":32,"classification":33,"search_phrases":76,"slug":79,"view_count":41,"doi":8,"paper":8,"created_at":80},806,"农业农村部健全农产品全国统一分级标准体系——全国\"三品一标\"农产品达8.6万个,分级农产品实现优质优价","https:\u002F\u002Ffoodscn.cn\u002Fjianguan\u002F15314","农业农村部近日就十四届全国人大三次会议第5402号建议做出答复:已建成涵盖粮油、果蔬、畜禽、水产等品类的农产品质量分级标准体系,现有国家标准、农业行业标准350余项;各地开展水果、肉牛等重点品类分级试点,推广智能化分级技术;财政资金已统筹支持农产品标准化及品质提升,品牌相关国家标准44项,全国\"三品一标\"农产品达8.6万个。",null,"本报讯  （记者 袁国凤）近日，农业农村部就十四届全国人大三次会议第5402号建议《关于全面推进农产品质量分级工作，以“四个农业”引领农业高质量发展、助力农业强国建设的建议》做出答复表示，我国已建成多品类农产品质量分级标准体系。各地积极开展分级试点，创新评价模式，动态完善标准，推广智能分级技术并常态开展技术服务。强化财政保障，稳步推进品牌建设与产销对接，推动分级农产品实现优质优价。\n\n农业农村部表示，目前我国已建成涵盖粮油、果蔬、畜禽、水产等品类的农产品质量分级标准体系，现有国家标准、农业行业标准350余项。各地有序开展水果、肉牛等重点品类分级试点，创新“三方共评”等评价模式，同步推进多品类标准研制，并严格执行标准复审机制，持续优化标准内容。同时，各地依托龙头企业、合作社建立分级培育体系，推广智能化分级技术，基层技术培训与服务常态化开展。在政策保障方面，财政资金已统筹支持农产品标准化及品质提升工作；品牌建设、产销对接工作稳步推进，现有品牌相关国家标准44项，全国“三品一标”农产品达8.6万个，分级农产品逐步实现优质优价，多地试点形成成熟可借鉴的工作模式。\n\n农业农村部表示，下一步，将从五方面持续推进工作：一是健全农产品全国统一分级标准体系，推动行业标准升级，细化品类规则，建立动态更新机制，构建国标引领、地方补充的标准格局；二是培育各类经营主体，加大科研投入，深化智能技术应用，完善基层技术服务；三是强化政策资金保障，争取专项财政支持、税费减免及金融保险服务，降低主体经营成本；四是畅通产销链路，搭建对接平台，培育农产品品牌，引导形成优质优价的消费氛围；五是扩大分级试点范围，总结推广典型经验，推动分级工作常态化、制度化。","中国食品报 2026年8月18日","2026-08-18T00:00:00Z","政策",10,false,86,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},28,22,17,12,7,1,"全国性政策进展，含具体数据与下一步措施，信息量大，权威性高，时效稍逊。",[25],{"name":10,"url":6},[27,28,29,30,31],"品牌建设","农产品分级","三品一标","农业行业标准","优质优价",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":42,"reason":75},[39,47,53,59,65,70],{"code":40,"score":41,"supported":42,"title":43,"abstract":44,"tags":46},"C",3,true,[],[45],"畜禽",[],{"code":48,"score":41,"supported":42,"title":49,"abstract":50,"tags":52},"C2",[],[51],"肉牛",[],{"code":54,"score":41,"supported":42,"title":55,"abstract":56,"tags":58},"D",[],[57],"水产",[],{"code":60,"score":41,"supported":42,"title":61,"abstract":62,"tags":64},"E4",[],[63],"农产品质量",[],{"code":66,"score":22,"supported":14,"title":67,"abstract":68,"tags":69},"E1",[],[],[28],{"code":71,"score":22,"supported":14,"title":72,"abstract":73,"tags":74},"E5",[],[],[27],"多个产业证据相当，需要确认主归属",[77,78],"农业行业标准 农产品分级 三品一标 优质优价","农业行业标准 农产品分级","农业行业标准农产品分级三品一标优质优价-806","2026-08-22T00:05:56.796290Z",{"total":82,"page":22,"page_size":82,"items":83},6,[84,149,219,275,327,393],{"id":85,"title":86,"url":87,"summary":88,"summary_zh":8,"content":89,"source_name":90,"source_url":8,"published_at":91,"category":92,"cover_url":8,"hotness":13,"is_selected":14,"score":93,"score_detail":94,"sources":101,"tags":103,"primary_topic":108,"secondary_topics":114,"classification":115,"search_phrases":143,"slug":146,"view_count":147,"doi":8,"paper":8,"created_at":148},4544,"黑龙江农科院：寒地龙果凭啥\"订单追着跑\"——蓝靛果种植规模世界第一，红树莓、黑加仑全国第一","https:\u002F\u002Fwww.stdaily.com\u002Fweb\u002Fgdxw\u002F2026-10\u002F09\u002Fcontent_593121.html","近日，黑龙江省农业科学院金秋博览会系列活动暨\"寒地龙果\"现场观摩会在黑龙江省农业科学院园艺分院举行。寒地龙果家族包括蓝靛果、秋子梨、软枣猕猴桃、寒地小苹果等特色果品，已成为黑龙江寒地果业快速发展的鲜活见证。黑龙江省蓝靛果种植规模位居世界第一，红树莓、黑加仑产量位居全国第一。文章援引国家葡萄产业技术体系蓝靛果哈尔滨综合试验站站长霍俊伟研究员观点，从2024年开始，以蓝靛果为代表的寒地小浆果迎来产业爆发转折点，曾经藏在深山无人识的山野小果一跃站上国内高端消费市场。企业代表高云丽介绍，2025年自主选育的\"蓝精灵\"蓝靛果鲜果送进盒马鲜生在北、上、杭门店，2026年拓展到全国10多个城市，供不应求。文章同时指出产业仍面临种植标准化、冷链物流、农业保险配套等短板，未来将通过\"做大基地、做强加工、做活流通、做亮品牌\"四步走差异化路径实现产业升级。","“订单源源不断，但是老百姓不敢种。”高云丽在会上道出产业痛点——果树种植见效周期长，不少农户心里犯嘀咕；产业种植碎片化，标准化生产体系尚未完全落地；冷链物流、农业保险、金融信贷配套仍有短板；区域公共品牌、企业品牌、产品品牌三者协同不足，制约产业进一步做大。\n\n针对这些现实难题，黑龙江省农业科学院副院长焦少杰结合多地实地调研情况，围绕寒地龙果产业高质量发展提出建议。“要错位布局赛道，规避产业内耗。”他表示，果树生长繁育周期漫长，盲目同质化布局将造成科研与产业资源浪费。不同市场主体、科研力量应当找准自身定位，有的要深耕品种选育，有的要主攻深加工、流通环节，实现分工协作，补齐全产业链短板。他还建议，强化政府主导，做强公共品牌，把省内各类特色果品纳入公共品牌体系，破解单品产能有限、市场仿冒乱象等现实问题；同时，要持续推动政研企联动，夯实产业根基。\n\n政策层面的扶持正在加速落地。黑龙江省农业农村厅中药材发展处（经济作物处）处长修国辉说，围绕寒地龙果产业，黑龙江确立“贯通全省、叫响全国、走向世界”三步走发展战略，落实“做大基地、做强加工、做活流通、做亮品牌”全链条工作部署。产业发展切忌品种“大而全”，要集中资源攻坚本省最优、最具道地性、市场潜力突出的核心品种，避免“样样通、样样松”的发展困境。\n\n修国辉表示，依托黑龙江高纬寒地、黑土地病虫害少的独特生态禀赋，寒地龙果将坚持走“小而精、特而强”的差异化路线，把黑龙江得天独厚的冷资源转化为富民兴产的热经济。","《科技日报》2026 年 10 月 09 日 转黑龙江省农业科学院","2026-10-08T16:00:00Z","报道",75,{"impact":95,"substance":96,"depth":97,"authority":98,"freshness":99,"relevant":22,"comment":100},20,18,16,13,8,"省级科研机构与主管部门共议寒地小浆果产业路径，含产业痛点与政策部署，信息增量与信源权威度较好，值得进入每日精选。",[102],{"name":90,"url":87},[27,104,105,106,107],"寒地龙果","蓝靛果","特色果业","小浆果产业",{"code":109,"slug":110,"name":111,"path":112,"parent_code":113},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":116,"locked":14,"version":35,"method":36,"evidence":117},"classified",{"candidates":118,"agricultural_evidence":42},[119,127,133,139],{"code":109,"score":120,"supported":42,"title":121,"abstract":122,"tags":126},9,[],[123,124,125],"苹果","葡萄","猕猴桃",[],{"code":128,"score":41,"supported":42,"title":129,"abstract":130,"tags":132},"E3",[],[131],"冷链",[],{"code":134,"score":41,"supported":42,"title":135,"abstract":136,"tags":138},"G3",[],[137],"农业保险",[],{"code":71,"score":22,"supported":14,"title":140,"abstract":141,"tags":142},[],[],[27],[144,145],"黑龙江农科院 寒地龙果 蓝靛果","寒地龙果 三步走 品牌","黑龙江农科院寒地龙果蓝靛果-4544",2,"2026-10-10T00:14:58.318072Z",{"id":150,"title":151,"url":152,"summary":153,"summary_zh":154,"content":8,"source_name":155,"source_url":152,"published_at":156,"category":157,"cover_url":8,"hotness":13,"is_selected":14,"score":158,"score_detail":159,"sources":161,"tags":163,"primary_topic":168,"secondary_topics":174,"classification":175,"search_phrases":195,"slug":198,"view_count":199,"doi":200,"paper":201,"created_at":218},4413,"Planting subsidies or brand building? Policy thresholds and goal conflict in agribusiness-led contract farming","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1964914","Introduction Under yield uncertainty and agribusiness-led contract farming, government intervention is important for sustaining agricultural production and supporting farmer profit. Yet production-side planting subsidies and demand-side brand-building policies operate through different mechanisms, leaving their relative advantages and applicable conditions unclear. This study examines how the government should choose between the two policies and how firm social responsibility shapes their relative performance. Methods We develop a sequential game involving a government, an agribusiness firm, and a farmer under stochastic yield. The firm's objective incorporates concern for farmer profit. Equilibrium decisions are derived by backward induction, and the policies are compared in terms of social welfare and farmer profit. Numerical analysis illustrates the analytical results. Results The planting subsidy policy directly strengthens the farmer's production incentive, whereas the brand-building policy expands market demand and induces the firm to offer a higher procurement price. The benefits of brand building depend critically on its cost-effectiveness. We identify two endogenous thresholds: a social-welfare threshold and a farmer-profit threshold, with the former strictly lower than the latter. As brand-building cost-effectiveness increases, policy preference shifts through three regions: planting-subsidy dominance, goal conflict, and brand-building dominance. In the intermediate region, brand building generates higher social welfare, while the farmer remains better off under planting subsidies. Yield risk, price sensitivity, and planting costs widen the goal-conflict region, whereas higher expected yield and stronger firm social responsibility narrow it. Market size affects absolute outcomes but does not change the relative policy ranking. Discussion These findings extend the agricultural-policy literature from the design of production subsidies to the choice between production-side and demand-side interventions. They show that improvements in aggregate welfare do not necessarily translate into greater benefits for farmers.","引言 在产量不确定性和农业企业主导的订单农业背景下，政府干预对于维持农业生产和支持农民利润至关重要。然而，生产端的种植补贴与需求端的品牌建设政策通过不同机制发挥作用，其相对优势和适用条件尚不明确。本研究考察政府应如何在两种政策之间进行选择，以及企业社会责任如何影响二者的相对表现。方法 我们构建了一个包含政府、农业企业和农户的序贯博弈模型，其中产量具有随机性。企业的目标函数中纳入了对农民利润的关注。通过逆向归纳法求解均衡决策，并从社会福利和农民利润两个维度对政策进行比较。数值分析用于验证解析结果。结果 种植补贴政策直接强化了农户的生产激励，而品牌建设政策则扩大了市场需求并促使企业提供更高的收购价格。品牌建设的收益关键取决于其成本效益。我们识别出两个内生阈值：社会福利阈值和农民利润阈值，且前者严格低于后者。随着品牌建设成本效益的提高，政策偏好依次经历三个阶段：种植补贴占优、目标冲突和品牌建设占优。在中间区域，品牌建设带来更高的社会福利，而农户在种植补贴下境况更好。产量风险、价格敏感性和种植成本会扩大目标冲突区域，而更高的预期产量和更强的企业社会责任则会缩小该区域。市场规模影响绝对结果，但不改变政策的相对排序。讨论 这些发现将农业政策文献从生产补贴的设计拓展至生产端与需求端干预之间的选择。研究表明，总体福利的改善并不必然转化为农民收益的增加。","Frontiers in Sustainable Food Systems","2026-10-07T00:00:00Z","论文",77,{"impact":97,"substance":18,"depth":96,"authority":98,"freshness":99,"relevant":22,"comment":160},"以序贯博弈模型揭示生产端补贴与需求端品牌建设之间的社会福利与农户利润目标冲突，为农业政策选择提供新结论，学术增量明确但属理论模型研究，公共影响有限。",[162],{"name":155,"url":152},[27,164,165,166,167],"农业政策","订单农业","农业补贴","农户收益",{"code":169,"slug":170,"name":171,"path":172,"parent_code":173},"J1","policy-planning","政策制度与发展规划","\u002Ftopic\u002Fpolicy\u002Fpolicy-planning","J",[],{"status":116,"locked":14,"version":35,"method":36,"evidence":176},{"candidates":177,"agricultural_evidence":42},[178,182,186,190],{"code":169,"score":41,"supported":42,"title":179,"abstract":180,"tags":181},[],[164],[],{"code":71,"score":147,"supported":14,"title":183,"abstract":184,"tags":185},[],[],[27,165],{"code":134,"score":22,"supported":14,"title":187,"abstract":188,"tags":189},[],[],[166],{"code":191,"score":22,"supported":14,"title":192,"abstract":193,"tags":194},"G4",[],[],[165],[196,197],"订单农业 种植补贴 品牌建设","农业政策 农业补贴 农户收益 品牌建设","订单农业种植补贴品牌建设-4413",0,"10.3389\u002Ffsufs.2026.1964914",{"doi":200,"openalex_id":202,"authors":203,"venue":155,"cited_by_count":199,"oa_url":210,"card":211,"direction":215,"ingested_from":217},"W7220848356",[204,207],{"name":205,"orcid":206},"Lidong Chen","https:\u002F\u002Forcid.org\u002F0000-0002-6228-1536",{"name":208,"orcid":209},"Zigong Cai","https:\u002F\u002Forcid.org\u002F0000-0001-8551-9159","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fsustainable-food-systems\u002Farticles\u002F10.3389\u002Ffsufs.2026.1964914\u002Fpdf",{"tldr":212,"method":213,"finding":214,"direction":215,"opportunity":216},"构建政府、农企与农户序贯博弈，比较种植补贴与品牌建设政策并识别目标冲突阈值。","随机产量下序贯博弈、逆向归纳与数值分析。","品牌建设成本效益提高使政策偏好经历补贴主导、目标冲突、品牌主导三阶段，福利与农户利润阈值不同。","农业人工智能与决策模型","可结合实证数据检验阈值，并设计兼顾社会福利与农户利润的混合政策机制。","openalex","2026-10-08T23:30:07.437474Z",{"id":220,"title":221,"url":222,"summary":223,"summary_zh":224,"content":8,"source_name":225,"source_url":222,"published_at":226,"category":157,"cover_url":8,"hotness":13,"is_selected":14,"score":227,"score_detail":228,"sources":230,"tags":232,"primary_topic":8,"secondary_topics":237,"classification":238,"search_phrases":257,"slug":260,"view_count":147,"doi":261,"paper":262,"created_at":274},4044,"BeLFG-Net: A Lightweight Betel Leaf Freshness Grading Network via Hybrid Depthwise Separable Convolutions","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102597","Post-harvest quality grading of betel leaves ( Piper betle L.) is critical to supply chain efficiency across South and Southeast Asia, yet assessment remains an entirely manual process susceptible to inter-rater inconsistency and throughput bottlenecks. Visual freshness cues—saturated green pigmentation, surface desiccation, and brown discoloration—form a continuous rather than discrete progression, making threshold-based color analysis insufficient. We propose BeLFG-Net, a Betel Leaf Freshness Grading Network, that addresses this challenge through a hybrid four-block encoder combining standard convolutions for initial feature establishment with depthwise separable pairs for parameter-efficient cross-channel mixing, followed by global average pooling and a compact classification head. The key efficiency gain arises from the depthwise separable factorization, which decouples spatial filtering from channel-wise integration and reduces computation approximately 8–9 × relative to equivalent standard convolutions, yielding a total of only 979,651 parameters. We further introduce a progressive dropout schedule ( p ∈ {0.25, 0.25, 0.25, 0.50}) that imposes strongest regularization at the bottleneck transition, effectively curbing overfitting on the 766-image field dataset augmented to 6,262 samples. On the three-class freshness discrimination task—fresh, moderate, and stale—BeLFG-Net achieves 95.72% test accuracy with per-class F1-scores of 0.96, 0.96, and 0.95, outperforming ResNet-50 (93.77%) and MobileNetV2 (91.65%) while using 26 × and 3.5 × fewer parameters, respectively. Ablation experiments confirm that the hybrid depthwise separable block design, progressive dropout, and global average pooling each contribute independently to generalization, with combined improvements of + 6.76 % over a standard CNN baseline. These results establish that domain-specific lightweight architectures can deliver high-accuracy post-harvest classification under the resource constraints common to agricultural edge deployments.","采后槟榔叶（Piper betle L.）品质分级对南亚和东南亚供应链效率至关重要，然而目前评估仍完全依赖人工，易受评估者间不一致和吞吐瓶颈的影响。视觉新鲜度线索——饱和绿色色素、表面干燥和褐色变色——呈连续而非离散变化，使得基于阈值的颜色分析不足以应对。我们提出BeLFG-Net，即槟榔叶新鲜度分级网络（Betel Leaf Freshness Grading Network），通过混合四模块编码器应对这一挑战，该编码器将用于初始特征建立的标准卷积与用于参数高效跨通道混合的深度可分离卷积对相结合，随后采用全局平均池化和紧凑分类头。关键效率提升源于深度可分离分解，它将空间滤波与通道整合解耦，相较于等效标准卷积减少约8–9倍计算量，总参数量仅为979,651。我们进一步引入渐进式dropout调度（p ∈ {0.25, 0.25, 0.25, 0.50}），在瓶颈过渡处施加最强正则化，有效抑制了在766张田间图像数据集（增强至6,262个样本）上的过拟合。在三类新鲜度判别任务——新鲜、中等和不新鲜——中，BeLFG-Net达到95.72%的测试准确率，各类别F1分数分别为0.96、0.96和0.95，优于ResNet-50（93.77%）和MobileNetV2（91.65%），同时参数量分别减少26倍和3.5倍。消融实验证实，混合深度可分离模块设计、渐进式dropout和全局平均池化各自独立促进泛化，相较标准CNN基线合计提升+6.76%。这些结果表明，领域特定的轻量级架构能够在农业边缘部署常见的资源约束下实现高精度采后分类。","Smart Agricultural Technology","2026-10-01T00:00:00Z",74,{"impact":20,"substance":18,"depth":96,"authority":98,"freshness":120,"relevant":22,"comment":229},"面向蒌叶采后分级的轻量化深度网络研究，方法新颖、数据与对比实验扎实，对农业边缘部署有参考价值，但属细分作物应用，产业影响有限。",[231],{"name":225,"url":222},[233,234,235,28,236],"智慧农业","农业人工智能","采后处理","轻量化模型",[],{"status":239,"locked":14,"version":35,"method":36,"evidence":240},"unclassified",{"candidates":241,"agricultural_evidence":42,"reason":256},[242,247,251],{"code":243,"score":147,"supported":14,"title":244,"abstract":245,"tags":246},"I2",[],[],[234,236],{"code":66,"score":22,"supported":14,"title":248,"abstract":249,"tags":250},[],[],[28],{"code":252,"score":22,"supported":14,"title":253,"abstract":254,"tags":255},"I1",[],[],[233],"缺少足够的主题证据",[258,259],"蒌叶 新鲜度 分级","BeLFG-Net 轻量网络","蒌叶新鲜度分级-4044","10.1016\u002Fj.atech.2026.102597",{"doi":261,"openalex_id":263,"authors":264,"venue":225,"cited_by_count":199,"oa_url":222,"card":269,"direction":215,"ingested_from":217},"W7216219039",[265,267],{"name":266,"orcid":8},"Fahim Ur Rahman",{"name":268,"orcid":8},"Afraz Ul Haque",{"tldr":270,"method":271,"finding":272,"direction":215,"opportunity":273},"提出轻量网络BeLFG-Net，实现槟榔叶采后新鲜度三级自动分级。","混合深度可分离卷积编码器+渐进Dropout，766张图像增强至6262张。","测试准确率95.72%，优于ResNet-50和MobileNetV2且参数量大幅减少。","可迁移至其他叶菜\u002F农产品采后分级，并探索边缘设备实时部署与多模态融合。","2026-10-03T23:30:03.701027Z",{"id":276,"title":277,"url":278,"summary":279,"summary_zh":8,"content":280,"source_name":281,"source_url":8,"published_at":282,"category":92,"cover_url":8,"hotness":13,"is_selected":14,"score":283,"score_detail":284,"sources":289,"tags":291,"primary_topic":297,"secondary_topics":302,"classification":303,"search_phrases":322,"slug":325,"view_count":22,"doi":8,"paper":8,"created_at":326},3232,"2026年中国热带作物产业大会在昆明举办——云南农科院发布咖啡重大科技成果 云南咖啡种植面积占全国98%以上","https:\u002F\u002Fwww.jingjiribao.cn\u002Fstatic\u002Fdetail.jsp?id=684363","9-17 经济日报报道：2026年中国热带作物产业大会9-17在云南昆明举行。本次大会聚焦咖啡这一热带作物，以\"咖位中国·链动全球\"为主题。云南省农业科学院发布咖啡重大科技成果，包括咖啡园\"乔—灌—草\"立体复合种植技术、咖啡化肥农药减施增效技术、咖啡鲜果无水加工技术、咖啡定向发酵关键技术等，覆盖种植、植保与加工环节。云南省市场监管局宣布成立云南省咖啡技术标准化委员会并揭牌。\"十四五\"期间，云南咖啡豆精品率从8%跃升至41.7%，精深加工率从20%提升到85%。2025年云南咖啡种植面积达151.88万亩、产量达17.07万吨，均占全国98%以上，咖啡全产业链产值达995亿元。","2026年中国热带作物产业大会9月17日在云南昆明举行。本次大会聚焦咖啡这一热带作物，以“咖位中国·链动全球”为主题，200余名专家学者、企业家、业界代表等围绕咖啡提质、品牌建设与国际合作展开研讨，推动我国咖啡向标准化、精品化、品牌化方向发展。\n\n![Image 1](https:\u002F\u002Fstatic.jingjiribao.cn\u002F2026\u002F9\u002F20\u002F20260920103055_7096.JPEG)\n\n开幕式上，云南省市场监管局宣布成立云南省咖啡技术标准化委员会并揭牌。云南省农业科学院发布咖啡重大科技成果，包括咖啡园“乔—灌—草”立体复合种植技术、咖啡化肥农药减施增效技术、咖啡鲜果无水加工技术、咖啡定向发酵关键技术等，覆盖种植、植保与加工环节。云南日报报业集团发布《中式咖啡文化传播影响力报告》。\n\n据介绍，云南热区面积约8.1万平方公里，是全国热区资源富集省份之一。近年来，云南立足多样立体的气候资源禀赋，大力发展热作产业，咖啡成为最具辨识度、最有竞争力的热作产业之一。“十四五”期间，云南咖啡豆精品率从8%跃升至41.7%，精深加工率从20%提升到85%。2025年，云南咖啡种植面积达151.88万亩、产量达17.07万吨，均占全国98%以上，咖啡全产业链产值达995亿元。\n\n本次大会设“变局与新机——全球咖啡格局重塑中的中国路径与中非、GMS（大湄公河次区域）机遇”“标准筑基·科技赋能——中国咖啡的品质根基与创新驱动”“从产地到品牌——云南咖啡的精品化跃迁”“世界咖啡·中国表达——中国咖啡文化国际传播”4个平行分论坛。\n\n本次大会由农业农村部南亚热带作物中心、云南省农业农村厅、昆明市人民政府共同主办，大会期间，云南还举办咖啡加工工职业技能大赛、花咖之夜、2026云南咖啡展、滇池国际咖啡文化嘉年华·“秋韵啡扬”、滇池国际咖啡文化嘉年华·翠湖咖啡主题市集等活动，让参会嘉宾、游客与本地消费者体验云南丰富多彩的咖啡文化。","经济日报","2026-09-17T00:00:00Z",87,{"impact":285,"substance":286,"depth":19,"authority":287,"freshness":82,"relevant":22,"comment":288},27,23,14,"全国性热带作物产业大会落地昆明，云南农科院发布覆盖种植到加工的重大科技成果，并给出精品率、精深加工率与全产业链产值等关键数据，产业级信息增量充足，值得进入每日精选。",[290],{"name":281,"url":278},[27,292,293,294,295,296],"标准化","咖啡产业","精深加工","热带作物","农业科技成果",{"code":298,"slug":299,"name":300,"path":301,"parent_code":113},"B3","tea-coffee","茶叶与咖啡","\u002Ftopic\u002Fhorticulture\u002Ftea-coffee",[],{"status":116,"locked":14,"version":35,"method":36,"evidence":304},{"candidates":305,"agricultural_evidence":42},[306,311,318],{"code":298,"score":20,"supported":42,"title":307,"abstract":309,"tags":310},[308],"咖啡",[308],[293],{"code":312,"score":82,"supported":42,"title":313,"abstract":314,"tags":317},"F4",[],[315,316],"农药","植保",[],{"code":71,"score":22,"supported":14,"title":319,"abstract":320,"tags":321},[],[],[27],[323,324],"云南农科院 咖啡 科技成果","云南咖啡 种植面积 全产业链产值","云南农科院咖啡科技成果-3232","2026-09-23T00:04:30.734823Z",{"id":328,"title":329,"url":330,"summary":331,"summary_zh":332,"content":8,"source_name":333,"source_url":330,"published_at":334,"category":157,"cover_url":8,"hotness":13,"is_selected":14,"score":158,"score_detail":335,"sources":338,"tags":340,"primary_topic":344,"secondary_topics":349,"classification":350,"search_phrases":375,"slug":378,"view_count":147,"doi":379,"paper":380,"created_at":392},2650,"Automated Cocoa Bean Classification and Defect Detection Based on ASEAN Standard Using Image Processing and Feature-Based Analysis","https:\u002F\u002Fdoi.org\u002F10.64823\u002Fijeee.2601005","This study presents an automated cocoa bean classification and defect detection system developed in accordance with the ASEAN Standard for Cocoa Bean (ASEAN Stan 34:2014). Implemented in MATLAB, the system utilizes digital image processing and computer vision techniques to segment individual cocoa beans, extract geometric, color, and texture features, and classify them into quality categories: Extra Class, Class I, Class II, and Non-Compliant. The image processing workflow integrates color space transformations (RGB to HSV), adaptive thresholding, and morphological filtering to ensure accurate segmentation. Feature extraction targets parameters such as area, length, aspect ratio, texture entropy, and color uniformity to identify specific defects including moldy, slaty, insect-damaged, and germinated beans. Validation against independent expert grading achieved an overall reliability rate of 96.2%, with high precision (0.93) and recall (0.91), and an average processing speed of 1.3 seconds per image. The developed analyzer provides an objective, rapid, and repeatable tool to support standardization and postharvest cocoa quality control across the ASEAN region. Keywords: Defect Detection; MATLAB; cocoa bean grading; ASEAN Standard; digital image processing; computer vision","本研究提出了一套依据《东盟可可豆标准》（ASEAN Stan 34:2014）开发的自动化可可豆分类与缺陷检测系统。该系统在MATLAB中实现，利用数字图像处理与计算机视觉技术对单颗可可豆进行分割，提取几何、颜色和纹理特征，并将其分为优质级（Extra Class）、一级（Class I）、二级（Class II）和不合格（Non-Compliant）四个质量类别。图像处理流程整合了颜色空间变换（RGB转HSV）、自适应阈值分割和形态学滤波，以确保分割的准确性。特征提取针对面积、长度、长宽比、纹理熵和颜色均匀性等参数，以识别霉变、僵化、虫害和发芽等特定缺陷。经与独立专家评级进行验证，系统总体可靠率达到96.2%，精确率为0.93，召回率为0.91，平均处理速度为每张图像1.3秒。所开发的分析仪为支持东盟地区可可采后质量控制的标准化提供了一种客观、快速且可重复的工具。关键词：缺陷检测；MATLAB；可可豆分级；东盟标准；数字图像处理；计算机视觉","International Journal of Electrical and Electronics Engineering","2026-09-14T00:00:00Z",{"impact":96,"substance":336,"depth":19,"authority":98,"freshness":99,"relevant":22,"comment":337},21,"基于东盟标准的可可豆自动分级与缺陷检测研究，方法成熟、验证可靠（96.2%），对热带经济作物产后质控有实用价值，但属细分领域技术进展，影响力有限。",[339],{"name":333,"url":330},[233,234,341,342,28,343],"计算机视觉","行业标准","可可产业",{"code":243,"slug":345,"name":346,"path":347,"parent_code":348},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":116,"locked":14,"version":35,"method":36,"evidence":351},{"candidates":352,"agricultural_evidence":42},[353,358,363,367,371],{"code":243,"score":99,"supported":42,"title":354,"abstract":355,"tags":357},[],[341,356],"computer vision",[234,341],{"code":298,"score":41,"supported":42,"title":359,"abstract":360,"tags":362},[],[361],"可可",[],{"code":66,"score":22,"supported":14,"title":364,"abstract":365,"tags":366},[],[],[28],{"code":252,"score":22,"supported":14,"title":368,"abstract":369,"tags":370},[],[],[233],{"code":169,"score":22,"supported":14,"title":372,"abstract":373,"tags":374},[],[],[342],[376,377],"农业人工智能 农产品分级 计算机视觉 可可产业","农业人工智能 农产品分级","农业人工智能农产品分级计算机视觉可可产业-2650","10.64823\u002Fijeee.2601005",{"doi":379,"openalex_id":381,"authors":382,"venue":333,"cited_by_count":199,"oa_url":385,"card":386,"direction":391,"ingested_from":217},"W7212670192",[383],{"name":384,"orcid":8},"Jennifer Natnat","https:\u002F\u002Fioro.org\u002Farticle\u002F529160740839\u002Fpdf",{"tldr":387,"method":388,"finding":389,"direction":215,"opportunity":390},"基于图像处理与特征分析，按东盟标准自动分类可可豆并检测缺陷。","MATLAB图像处理，RGB转HSV、自适应阈值、形态学滤波，提取几何颜色纹理特","系统分类准确率96.2%，精度0.93，召回0.91，单图处理1.3秒。","可扩展至多作物、多标准实时分级，结合深度学习提升复杂缺陷识别鲁棒性。","智慧农业 \u002F 农业物联网","2026-09-16T23:30:13.899726Z",{"id":394,"title":395,"url":396,"summary":397,"summary_zh":398,"content":8,"source_name":399,"source_url":396,"published_at":400,"category":157,"cover_url":8,"hotness":13,"is_selected":14,"score":401,"score_detail":402,"sources":404,"tags":406,"primary_topic":408,"secondary_topics":409,"classification":410,"search_phrases":434,"slug":436,"view_count":147,"doi":437,"paper":438,"created_at":452},2339,"Quality Assessment of Scotch Bonnet Pepper (Capsicum Chinense Jacq) Using Image Processing Techniques","https:\u002F\u002Fdoi.org\u002F10.53982\u002Fajerd.2026.0903.06-j","Scotch Bonnet peppers (Capsicum chinense) are globally cultivated cash crops prized for their distinct culinary uses and high nutritional profile. However, meeting rising consumer demands for premium quality is hindered by traditional manual inspection, which remains subjective, slow, and labour-intensive. To address this, this study presents a computer vision-based framework designed to automate the pepper grading process. A convolutional neural network (CNN), a support vector machine (SVM), and logistic regression were trained and tested using a diverse dataset of 455 images capturing peppers at multiple stages of maturity. The algorithms categorized the crops into binary quality classes (\"good\" vs. \"bad\") by analysing extracted physical attributes, including dimensions, geometry, colouration, and surface uniformity. Model performance was quantified using standard metrics, namely precision, recall, F1 score, and overall accuracy. The findings reveal that while all classifiers achieved acceptable benchmarks, the deep learning CNN model demonstrated superior capabilities, reaching an accuracy of 97%—outperforming logistic regression at 80% and the SVM at 78%. Ultimately, these outcomes validate the integration of automated image analysis systems into modern agricultural pipelines, offering a robust and scalable substitute for manual quality control.","苏格兰帽椒（Capsicum chinense）是全球广泛种植的经济作物，因其独特的烹饪用途和高营养价值而备受青睐。然而，传统的人工检测方式主观性强、速度慢且劳动强度大，难以满足消费者对优质产品日益增长的需求。为解决这一问题，本研究提出了一种基于计算机视觉的框架，旨在实现辣椒分级过程的自动化。研究使用包含455张图像的数据集对卷积神经网络（CNN）、支持向量机（SVM）和逻辑回归进行了训练和测试，该数据集涵盖了辣椒多个成熟阶段的图像。这些算法通过分析提取的物理属性（包括尺寸、几何形状、色泽和表面均匀度），将作物分为二元质量类别（“优质”与“劣质”）。模型性能采用标准指标进行量化评估，即精确率、召回率、F1分数和总体准确率。研究结果表明，尽管所有分类器均达到了可接受的基准水平，但深度学习CNN模型表现更为优异，准确率达到97%，优于逻辑回归的80%和支持向量机的78%。最终，这些结果验证了自动化图像分析系统融入现代农业流程的可行性，为人工质量控制提供了一种稳健且可扩展的替代方案。","ABUAD Journal of Engineering Research and Development (AJERD)","2026-09-12T00:00:00Z",71,{"impact":287,"substance":95,"depth":97,"authority":20,"freshness":120,"relevant":22,"comment":403},"基于CNN的辣椒品质自动分级研究，97%准确率且对比SVM与逻辑回归，方法清晰、结论可靠，对农产品智能分选有参考价值，但属细分作物应用，影响范围有限。",[405],{"name":399,"url":396},[233,234,341,407,28],"辣椒",{"code":243,"slug":345,"name":346,"path":347,"parent_code":348},[],{"status":116,"locked":14,"version":35,"method":36,"evidence":411},{"candidates":412,"agricultural_evidence":42},[413,420,426,430],{"code":243,"score":414,"supported":42,"title":415,"abstract":416,"tags":419},11,[],[417,341,418,356],"深度学习","deep learning",[234,341],{"code":421,"score":422,"supported":42,"title":423,"abstract":424,"tags":425},"B1",4,[],[407],[407],{"code":66,"score":22,"supported":14,"title":427,"abstract":428,"tags":429},[],[],[28],{"code":252,"score":22,"supported":14,"title":431,"abstract":432,"tags":433},[],[],[233],[435,377],"农业人工智能 农产品分级 计算机视觉 智慧农业","农业人工智能农产品分级计算机视觉智慧农业-2339","10.53982\u002Fajerd.2026.0903.06-j",{"doi":437,"openalex_id":439,"authors":440,"venue":399,"cited_by_count":199,"oa_url":396,"card":447,"direction":215,"ingested_from":217},"W7212404580",[441,443,445],{"name":442,"orcid":8},"Babatunde Olayinka Oyefeso",{"name":444,"orcid":8},"Rotimi Rufus Dinrifo",{"name":446,"orcid":8},"Oladapo Oyedeji",{"tldr":448,"method":449,"finding":450,"direction":215,"opportunity":451},"用图像处理和CNN\u002FSVM\u002F逻辑回归对苏格兰帽椒进行好坏二分类质量分级。","455张多成熟度辣椒图像，提取尺寸、几何、颜色、表面均匀性特征，训练CNN、SV","CNN准确率达97%，显著优于逻辑回归80%和SVM78%，验证自动图像分析可替代人工质检。","可扩展到多等级细粒度分级、多品种泛化及田间实时轻量化部署研究。","2026-09-13T23:30:43.649124Z"]