Alerta

一种识别极端洪枯事件的方法、装置、介质和设备

Resumen de: CN121561552A

本发明公开了一种识别极端洪枯事件的方法、装置、介质和设备，该方法包括：在获取目标流域各站点日水文序列后，提取年水文序列，对每个站点年水文序列进行突变点识别，确定各站点对应显著突变点；根据显著突变点确定基准年和变化年，将基准年的每日水位均值作为变化年的每日水位基准；根据每日水位基准和各个基准年中对应的同日水位计算标准差，根据每日水位基准和标准差的不同倍数划分出多个阈值区间；根据当前洪枯期中每日水位和对应阈值区间进行风险等级评估，在每日水位对应目标风险等级时确定潜在洪枯事件；根据潜在洪枯事件起始日期和持续天数，判定当前洪枯期是否发生极端洪枯事件。本发明提供的方案，能够更精准地识别极端洪枯事件。

一种多类型储能系统涉网性能评价方法、系统、设备及介质

Resumen de: CN121563050A

本发明涉及性能评估技术领域，公开一种多类型储能系统涉网性能评价方法、系统、设备及介质，包括：根据多类型储能系统接入电网评估需求确定一级指标和二级指标，并构建多类型储能系统涉网性能评价指标体系；通过结合第一评价算法、第二评价算法、第三评价算法对一级指标的权重和二级指标的权重进行分析；基于多类型储能系统涉网性能评价指标体系的指标值及对应的指标权重综合计算储能系统总体涉网性能，实现总体评估。本发明能够在构建多类型储能系统涉网性能评价指标框架体系的基础上利用主客观相结合评价方法全面地量化评估多类型储能系统涉网性能，具有较高准确性。

一种混凝土坝安全仪器监测数据与人工巡视检查数据相融合的方法

Resumen de: CN121561763A

本发明提供了一种混凝土坝安全仪器监测数据与人工巡视检查数据相融合的方法，属于水利水电工程领域。针对水电站大坝运行安全评估中仪器监测与人工巡视检查数据分离、关联性不足的问题，本发明通过构建大坝安全仪器监测与巡视检查融合知识图谱，实现监测和巡检项目的高效组织定位，解决监测数据与巡检缺陷的关联定位难题；在此基础上，通过建立考虑空间和逻辑关联性的模糊综合评价方法来计算获得大坝监测数据和巡视检查空间融合评判指标权重，实现了基于知识图谱和模糊综合评价的混凝土坝监测与巡检空间融合。该发明能有效整合监测数据与巡视结果，提升了安全分析的准确性，为全面评估大坝运行状态提供技术支持。

一种优化pH与磷含量提高农田土壤有机碳的管理方法

Resumen de: CN121565319A

本发明公开了一种优化pH与磷含量提高农田土壤有机碳的管理方法，涉及农田精准管理技术领域，包括：在目标农田区域部署涵盖pH、磷含量及温湿度多维传感节点的多参数智能传感器网络，并通过果蝇算法优化传感节点的布局；利用部署的多参数智能传感器网络持续采集土壤pH、速效磷含量、温湿度的多维传感数据。本发明引入基于强化学习的有机碳流失风险模型，能够从历史与实时数据中自主学习和建立土壤化学状态与有机碳流失风险之间的复杂非线性映射关系，且具备在线推理能力，可对实时传入的多维传感数据进行即时的流失风险等级评估，并基于多源校验逻辑触发预警，实现对有机碳流失风险的早期、准确识别和预警。

一种基于电力数据综合评估集成的能源转型指数量化方法

Resumen de: CN121563277A

本发明公开一种基于电力数据综合评估集成的能源转型指数量化方法，该方法主要用于能源转型评估领域，如能源政策制定、能源投资决策以及能源技术发展方向等方面。其步骤包括：构建指标体系、CRITIC‑BWM求取权重和模糊综合评价。S1：构建指标体系时，从能源供应结构、电力清洁化、政策支撑和经济效益四个维度出发，细化出可再生能源占比、传统能源占比、能源自给率等十二个二级指标；S2：CRITIC‑BWM求取权重则分为CRITIC法计算客观权重和BWM法计算主观权重，最后进行权重综合；S3：模糊综合评价包括模糊集合构建和模糊综合评价模型两个步骤，通过计算指标隶属度、构建模糊关系矩阵，将最终权重向量与模糊关系矩阵结合，确定能源转型指数的最终评价等级并分析各指标影响。

一种基于多属性模糊决策算法的异性纤维含量多指标评价方法

Resumen de: CN121562844A

本发明涉及棉花中异性纤维含量评定和多属性群决策方法的相关领域，公开了一种基于多属性模糊决策算法的异性纤维含量多指标评价方法，旨在解决国标中异性纤维含量评价指标单一问题，综合考量多类属性指标，在考虑权重未知和保证评价函数唯一解前提下，建立异性纤维含量多属性指标评价方法。本发明包括：决策方法对比模块将现有多种模糊决策算法对比以获取适用算法，确定决策算法主体；数据获取模块从输入端获取多属性指标的异性纤维含量数据；数据预处理模块考虑数据误差生成决策矩阵，并进行规范化处理；权重确定模块计算异性纤维决策集和属性集的权重分布；决策机制模块将模糊决策环境结合适用功能算子构建聚合算子；聚合计算模块根据聚合算子和权重信息进行异性纤维多属性指标含量聚合计算；评价优化模块根据增广矩阵对评价函数优化；分析对比模块实现决策结果敏感度分析及决策方案对比。

METHODS AND SYSTEMS FOR NEURAL NETWORK OPTIMIZATION

Resumen de: WO2026039827A1

Methods and systems for optimizing neural networks, and in certain embodiments optimizing neural networks for low power edge devices/ sensors and providing fault tolerance for neural network execution. Certain disclosed neural networks can change width during inference, such as using one width for one layer, and using a different width for a later layer and such networks may be trained such that the accuracy at any width/depth combination is equivalent to a standard network (that cannot change) of the same width and depth.

METHOD AND SERVICE SERVER FOR PROVIDING CUSTOMIZED CONTENTS RECOMMENDATION INFORMATION CORRESPONDING TO A VIRTUAL PROFILE GROUP

Resumen de: KR20260022131A

네트워크를 통해 연결된 셋톱박스에게 서비스를 제공하는 서비스 서버의 동작 방법으로서, 상기 셋톱박스로부터 상기 셋톱박스와 연결된 무선 액세스 포인트의 서비스 커버리지에서 단말 스캔을 통하여 획득된 개인 단말 스캔 정보를 수신하는 단계, 복수개의 가상 프로필 그룹 별로 각 가상 프로필 그룹의 구성원인 적어도 하나 이상의 개인 단말 식별자가 매핑되어 저장된 가상 프로필 그룹 DB로부터, 상기 개인 단말 스캔 정보의 개인 단말 식별자에 매핑되는 적어도 하나의 가상 프로필 그룹을 추출하는 단계, 그리고 추출한 가상 프로필 그룹에 매칭되는 커스터마이즈된 컨텐츠 추천 정보를 상기 셋톱박스에게 전송하는 단계를 포함한다.

APPARATUS AND METHOD OF TRANSPORT DATA AGGREGATION

Resumen de: US20260049833A1

An apparatus and method for transport management is presented. The apparatus includes a memory communicatively connected to a processor to output routing data of transport entities as a function of aggregated transport data, wherein the outputting comprises: receive transport data and bound parameters of a transport from a carrier device; iteratively train an aggregation machine-learning model to combine the transport data, wherein the training comprises generating an aggregation training data correlating the transport data as inputs and aggregated transport data as outputs; modify a characteristic of the transport; update the aggregated transport data based on the modification of the characteristic of the transport; retrain the aggregation machine-learning model as a function of the updated aggregated transport data; generate the routing data, wherein the routing data comprises instructions to further modify the characteristic of the transport; and automatically change the characteristic of the transport based on the routing data.

リスク評価に基づく都市排水貯留調節施設運転の段階的な意思決定解析方法

Nº publicación: JP2026505807A 18/02/2026

Solicitante:

長江生態環保集団有限公司

Resumen de: WO2025145610A1

An urban drainage, regulation and storage facility operation step-by-step decision analysis method based on risk assessment. When information of each decision standard preference for urban drainage, regulation and storage facility operation is completely missing or is unclear, a method combining game theory with feasible weight space is used to aggregate urban drainage, regulation and storage facility operation weights; stochastic multi-criteria decision analysis algorithm and fuzzy optimization models are used to construct a stochastic multi-criteria decision analysis-fuzzy optimization model for the urban drainage, regulation and storage facility operation; an urban drainage, regulation and storage facility operation decision risk assessment model is constructed to quantitatively assess the risk of urban drainage, regulation and storage facility operation decision errors; and multi-stage multi-criteria decision analysis is used to determine step by step information of the weight of each standard of the urban drainage, regulation and storage facility operation, thereby achieving an optimal decision for the urban drainage, regulation and storage facility operation.