Resumen de: AU2026201258A1
A method for tracking surgical items with a system including an imaging system, a display, and one or more processors, the method comprising: capturing, with the imaging system, a video that depicts a user handling the surgical items; receiving, with the one or more processors, the video; 5 performing, with the one or more processors, computational analysis of the video to detect a characteristic arm motion of the user, wherein the characteristic arm motion is indicative of the user moving the surgical item to be counted in to a surgical procedure; updating, with the one or more processors, a count of surgical items in response to each instance of the characteristic arm motion being 10 detected; and displaying, on the display, the updated count. eb e b
Resumen de: EP4708229A1
Die Erfindung betrifft ein Verfahren zum Erzeugen eines Datensatzes zum Identifizieren von Holzwerkstoffplatten, bei dem mindestens zwei Holzwerkstoffplatten, insbesondere mehrere Holzwerkstoffplatten ein Plattenpaket bilden, bei dem zumindest ein digitales Bild von einem Teil des Plattenpakets mit Abschnitten der Seitenkanten der Holzwerkstoffplatten aufgenommen wird, bei dem Bildausschnitte aus dem digitalen Bild mit den Abschnitten der einzelnen Seitenkanten ermittelt werden, bei dem ein Vergleichsdatensatz für jeden Bildausschnitt anhand der Struktur der Holzwerkstoffelemente ermittelt wird, bei dem der Vergleichsdatensatz jeder Holzwerkstoffplatte gespeichert wird und bei dem mindestens eine Information zu der jeweiligen Holzwerkstoffplatte und zu dem jeweiligen Plattenpaket mit dem Vergleichsdatensatz jeder Holzwerkstoffplatte verknüpft und in einer Datenbank gespeichert werden. Zudem betrifft die Erfindung ein Verfahren zum Identifizieren einer Holzwerkstoffplatte.
Resumen de: MX2025012983A
Obtaining on-demand coatings delivered from a remote location based on vehicle data includes displaying a user interface on a digital display of a digital device being accessed by a user at a geographic location. User input is received that creates a record for a vehicle to be refinished. Spectrophotometric data and image data corresponding to the vehicle is received from a digital color measurement device. A representation of the vehicle in the form of selectable vehicle parts is displayed. A requested order is sent to a remote mixing server in a different geographic location to mix a user selected color match in an amount that reflects a quantity of coating calculated for a selected vehicle part.
Resumen de: WO2024227518A1
Smart box (1) for containing articles, the smart box (1) being connectable to a rack (2) in particular for manufacturing and/or retail purposes, the smart box (1) comprising a local control unit (3), in particular a microcontroller, for processing local signals, at least one sensor (4) for detecting or measuring a physical property related to the smart box (1) and/or the article, a box interface (5) to establish a signal connection with the rack (2), and at least a feedback indicator (6) for providing a feedback indication to a user related to the article based at least on a signal generated by the sensor (4).
Resumen de: EP4708167A2
An automated inventory monitoring system includes an image capture module able to create an image of an aisle of a retail store. Images of products labels are identified in the image and classified as shelf labels or peg labels. For shelf labels, an area of the shelf is defined and associated with the shelf label. Images of products are identified in the image and products on the shelf within an area associated with a shelf label are associated with the shelf label. Products located below a peg label are associated with the peg label. Based on the association between labels and products, out-of-stock products, plugs and spread may be detected and reported to the staff of the retail store.
Resumen de: EP4708169A1
A wearable device has a body with one or more connectors for coupling the body to a lanyard. A camera assembly is mounted on the body. The camera assembly includes a pair of cameras configured to capture images of an environment surrounding the wearable device. The wearable device also includes a network adapter to transmit data derived from the captured images to a processing system.
Resumen de: EP4708181A1
Computerized systems and methods are described for managing vendor-agnostic configure-to-order (CTO) and quote-to-order (QTO) processes. A Real-Time Data Mesh (RTDM) is provided for aggregating, standardizing, and normalizing real-time data from various sources. A Single Pane of Glass User Interface (SPoG UI) facilitates dynamic interaction and visibility into vendor performance. An Advanced Analytics and Machine-Learning (AAML) Module analyzes product compatibility, optimizes pricing strategies, and predicts market trends. A Vendor-Agnostic CTO/QTO Integration Module (VACIM) includes a Process Standardization Engine and a Vendor Data Transformation Gateway to ensure uniformity across vendors. Methodologies within the invention automate data processing, integrate transformation gateways for data consistency, and employ rule engines driven by machine learning for decision-making, thereby streamlining vendor processes, enhancing scalability, and optimizing pricing strategies in a scalable, adaptable framework.
Resumen de: GB2643876A
System and method 100 for inventory management includes a mobile device (440, fig. 4) configured to capture 110 product information by scanning a barcode and/or capturing a product image(s). A cloud-based database (212, fig. 2) stores 120 the information. Processing circuitry (420, fig. 4) validates the information through a multi-level approval process 130, updates 140 a real-time inventory status based on the validated information, and synchronises 150 the updated inventory data with the cloud-based database. The multi-level approval process may include sending the product information to first and second approvers, who may be human users and/or automated systems. In aspects, a user interface (500, fig. 5) displays product details and facilitates user interaction for inventory management tasks. Aspects enable efficient product onboarding, real-time inventory tracking, and seamless integration with existing store systems, addressing challenges of managing large product catalogues and maintaining accurate inventory data for small to mid-sized retail stores.
Resumen de: WO2024233300A1
This disclosure describes techniques for implementing an asset bucket on user devices for organizing assets in a database. Assets may include, without limitation, stored multimedia data from various sources, grouped multimedia data, events, conditions, parameters, environmental data, and other data or telemetry data that are stored in a network operating center (NOC) server database or a third-party database. The asset bucket may include a persistent working space that can be rendered as a pane on a device's user interface for organizing assets that can be selected from a rendered window or windows on the device's user interface and/or directly inputted on the persistent working space. By configuring the asset bucket to facilitate performance of actions on the selected assets, the asset bucket may improve generation of reports on these selected assets.
Resumen de: MX2025013075A
Example systems and methods are disclosed for determining a facility schedule for a growing facility. One example computer-implemented method includes, in response to an instruction, accessing, by a computing device, data representative of a growing facility and data representative of a product to be introduced into the growing facility and determining, by the computing device, a facility schedule based on a mixed integer programming model indicative of a product delivery schedule and resources of the growing facility. The method then includes implementing, by the computing device, the facility schedule into the growing facility.
Resumen de: AU2024220200A1
Attorney Docket No. 51071-97 A system may execute, by a generative artificial intelligence system, generative artificial intelligence algorithms trained on value chain network data. A system may receive input data including at least one of images, video, audio, text, programmatic code, and data, process the input data using the generative artificial intelligence algorithms to generate output content, wherein the output content includes at least one of structured prose, images, video, audio content, software source code, formatted data, algorithms, definitions, and context-specific structures, and generate an internal state of the generative artificial intelligence system, including a set of weights and/or biases as a result of prior processing. A system may provide the generated output content to a user interface for presentation to a user.
Resumen de: WO2024226741A2
A tractor has a processor and memory storing machine-readable instructions that, when executed by the processor, cause the processor to: select at least one image captured by a camera of a parking spot being passed by the tractor when a point-of-interest (POI) of the parking spot is most centered within a field of view of the camera, store the image in the memory in association with the parking spot, determine that the parking spot is occupied after a costmap for the parking spot is populated by the LIDAR, retrieve the image corresponding to the parking spot from the memory, determine, from the image, a trailer identifier of a trailer parked in the parking spot; and send a message defining the parking spot and the trailer identifier to an inventory service for use in updating a yard inventory.
Resumen de: WO2024226585A1
A method of identifying a product from a digital image includes receiving, at a digital identification service, image data associated with a digital image of an unregistered packaged product, and programmatically processing the image data, via the digital identification service, to identify a registered product that is different from and similar to the unregistered packaged product.
Resumen de: MX2025012697A
Aspects of the present disclosure relate to dynamically determining location attributes based on global positioning system (GPS) data. These techniques may include receiving GPS data from a plurality of devices associated with a physical structure. In addition, the techniques may include generating a virtual geofence around the physical structure based in part on GPS trajectory data derived from the GPS data, and determining one or more location attributes based on the virtual geofence. Further, the techniques may include presenting, via an application, the one or more location attributes within a site profile.
Resumen de: EP4708123A1
Embodiments of this specification provide a target object determination method and apparatus. The method is applied to an object scanning device, and includes: determining, in response to an object selection instruction, a current location according to a positioning electronic label; determining, according to the current location and object attribute information of initial objects, a target object electronic label of a target object whose distance to the current location falls within a preset distance range; and sending a guiding instruction to the target object electronic label, to cause the target object electronic label to guide, according to the guiding instruction and in a preset guiding manner, a user to select the target object. According to the method, based on a handheld terminal location, an electronic label indicator corresponding to a commodity in an order within a specific distance range may be triggered to be turned on, thereby avoiding a problem of mutual interference caused when electronic label indicators corresponding to all commodities in a plurality of orders are turned on simultaneously in a case that picking is performed for the plurality of orders, and improving the commodity picking efficiency.
Resumen de: CN121640356A
本发明公开了基于机器视觉的货架巡检方法、系统及存储介质,涉及货架巡检技术领域,包括以下步骤;步骤一:通过图像采集设备获取货架的视觉数据,在获取到数据后,通过大数据技术搭建采集设备运动路径,并对运动的路径进行标识;步骤二:使用计算机视觉和深度学习算法对图像进行处理,提取关键信息,在提取关键数据后对数据进行分析,数据分析后搭建存储数据库;步骤三:提前设定标准信息的基准数据及校验规则,将分析结果与存储数据库中的标准信息进行比对,生成巡检报告,包括缺货警报、价格错误和陈列错误。本发明能够实现不间断的巡检工作,巡检速度远超人工,且进行巡检时的准确性更高,减少人为疏忽和错误,数据客观可靠,能够实现可量化。
Resumen de: CN121638197A
本发明涉及物流管理技术领域,具体为一种农产品出口智能报关单据生成方法,包括以下步骤:采集目标农产品批次在加工厂出厂磅单、仓库入库地磅和集装箱装箱环节的计重数据,提取与批次对应的出口商AEO认证等级、历史差错率和申报货值,建立待处理综合数据档案。本发明基于对农产品批次在各物流节点的计重数据采集,将计重数据与出口商认证等级、历史差错率、申报货值等多维信息融合分析,通过理论水分蒸发率的计算,预测出理论重量,并进行称重数据的迭代校准,实现了更加精确的申报重量预测,解决出口申报重量误差大的问题。
Resumen de: CN121639086A
本发明涉及仓储管理技术领域,且公开了一种集约化智能仓储管理系统,包括多维监测模块和智能仓储模块。该系统通过多维监测模块采集所有物资的管理数据和所有库区的管理数据,并分类组成数据集,智能仓储模块实时判断每个等待入库的物资属性,以及与历史库位和各库区的适配程度,分别采用适配评分和适配指数两种机制进行库位匹配,为不同类别的物资提供了差异化的存放策略,智能化仓储处理效率高,智能仓储模块对每个已经入库物资的存放质量进行评估,生成损耗指数,再判断每个等待出库物资的循环特性,输出相应的存放建议和管理建议,实现了从被动管理到主动预警的升级,降低了维护成本和运营风险,精细化维护存放质量更稳定。
Resumen de: CN121639321A
本发明公开的属于智慧物流技术领域,具体为一种智慧物流竞价系统,包括:需求发布与智能匹配模块,用于通过引导需求方完成物流需求参数的规范化录入,并结合大数据分析匹配供应方资源池;特殊物流专项管理模块,用于在需求匹配基础上叠加专项资质审核,补充特殊需求参数,并适配专项竞价规则,从源头排除资质不符供应商,避免无效竞价与合规风险,为特殊物流场景的竞价公正性与履约安全性提供专项保障。本发明通过需求发布与智能匹配模块的跨区域供应商精准推送及资质、历史履约差评筛选,具有实现需求方打破地理限制、高效触达异地优质供应资源、拓宽供应资源池。
Resumen de: CN121639102A
本发明涉及仓储空间动态管理技术领域,尤其为一种基于多源数据融合与智能优化的仓储空间动态管理系统,包括实时数据采集与融合模块、动态需求预测与可视化模块、多目标动态优化决策模块、方案决策与指令执行模块及闭环反馈与模型更新模块,实时数据采集与融合模块整合多源数据生成综合状态数据集,动态需求预测与可视化模块基于该数据集预测需求并生成动态需求热力图,多目标动态优化决策模块构建多目标货位分配模型并自适应调整权重求解最优方案集,方案决策与指令执行模块选定方案并解析为操作指令,闭环反馈与模型更新模块形成闭环并更新预测模型。本发明实现仓储空间动态智能优化,提升运营效率,降低管理成本,适配现代化仓储管理需求。
Resumen de: CN121638617A
本发明涉及供应链管理技术领域,具体公开了基于AI供需匹配算法的供应链上下游企业资源协同分配方法。该方法包括:为各企业节点维护包含本体、推荐及通道信任分值的动态信任档案;构造融合供需属性与多维度信任特征的综合网络图;响应资源请求,执行跨层路径发现算法,在综合网络图中搜索路径综合信任度最优且可含多层转运节点的供应路径;据以生成协同分配方案,并在执行中要求关键节点基于其信任档案对流转进行验证与签注;方案执行后,依据实际行为数据更新相关节点的动态信任档案。本发明将动态信任深度融入匹配决策,实现了可靠、柔性且具备闭环学习能力的供应链资源协同分配。
Resumen de: CN121638680A
本发明提供一种面向服装线上销售运输环节的碳足迹核算方法,包括确定服装线上销售阶段的销售模式,基于销售模式明确针核算路径;收集对应核算路径上的服装线上销售运输环节的能耗数据以及辅助参数;构建基于订单地理分布的加权平均运输距离模型;基于退货率和换货率对加权平均运输距离模型进行更新得到动态运输距离修正模型;结合动态运输距离修正模型、能耗数据以及辅助参数构建多模态碳足迹核算模型,考虑了高退货率导致的退、换货逆向物流、高退换货率导致的多次逆向物流、根据订单比例地理距离分配、多车型混合运输等问题仓库库存能耗、订单处理能耗等线上销售特有的碳排放源,为优化物流路径、降低退货率、制定低碳运营策略提供数据支持。
Resumen de: CN121638909A
本发明公开了一种跨境商贸订单的动态风险监测系统,具体涉及国际贸易技术领域,其包括用于负责从各个源头获取跨境订单的数据并对这些数据进行整合的订单数据采集整合模块。本发明通过订单数据的实时采集和清洗,结合客户画像和物流追踪,系统能够精准识别并评估信用、地理、市场、物流及价格波动等多维度风险,智能决策模块在检测到异常风险时,能够自动触发警报并提供实时决策支持,帮助企业迅速响应并采取应急措施,数据分析报告模块通过生成实时风险状态、趋势预测和定制化报告,帮助管理者全面把握订单风险,优化决策过程,从而有效降低潜在风险、提升跨境商贸的安全性和合规性。
Resumen de: CN121639079A
本发明公开了一种农村地区卡车与无人机协同配送路径规划与资源调度方法,属于路径规划技术领域,该方法将带柔性时间窗的多目标卡车‑无人机车辆路径问题建模为深度强化学习中的奖励最大化问题,允许在容忍时间内偏离时间窗,并对严重偏差施加惩罚;采用多智能体模型,将由卡车及搭载无人机组成的配送单元视为智能体,通过多阶时空图卷积网络嵌入捕捉复杂物流网络的时空拓扑特征,利用其注意力机制对邻接节点特征加权求和生成客户节点的特定权重,增强智能体状态感知能力;并基于多智能体近端策略优化算法优化多个卡车‑无人机组协同的配送路径,该并行处理方法结合ST‑MGCN嵌入有效降低了动作空间搜索维度,提高了网络收敛速度和求解效率。
Nº publicación: CN121626590A 10/03/2026
Solicitante:
无锡星智数服科技有限公司
Resumen de: CN121626590A
本发明涉及仓储管理控制系统的技术领域,公开一种仓储系统一轨多车协同调度方法,包括以下步骤:基于预设动作触发运行模式调整以运行全局优化模式或实时响应模式;在实时响应模式下:每当出现一次预设动作,获取所有空闲运输设备的时间窗信息,根据时间窗信息和运输任务信息确定出最优的运输设备和运输任务请求的组合,将运输任务请求分配给对应的运输设备;在全局优化模式下:每当任意运输设备执行完一个运输任务,则将所有待执行的运输任务请求根据预设的算法确定需执行的运输设备,并存储到对应的分配队列中。通过灵活切换工作模式,仓储运输资源得到弹性分配,兼顾响应时效性和产线效率。