Alerta

一种物流运输成本数据的处理方法和装置

Resumen de: CN121073334A

本发明公开了一种物流运输成本数据的处理方法和装置，涉及计算机技术领域。该方法的一具体实施方式包括：响应于接收到成本数据处理指令，基于数据表的元数据信息，对待处理成本数据进行特征识别，得到待处理成本数据对应的分摊特征；通过决策树算法从预设的分摊因子集合中选取目标分摊因子；基于深度学习算法和可用路径筛选规则从预设的分摊路径集合中选取目标分摊路径；根据待处理成本数据对应的分摊特征、目标分摊因子和目标分摊路径进行成本数据处理。该实施方式提升分摊配置的灵活性和合理性、降低人为干预和依赖，减少返工迭代，避免不必要的资源消耗，降低计算代价，提高数据处理效率。

农业供应链数据分析系统及方法

Resumen de: CN121071933A

本发明公开了农业供应链数据分析系统及方法，涉及农业数据安全技术领域，各主体先对生产、库存、销量记录进行差分隐私扰动与同态加密并上传，平台据此构建数据面；随后调用知识图谱语义映射器，将加密特征映射至产量‑库存‑销量三元框架并对齐时间索引；在语义对齐数据流上，利用联邦学习训练时序图神经网络，输出带置信区间的全局需求预测；基于该预测，结合库存策略，采用深度强化学习生成补货量计划与优先级列表下发；主体执行后，将实际销售等反馈再次加密上传，平台增量更新知识图谱并用元学习微调模型，同时动态调整隐私预算，提升供应链韧性与精确度值。

智能码垛机器人的智能调度系统及方法

Resumen de: CN121073148A

本发明提供了一种智能码垛机器人的智能调度系统及方法，方法包括步骤S1：通过深度相机采集物料点云数据并识别物料尺寸，获取物料重量；步骤S2：根据物料尺寸计算物料体积，并结合物料重量得到密度值；计算气动夹爪的行程参数，并通过智能规划算法生成码垛方案；步骤S3：基于所述行程参数控制气动夹爪开合以抓取物料，执行所述码垛方案完成物料堆叠；步骤S4：检测堆叠完成的物料的外形，使WMS储位调度模块根据检测结果将物料配送至合适的储位。本发明针对柔性物料的形态特性，采用凸包分析与异常值过滤结合的尺寸识别方法，提高了非规则物体测量精度，解决了茶叶等多规格柔性散装物料在码垛环节中换型慢、破损高、调度低效的问题。

一种面向多场景多目标约束的充电基础设施维修物资协同调度方法

Resumen de: CN121073117A

本发明公开了一种面向多场景多目标约束的充电基础设施维修物资协同调度方法，属于物资协同调度领域。针对充电基础设施维修过程中物资运输、库存管理及设备翻新等环节，充分考虑多场景、多目标与多约束条件。对调度问题进行数学建模，构建涵盖成本最小化、缺货惩罚、翻新与碳排放控制等多目标优化模型，并综合运输、库存和翻新等动态约束。随后，采用基于人工旅鼠算法的智能优化策略对模型求解，获得各场景下的最优物资调度方案。该方法能够灵活应对需求变化与多目标冲突，提升充电基础设施维修物资的调度效率与资源利用率，降低运维总成本，满足绿色低碳及应急保障的行业需求。

一种基于多维数据的药品市场需求预测方法及系统

Resumen de: CN121073538A

本发明涉及医药供应链管理技术领域，尤其涉及一种基于多维数据的药品市场需求预测方法及系统，其方法包括：采集并预处理多源业务数据；构建张量网络的动态因果图获取因果嵌入，采用格罗莫夫‑瓦瑟斯坦与施罗丁格桥对齐潜空间，并以路径瓦瑟斯坦正则约束轨迹；在带状态空间记忆的条件扩散模型中生成需求分位数曲线，结合增广拉格朗日与保形预测实现可行域与覆盖率保证；将分位数与库存状态输入强化学习策略网络，在数字孪生供应链中闭环更新。本发明提升极端场景下的鲁棒性、可解释性与策略稳定性。

订单取件开箱验视连拍方法、装置、设备及存储介质

Resumen de: CN121077754A

本发明涉及物流领域，公开了订单取件开箱验视连拍方法、装置、设备及存储介质，该方法用于按预设序列采集取件开箱影像。该方法包括：获取待取订单的订单信息和预分配取件人信息，并对取件人进行身份校验，将校验通过的订单标记为可取件订单；根据可取件订单的物品类型匹配基础拍摄参数；按照环境全景、包裹外观、开箱过程、物品细节的预拍摄顺序生成拍摄指令；提取已完成拍摄的影像数据，将提取的影像数据保存在终端设备的本地缓存模块，形成本地缓存数据，并将提取的影像数据通过分片压缩技术异步推送至云端服务器，形成云端数据；校验本地缓存数据与云端数据的一致性，通过后删除本地缓存数据，并生成带时间戳的验视档案。

基于地理围栏的社区化商品服务匹配方法、系统及介质

Resumen de: CN121073595A

本发明涉及基于地理围栏的社区化商品服务匹配方法、系统及介质涉及互联网通信领域中的网络虚拟社区交流技术领域，旨在解决传统服务中信息过载、信用缺失及服务半径失控三大核心问题。技术方案通过构建动态地理围栏引擎，结合用户设定距离实时生成电子围栏，严格约束信息推送与履约范围；采用语音化信息处理系统，将文字信息转化为1.2倍速吆喝式音频，突破视觉交互限制；创新区块链信用管理模块，通过押金冻结机制与自动化罚没规则建立刚性的社区交易担保；同步开发分层履约调度模型，整合自提、商户直送及社区中老年劳动力配送三模式，实现资源精准匹配。

冷链供应链风险监控方法及系统

Resumen de: CN121073329A

本发明涉及供应链风险监控技术领域，公开了一种冷链供应链风险监控方法及系统，该方法包括：采集冷链交接环节的温度数据、时间戳数据和操作视频数据；基于所述温度数据计算温度暴露积分值，并基于所述操作视频数据进行交接操作合规性验证，得到验证结果；基于所述温度暴露积分值调整HACCP关键控制点的风险阈值；基于所述温度暴露积分值、所述验证结果和所述时间戳数据进行责任归属计算，得到交接责任分配结果并基于所述风险阈值生成风险监控验证报告，本发明能够精确量化货品在交接过程中的累积温度危害，提高了操作监管的效率和准确性，进而提升了风险防控的有效性。

Verfahren und System zum Befüllen eines Parkplatzes mit Fahrzeugen zum Verladen auf einen Autozug sowie Computerprogrammprodukt

Resumen de: DE102024115376A1

Die Erfindung betrifft ein Verfahren zum Befüllen eines Parkplatzes (18) mit Fahrzeugen (10) zum Verladen auf einen Autozug (12), das folgende Schritte aufweist: a) Erfassen von Produktionsdaten, die Informationen bezüglich einem Fahrzeugtyp und einem Fertigstellungszeitpunkt für jedes Fahrzeug (10) aufweisen, von Parkplatzdaten, die Informationen zur Anzahl an verfügbaren Parkplätzen (18) und zur Anzahl an belegten Parkplätzen (18) aufweisen, von Fahrzeugdaten, die wenigstens einen geometrischen Parameter zu jedem Fahrzeug (10) aufweisen, und von Autozugdaten, die wenigstens einen geometrischen Parameter des Autozuges (12) aufweisen, und b) Ermitteln der Positionen der Fahrzeuge (10) auf dem Parkplatz (18), indem Fahrzeugbündel (34, 36) auf Basis der Produktionsdaten, der Parkplatzdaten, der Fahrzeugdaten und der Autozugdaten gebildet werden, wobei abwechselnd ein Fahrzeugbündel (34) einer oberen Ladeebene (20) eines Waggons (22) des Autozuges (12) und ein Fahrzeugbündel (36) einer unteren Ladeebene (24) eines Waggons (22) des Autozuges (12) zugeordnet sind. Des Weiteren betrifft die Erfindung ein System (26) zum Beladen eines Autozugs (12) mit Fahrzeugen (10) sowie ein Computerprogrammprodukt.

搬送計画作成装置、搬送計画作成方法、及び搬送計画作成プログラム

Resumen de: JP2025176680A

【課題】運搬車両間の作業干渉を抑制しつつ運搬車両の作業負荷を平準化し、運搬車両全体の作業効率を向上させる。【解決手段】搬送計画作成装置１０は、運搬車両が前記運搬作業を実行する際に要する時間である運搬作業時間を運搬作業毎に算出し、複数の運搬作業から複数の運搬作業群を生成し、運搬作業群に含まれる一の運搬作業の終了後の搬送先から運搬作業群に含まれる他の運搬作業の搬送先までの、運搬対象の積載されていない状態の台車を載せた運搬車両の移動時間を示す空搬送時間の指標である運搬作業組合せ負荷を運搬作業群毎に算出し、運搬作業組合せ負荷と運搬作業時間から算出される作業負荷評価値を運搬作業群毎に算出し、各運搬作業群の作業負荷評価値が平準化するように複数の運搬作業群を再編成し、運搬作業群の単位で運搬車両に運搬作業を割り当て、運搬車両に割り当てられた運搬作業群に含まれる運搬作業の搬送順番を決定する。【選択図】図４

Verfahren zum Einrichten und/oder Verwalten eines Arbeitsbereichs für das Handwerk, Computerprogramm und Datenverarbeitungsanlage

Resumen de: DE102024115199A1

Die Erfindung betrifft ein Verfahren zum Einrichten und/oder Verwalten eines Arbeitsbereichs für das Handwerk, insbesondere Elektrohandwerk, KFZ-Handwerk, Sanitärhandwerk, Schreinerhandwerk und dergleichen, insbesondere Werkstätten, Lagerräume, Montagelinien, Sozialräume, unter Verwendung einer Datenverarbeitungsanlage mit wenigstens einem Datenspeicher, wenigstens einer Eingabeeinrichtung und wenigstens einer Anzeigevorrichtung mit den Schritten: Bereitstellen eines Katalogs mit mehreren digitalen dreidimensionalen Modellen von Werkstatteinrichtungen, insbesondere Regale, Schränke, Werkbänke, Arbeitsplätze, Werkstattwagen und/oder Platzhalter für große Sonderwerkzeuge oder Maschinen, Bereitstellen eines Katalogs mit mehreren dreidimensionalen digitalen Modellen von Werkstattausstattungen, insbesondere Einlagen für Werkzeuge, Lagerboxen und Kartons für Verbrauchsmaterialien, beispielsweise Schrauben und/oder Platzhalter für Sondereinlagen oder Sonderbehältnisse, Bereitstellen eines Katalogs mit mehreren dreidimensionalen digitalen Modellen von Werkstattfüllgütern, insbesondere Werkzeuge, Flüssigkeiten, Verbrauchsmaterialien, Kleinteile und/oder Platzhalter für Sonderwerkzeuge, Bereitstellen eines dreidimensionalen digitalen Raumplans der Werkstatt, Auswählen mindestens einer Werkstatteinrichtung aus dem Katalog der Werkstatteinrichtungen und Anordnen der ausgewählten Werkstatteinrichtung in dem digitalen Raumplan des Arbeitsbereichs, Auswählen mindestens

VERFAHREN UND VORRICHTUNG ZUM PACKEN VON OBJEKTEN IN BEHÄLTER

Resumen de: DE102025118053A1

Die vorliegende Anmeldung betrifft ein Verfahren zum Packen von Objekten in Behälter, das Folgendes umfasst: Bestimmung mehrerer Kandidaten-Teilräume im Behälter basierend auf dem aktuellen Zustand des Raums im Behälter; Kodierung der mehreren Kandidaten-Teilräume und der Abmessungen eines ersten den Behälter zu befüllenden Objekts als Kandidaten-Teilraum-Einbettungssequenz und erste Objekt-Einbettungssequenz; Durchführung einer Attention-Verarbeitung in der Kandidaten-Teilraum-Einbettungssequenz und der ersten Objekt-Einbettungssequenz, um eine mittels Attention verarbeitende Kandidaten-Teilraum-Merkmalssequenz und eine mittels Attention verarbeitende erste Objekt-Merkmalssequenz zu erhalten; Bestimmung einer Position im Behälter zum Platzieren des ersten Objekts basierend auf der mittels Attention verarbeitenden Kandidaten-Teilraum-Merkmalssequenz und der mittels Attention verarbeitenden ersten Objekt-Merkmalssequenz.

ASSOCIATION-BASED INTELLIGENT ASSET TRACKING

Resumen de: WO2025250409A1

Systems and techniques are described herein for association-based asset tracking. For instance, a computing device (e.g., an application server) can determine a plurality of associations among a plurality of assets. The computing device can monitor a plurality of messages being communicated corresponding to each association of the plurality of associations, detect an exception has occurred based upon the monitoring, and generate a notification based upon the detected exception. Each association of the plurality of associations can be created between two different assets of the plurality of assets. Each of the two different assets can be in a same mesh network or can be in different mesh networks.

INDIVIDUALIZED INFORMATION AND RECOMMENDATION SYSTEM FOR VEHICLES

Resumen de: WO2025250282A1

A method for providing customized information to a user, that includes receiving at a backend portion historical information, regarding multiple features, from a first user and one or more other users, categorizing the information and users as a function of a similarity of certain features of the historical information, receiving at the backend portion current information from the first user, determining a predicted future use as a function of at least some of the historical information and at least some of the current information, and providing a customized recommendation from the backend portion to the first user.

APPARATUS, SYSTEM, AND METHOD FOR TRACKING AN ASSET IN A DECENTRALIZED MESH WIRELESS COMMUNICATION NETWORK

Resumen de: WO2025247512A1

A method for tracking an asset in a decentralized mesh wireless communication network. A positioning engine receives noisy location data from a plurality of location tracking tag devices at time intervals. At least one of the plurality of the location tracking tag devices is positioned on an asset. The plurality of location tracking tag devices form part of the decentralized mesh wireless communication network. Each of the plurality of location tracking tag devices periodically receives location reference information from a location reference device. The positioning engine records the noisy location data received from the plurality of location tracking tag devices with a time stamp. The positioning engine generates a clean dataset from the noisy location data received from the plurality of location tracking tag devices at each recorded time stamp. The positioning engine computes a position of the asset based on the clean dataset.

Machine Learning Assisted Alerts for Item Picking

Resumen de: US2025371495A1

A machine-learned predictive model is trained to predict potential for customer complaint. The model is part of an online concierge system. The online concierge system accesses a customer order that includes one or more items. The online concierge system determines input data for an item of the one or more items. The online concierge system determines a prediction value associated with potential for customer complaint for the item by applying the machine-learned prediction model to the input data. The online concierge system provides the prediction value to a picker client device associated with a picker who is assigned the item. The picker client device presents an alert to the picker based in part on the prediction value, and the alert includes a message that is customized to mitigate a cause of potential customer complaint for the item.

Method and System for Supply Chain Data Optimization and Visualization

Resumen de: US2025371487A1

A computer-implemented method for supply chain data optimization and visualization is provided. The method includes receiving training input and output data. The training input data comprises historical maritime and supply chain traffic data and the training output data comprises predicted supply chain routes. The method includes training a machine learning model using the training input and output data to generate a mapping function which maps the training input data to the training output data. The method includes generating an optimized supply chain route and at least one alternate supply chain route using selected parameters and the mapping function. The method includes displaying a visual representation of the optimized supply chain route and the alternate supply chain route.

Computer Model for Determining Optimal Value for an Item Based on a Predicted Elasticity of Demand

Resumen de: US2025371586A1

An online concierge system receives item data for an item included among an inventory at a retailer location, in which the item data includes a set of real-time item data for the item and a set of constraints. The system accesses and applies a first machine-learning model to predict a freshness satisfaction score for the item based at least in part on the item data. The system updates the item data to include the score and accesses and applies a second machine-learning model to predict an elasticity of demand for the item based at least in part on the updated item data. The system determines an optimal value associated with the item based at least in part on the freshness satisfaction score, the elasticity of demand, and the set of constraints. A value associated with the item is then adjusted based at least in part on the optimal value.

ASSOCIATION-BASED INTELLIGENT ASSET TRACKING

Resumen de: US2025371484A1

Systems and techniques are described herein for association-based asset tracking. For instance, a computing device (e.g., an application server) can determine a plurality of associations among a plurality of assets. The computing device can monitor a plurality of messages being communicated corresponding to each association of the plurality of associations, detect an exception has occurred based upon the monitoring, and generate a notification based upon the detected exception. Each association of the plurality of associations can be created between two different assets of the plurality of assets. Each of the two different assets can be in a same mesh network or can be in different mesh networks.

Aerospace Commerce Exchange

Resumen de: US2025371516A1

An aerospace commerce exchange system may include a network, a plurality of clients operably coupled to the network, and an aerospace commerce exchange platform operably coupled to the network to provide exchange services to the clients. At least one of the clients may be operably coupled to the aerospace commerce exchange platform via an air-to-ground wireless communication link or satellite link (or other links with which an aircraft may be associated) to provide or receive data associated with at least one of the exchange services.

METHODS AND SYSTEMS FOR INTELLIGENTLY MANAGING AND USING DATA IN A SUPPLY CHAIN ENVIRONMENT

Resumen de: WO2025250590A1

The present disclosure provides systems and methods for querying information related to a supply chain company. The method comprises receiving, via a graphical user interface (GUI), a user prompt in natural language inquiring information related to a supply chain company, generating, using a thought-based query generator, a database query based at least in part on the user prompt, executing the database query in a database to retrieve data and transmitting the data to a large language model (LLM), and generating an output by the LLM and displaying the output in the GUI.

WEARABLE LESSONS AND APPAREL EDUCATIONAL SYSTEM

Resumen de: WO2025250848A1

The present disclosure teaches a digital learning platform in which lessons and other interactions with the platform key off of a learner's inspiration by a wearer's garment with a graphic design and coding unique to that singular garment. The unique coding enables the learner to connect to the platform with their network connected, code scanning mobile device to access a lesson or course related to the graphic design while the wearer/user of the garment may receive value, points, and credit for the learner's activity.

APPLYING ENTRY EDGES IN A COVERED ENVIRONMENT

Resumen de: WO2025250660A1

Embodiments include a method that includes determining a location of a restriction zone, where the restriction zone includes a first edge and a second edge, providing an option to define a first policy for a materials handling vehicle when crossing into the restriction zone via the first edge and a second policy when crossing into the restriction zone via the second edge, and receiving user input defining the first policy and the second policy. Some embodiments include determining a location and an orientation from the materials handling vehicle, determining from the location and the orientation, that the materials handling vehicle is approaching the restriction zone via the first edge or the second edge, and communicating first policy data related to the first policy to the materials handling vehicle. Some embodiments include in response to determining communicating second policy data related to the second policy to the materials handling vehicle.

CONTAINER HANDLING METHOD AND APPARATUS, AND WAREHOUSING SYSTEM

Resumen de: WO2025246768A1

A container handling method and apparatus (1100), and a warehousing system (100). The warehousing system (100) comprises an inventory area (10), a control apparatus (110), first handling devices (120), second handling devices (130), and workstations (140). When each first handling device (120) completes a picking task at a corresponding workstation (140), in response to a return-to-warehouse instruction, on the basis of the position of the first handling device (120), the control apparatus (110) plans a pre-movement path for the first handling device (120); the control apparatus (110) controls the first handling device (120) to move along the pre-movement path, and during the movement of the first handling device (120) along the pre-movement path, determines a target return-to-warehouse path corresponding to the first handling device (120) returning from the workstation (140) to the inventory area (10); and the control apparatus (110) controls the first handling device (120) to return to the inventory area (10) along the target return-to-warehouse path.

Inventory quantity calculation system for estimating inventory quantities

Nº publicación: US2025371493A1 04/12/2025

Solicitante:

INNOLUX CORP [TW]
InnoLux Corporation

Resumen de: US2025371493A1

An inventory quantity calculation system includes a receiving unit, a calculation unit, and an output unit. The receiving unit receives historical beginning-of-period stock quantity estimates, historical end-of-period stock quantity estimates, historical end-of-period actual stock quantities, and historical estimated shipment quantities. Based on the received historical beginning-of-period stock quantity estimates, historical end-of-period stock quantity estimates, historical end-of-period actual stock quantities, and historical estimated shipment quantities, the calculation unit determines a decision value and calculates a first stock quantity estimate and a second stock quantity estimate for the end of the next time period. The output unit outputs the first stock quantity estimate, the second stock quantity estimate, or a third stock quantity estimate based on the decision value. The third stock quantity estimate is calculated based on the first stock quantity estimate and the second stock quantity estimate.