Feedback-driven exogenous factor learning in time series forecasting

    公开(公告)号:US09665830B2

    公开(公告)日:2017-05-30

    申请号:US14341525

    申请日:2014-07-25

    IPC分类号: G06F17/00 G06F17/20 G06N99/00

    CPC分类号: G06N99/005

    摘要: A system for forecast modeling includes at least one processor and at least one database that is operably coupled to the at least one processor. The database includes a time series data module that is configured to store time series data for a domain, an exogenous data module that is configured to store exogenous data associated with multiple exogenous factors and a feedback module that is configured to collect and store feedback data from multiple online users, where the feedback data is related to the exogenous data and the exogenous factors. The system includes a data pre-processor module that is configured to use the at least one processor to identify and select a portion of the exogenous factors using the feedback data collected from the online users for use in a forecast model in combination with the time series data for the domain.

    SYSTEM AND METHOD OF PRODUCT AND VENDOR SELECTION
    2.
    发明申请
    SYSTEM AND METHOD OF PRODUCT AND VENDOR SELECTION 审中-公开
    产品和供应商选择的系统和方法

    公开(公告)号:US20160203540A1

    公开(公告)日:2016-07-14

    申请号:US14596219

    申请日:2015-01-14

    IPC分类号: G06Q30/06 G06F17/30

    CPC分类号: G06Q30/0625 G06F17/3053

    摘要: Disclosed herein are technologies for providing recommendations as to particular products and/or services that are customer specific and general, based on customer preference and inquiry. The recommendations are provided as part of an online shopping system. In accordance with one aspect, an item query is received from a customer, and analyzed by a query analyzer to determine if the query is a general item query or a specific item query. A search may be performed for items based on the item query in an items database listing items offered for purchase. If the query is the general item query, customer preference is determined from results of the search. If the query is the specific item query, the items from the results of the search are grouped based on cost performance. The items of the search result are ranked and provided to the customer.

    摘要翻译: 这里公开的是基于客户偏好和查询来提供关于特定产品和/或服务的顾客特定和一般的建议的技术。 这些建议作为在线购物系统的一部分提供。 根据一个方面,从客户接收到项目查询,并由查询分析器分析以确定查询是否是一般项目查询或特定项目查询。 可以在项目数据库中基于项目查询对项目进行搜索以列出要购买的项目。 如果查询是一般项目查询,则根据搜索结果确定客户偏好。 如果查询是特定项目查询,搜索结果中的项目将根据成本绩效进行分组。 搜索结果的项目被排序并提供给客户。

    OPTIMIZATION OF PROJECT RESOURCE MANAGEMENT WITH MULTI-RESOURCE TYPES AND COST STRUCTURES
    4.
    发明申请
    OPTIMIZATION OF PROJECT RESOURCE MANAGEMENT WITH MULTI-RESOURCE TYPES AND COST STRUCTURES 审中-公开
    项目资源管理优化与多种类型和成本结构

    公开(公告)号:US20160180270A1

    公开(公告)日:2016-06-23

    申请号:US14574397

    申请日:2014-12-18

    IPC分类号: G06Q10/06

    CPC分类号: G06Q10/06313

    摘要: Disclosed herein are technologies related to an optimization of project resource management of projects having multiple resource types and cost structures. One or more the technologies involves optimizing a project based, at least in part, on project data and related resource data using successive genetic operations and evaluations and further producing a resource-acquisition plan for the optimized project.

    摘要翻译: 本文公开了与具有多种资源类型和成本结构的项目的项目资源管理优化相关的技术。 一个或多个技术涉及到使用连续的遗传操作和评估,至少部分地优化项目数据和相关的资源数据,并进一步为优化的项目制定资源采集计划。

    PROFIT MAXIMIZATION RECOMMENDER SYSTEM FOR RETAIL BUSINESSES
    5.
    发明申请
    PROFIT MAXIMIZATION RECOMMENDER SYSTEM FOR RETAIL BUSINESSES 审中-公开
    利润最大化零售业务建议系统

    公开(公告)号:US20160125500A1

    公开(公告)日:2016-05-05

    申请号:US14528763

    申请日:2014-10-30

    IPC分类号: G06Q30/06 G06F17/30 G06Q40/00

    CPC分类号: G06Q30/0631 G06Q40/12

    摘要: A method includes receiving an identification code for an item selected for purchase by a customer in a retail store, identifying at least one item similar to the customer-selected item, identifying at least one item related to the customer-selected item, calculating a value for a first expected profit for a first sale of the customer-selected item and the similar item, calculating a value for a second expected profit for a second sale of the customer-selected item and the related item, sorting the first sale and the second sale in an order based on the value for the first expected profit and the value for the second expected profit, and providing information associated with the first sale and the second sale, the information for use in recommending the similar item or the related item for purchase by the customer in the retail store.

    摘要翻译: 一种方法包括接收由零售商店中的客户选择购买的商品的识别码,识别与客户选择的商品相似的至少一个商品,识别与客户选择的商品相关的至少一个商品,计算价值 为了首次出售客户选择的项目和类似项目的第一预期利润,计算用于第二次销售客户选择的项目和相关项目的第二预期利润的价值,排序第一销售和第二销售 根据第一预期利润的价值和第二预期利润的价值进行订单销售,并提供与第一次销售和第二次销售相关的信息,用于推荐类似商品或相关商品的信息以供购买 由客户在零售店。

    EFFICIENT COMPUTERIZED CALCULATION OF RESOURCE REALLOCATION SCHEDULING SCHEMES
    6.
    发明申请
    EFFICIENT COMPUTERIZED CALCULATION OF RESOURCE REALLOCATION SCHEDULING SCHEMES 审中-公开
    高效计算资源重组调度方案

    公开(公告)号:US20160125333A1

    公开(公告)日:2016-05-05

    申请号:US14532330

    申请日:2014-11-04

    IPC分类号: G06Q10/06 G06Q10/08

    摘要: The present disclosure relates to a computer system comprising a database including, a reallocation scheduling module, the reallocation scheduling module configured to obtain an objective function including one or more integer-valued decision variables and automatically determine a proposed reallocation scheme for each of one or more items between a plurality of locations based on the objective function, wherein determining the reallocation scheme includes finding values of one or more decision variables that optimize the objective function while obeying the one or more constraints, wherein determining a proposed reallocation scheme includes solving an integer quadratic programming problem.

    摘要翻译: 本公开涉及包括数据库的计算机系统,所述数据库包括重新分配调度模块,所述重新分配调度模块被配置为获得包括一个或多个整数值决策变量的目标函数,并且自动地确定所提出的重新分配方案中的一个或多个 基于目标函数的多个位置之间的项目,其中确定重新分配方案包括在遵守一个或多个约束的情况下找到优化目标函数的一个或多个决策变量的值,其中确定所提出的重新分配方案包括求解整数二次方 编程问题。

    DISTRIBUTED FAILOVER FOR MULTI-TENANT SERVER FARMS
    7.
    发明申请
    DISTRIBUTED FAILOVER FOR MULTI-TENANT SERVER FARMS 有权
    多重服务器系统的分布式故障

    公开(公告)号:US20160124818A1

    公开(公告)日:2016-05-05

    申请号:US14528482

    申请日:2014-10-30

    IPC分类号: G06F11/20 G06F11/14 H04L29/08

    摘要: A failover manager may be configured to determine a plurality of tenants executable on a server of a plurality of servers, each tenant being a virtual machine executable on the server in communication with at least one corresponding user. The failover manager may include a replicated tenant placement selector configured to dispatch a first replicated tenant for a first tenant of the plurality of tenants to a first standby server of the plurality of servers, and configured to dispatch a second replicated tenant for a second tenant of the plurality of tenants to a second standby server of the plurality of servers. The failover manager also may include a replicated tenant loader configured to activate, based on a failure of the server, the first replicated tenant on the first standby server to replace the first tenant, and the second replicated tenant on the second standby server to replace the second tenant.

    摘要翻译: 故障转移管理器可以被配置为确定在多个服务器的服务器上可执行的多个租户,每个租户是在服务器上与至少一个对应的用户通信的可执行的虚拟机。 故障转移管理器可以包括复制的租户放置选择器,其被配置为向多个服务器的第一备用服务器发送用于多个租户的第一租户的第一复制租户,并且被配置为为第二租户 多个租户到多个服务器的第二备用服务器。 故障转移管理器还可以包括复制租户加载器,其被配置为基于服务器的故障来激活第一备用服务器上的第一复制租户以替换第一租户,并且第二备用服务器上的第二复制租户替换 第二租户。

    FEEDBACK-DRIVEN EXOGENOUS FACTOR LEARNING IN TIME SERIES FORECASTING
    8.
    发明申请
    FEEDBACK-DRIVEN EXOGENOUS FACTOR LEARNING IN TIME SERIES FORECASTING 有权
    反馈驱动的异常因子在时间序列预测中学习

    公开(公告)号:US20160026930A1

    公开(公告)日:2016-01-28

    申请号:US14341525

    申请日:2014-07-25

    IPC分类号: G06N99/00 G06N5/04

    CPC分类号: G06N99/005

    摘要: A system for forecast modeling includes at least one processor and at least one database that is operably coupled to the at least one processor. The database includes a time series data module that is configured to store time series data for a domain, an exogenous data module that is configured to store exogenous data associated with multiple exogenous factors and a feedback module that is configured to collect and store feedback data from multiple online users, where the feedback data is related to the exogenous data and the exogenous factors. The system includes a data pre-processor module that is configured to use the at least one processor to identify and select a portion of the exogenous factors using the feedback data collected from the online users for use in a forecast model in combination with the time series data for the domain.

    摘要翻译: 一种用于预测建模的系统包括至少一个处理器和至少一个可操作地耦合到所述至少一个处理器的数据库。 数据库包括被配置为存储域的时间序列数据的时间序列数据模块,被配置为存储与多个外部因素相关联的外部数据的外部数据模块,以及被配置为收集和存储来自 多个在线用户,反馈数据与外生数据和外生因素有关。 该系统包括数据预处理器模块,其被配置为使用至少一个处理器来使用从在线用户收集的反馈数据来识别和选择一部分外部因素,以用于与预测模型结合时间序列 域的数据。

    FILTER CUSTOMIZATION FOR SEARCH FACILITATION
    9.
    发明申请
    FILTER CUSTOMIZATION FOR SEARCH FACILITATION 有权
    滤波器自定义搜索功能

    公开(公告)号:US20160012135A1

    公开(公告)日:2016-01-14

    申请号:US14328522

    申请日:2014-07-10

    IPC分类号: G06F17/30

    摘要: A classifier may be used to receive, via a website, user input associated with a product search of a user, and may be further used to identify a plurality of filters associated with the product search and predict a user-specific subset of the plurality of filters. Then, a filter manager may be used to provide a webpage of the website to the user, based on the user-specific filter subset.

    摘要翻译: 分类器可以用于经由网站接收与用户的产品搜索相关联的用户输入,并且还可以用于识别与产品搜索相关联的多个过滤器,并且预测多个 过滤器。 然后,过滤器管理器可以用于基于用户特定的过滤器子集向用户提供网站的网页。

    SYSTEM AND METHOD OF FUEL FILLING TO MINIMIZE FUEL COST
    10.
    发明申请
    SYSTEM AND METHOD OF FUEL FILLING TO MINIMIZE FUEL COST 审中-公开
    燃料充填系统和方法,以最小化燃料成本

    公开(公告)号:US20150178799A1

    公开(公告)日:2015-06-25

    申请号:US14134567

    申请日:2013-12-19

    IPC分类号: G06Q30/02 G06Q50/06

    CPC分类号: G06Q30/0283 G06Q50/06

    摘要: In an example, a method for determining quantities of fuel to dispense at a plurality of terminals along a transit route of a vehicle includes identifying a plurality of terminals along the transit route, each terminal of the plurality of terminals have an associated cost-per-unit of fuel dispensed; initializing a set of candidate fueling scenarios, each candidate fueling scenario including an initial array of values, each value in the array of values indicating a quantity of fuel to dispense to the vehicle at one of the plurality of terminals along the transit route; iteratively, using at least one processor, modifying the set of candidate scenarios; identifying the candidate scenario of the set of candidate scenarios with the lowest total fuel cost; and transmitting for display, the quantity of fuel to dispense at each of the plurality of terminals according to the identified lowest total fuel cost candidate scenario.

    摘要翻译: 在一个示例中,用于确定在沿着交通路线的多个终端处分配的燃料量的方法包括:沿着所述运输路线识别多个终端,所述多个终端中的每个终端具有相关联的成本 - 燃油单位 初始化一组候选加油场景,每个候选加油场景包括初始数值阵列,所述值阵列中的每个值表示沿所述运输路线在所述多个终端中的一个终端处分配给所述车辆的燃料量; 迭代地使用至少一个处理器,修改所述一组候选场景; 确定具有最低总燃料成本的一组候选情景的候选情景; 以及根据所识别的最低总燃料成本候选情景,发送用于显示在所述多个终端中的每一个处分配的燃料量。