Sap Ag

Ebay, Incorporated

Apple Inc.

Yahoo! Inc.

Ye Chen

John Canny

Alexander Renz

Camille Chen

Paul V Flynn

Hartmut K Vogler

Yaranama Venkata Ramana Dass

Hsin-Yao Chen

Sarvesh Kumar Varatharajan

Maksims Ovsjanikovs

Mohit Narang

Peter M Agboh

Hsin-Yuo Liu

Tao Lin

Richard James Swan

Pavel Berkhin

Chia Yiaw Chong

Kaj Van De Loo

Christian Drumm

Dmitry Pavlov

Sultan R Helmi

Tursunjan Yasin

Claudius Link

Wouter Van Der Veen

R Scott Beckett

James Vrieling

Systems, methods, and mechanisms to enhance border router performance across Thread, Wi-Fi, and Bluetooth protocols, including mechanisms for Thread network mesh reconfiguration for optimized/enhanced coexistence and frequency selection with Wi-Fi and Bluetooth, co-located Wi-Fi/Bluetooth/Thread coexistence border router design, and dynamic adjustment for Thread energy detection (ED).

Thread device eco-system design

Optimized eco-system design with thread devices

Systems, methods, and devices are provided to efficiently share an antenna between multiple communication systems and allow for the communication systems to be simultaneously connected to the antenna with less attenuation and/or no fluctuation in signal strength. Communication circuitry may include an antenna that transmits and receives electromagnetic radiation. The communication circuitry may also include an antenna port that provides primary access to the antenna with a first attenuation via an antenna port input. Additionally, the communication circuitry may include a coupler attached to the antenna port. The coupler may provide secondary access to the antenna with a second attenuation.

Multi-radio front-end circuitry for radio frequency imbalanced antenna sharing system

A system, method, and machine readable medium for creating a personalized recommendation of an item by creating a topic vector based on a plurality of search queries, at least one of a plurality of users associated with the search queries or a plurality of items associated with the search queries; interring a topical preference for a user based on a search query by the user; and recommending at least one item based on the topical preference and the topic vector.

Personalized recommendation of a volatile item

A clustering and recommendation machine determines that an item is included in a cluster of items. The machine accesses item data descriptive of the item. The machine accesses a vector that represents the cluster and calculates the likelihood that the item is included in the cluster, based on the item variable and the probability parameter. The machine determines that the item is included in the cluster, based on the likelihood. The machine also recommends an item to a potential buyer. The machine accesses behavior data that represents a first event type pertinent to a first cluster of items. The machine calculates a probability that a second event type pertaining to a second cluster of items will co-occur with the first event type. The machine identifies an item from the second cluster to be recommended and presents a recommendation of the item to the potential buyer.

Probabilistic clustering of an item

Probabilistic recommendation of an item

A system, method, and machine readable medium for creating a personalized recommendation of an item by creating a topic vector based on a plurality of search queries, at least one of a plurality of users associated with the search queries or a plurality of items associated with the search queries; inferring a topical preference for a user based on a search query by the user; and recommending at least one item based on the topical preference and the topic vector.

A method and a system are provided for large-scale behavioral targeting for advertising over a network, such as the Internet. In one example, the system receives training data that is processed raw data of user behavior. The system generates selected features by performing feature selection on the training data. The system generates feature vectors from the selected features. The system initializes weights of a behavioral targeting model by scanning the feature vectors once. The system then updates the weights of the behavioral targeting model by scanning iteratively the feature vectors using a multiplicative recurrence.

Large-scale behavioral targeting for advertising over a network

Methods and apparatus, including computer program products, implementing and using techniques for monitoring and predicting various data related to an inventory. A data processing apparatus interacts with one or more business computers to obtain one of replenishment and consumption activity data related to an inventory. A model for variations in the inventory is created. The model is used to determine estimates of variation for one of currently planned replenishment activities and currently planned consumption activities. The estimates of variation are used to predict future inventory levels. A system including one or more agent computers is also described.

Agent using detailed predictive model

Methods and apparatus, including computer program products, implementing and using techniques for providing a web service agent application. The web service agent application has a communication module and a processing module. The communication module receives requests from one or more web service applications or one or more adaptive agent applications; and transmits responses to one or more web service applications or one or more adaptive agent applications. The processing module receives a request for information from the communication module; identifies a resource that can fulfill the request for information; obtains a response to the request from the identified resource; and delivers the response to the request to the communication module.

Web service agent

An inventory agent operating on software includes instructions operable to cause a programmable processor to receive inventory data relating to stock in an inventory, apply the inventory data to a conditional probabilistic predictive statistical algorithm, calculate a predicted inventory level, and use the calculated predicted inventory level to determine whether to order additional stock for the inventory. The statistical algorithm uses a conditional probabilistic model to process the data. The inventory agent may be implemented in a supply chain management system.

Inventory early warning agent in a supply chain management system

An inventory agent operating on software includes instructions operable to cause a programmable processor to receive inventory data relating to stock in an inventory. The inventory data includes planned inventory data and actual inventory data. The instructions are operable to cause the programmable processor to use the inventory data to calculate one or more correlations in errors between the planned inventory data and the actual inventory data, use the one or more correlations in errors to estimate a probability density for one or more errors, calculate a predicted inventory level, calculate a likely error of the predicted inventory level using the estimate of the probability density, and adjust the predicted inventory level with the likely error to estimate a likely actual inventory level. The inventory agent may be implemented in a supply chain management system.

Inventory early warning agent with correction by error correlation calculation

Methods and apparatus, including computer program products, to support real-time inventory management. Changes to the inventory including the addition or removal of an item from the inventory are reported to the item tracking system in real-time. An inventory planner normally operates on a periodic schedule to perform inventory management functions. The inventory planner can receive alerts from an early warning agent that can cause the inventory planner to perform at least some inventory management functions, outside of its normal periodic schedule. In particular, the agent can send an alert to the inventory planner to cause the inventory planner to determine whether replenishment of store inventory is needed. To make this determination, the inventory planner can retrieve real-time inventory data from the item tracking system.

Growing community of inventors

Sunnyvale, CA, United States of America

Ye Chen