Microsoft Technology Licensing, LLC

Other

Microsoft Corporation

Rovi Technologies Corporation

Xing Xie

Wei-Ying Ma

Yu Zheng

Longhao Wang

Chuang Wang

Lee Wang

Xin Fan

Yin Lou

Chengyang Zhang

Hong-Jiang Zhang

Lie Lu

Ying Li

Zhiwei Li

Chong Wang

Xiangye Xiao

Like Liu

Yutao Xie

Ruihao Weng

Yuki Arase

Yinghua Zhou

Jiafan Ou

Yu Chen

Patrick Markus Baudisch

Ji-Rong Wen

Yin Zhu

Xianfang Wang

Ming Li

Chang Sheng

Menglei Jia

Zaiben Chen

Liqun Chen

Zheng Chen

Hua Li

Qi Zhang

Zheng Zhang

Chang Zhang

Hongjiang Zhang

Ruihua Song

Chun Liang Yuan

Lei Liu

Shiding Lin

Ruochi Zhang

Zhigang Hua

Jianxun Lian

Mingqi Wu

Xining Li

Yang Ye

Joshua J Forman

Jihwan Song

Xihong Jin

Guomao Xin

Jing Yao

Yuntao Du

Bei Lu

Xiting Wang

Xiangjian Yang

Yanjun Zeng

Nicholas Jing Yuan

Yongqiang He

Jianqiao Feng

Gang Yan

Wencheng Zheng

Lizhu Zhang

Rongrong Ji

Yiqun Hu

Manni Duan

Jinggang Wang

Liang Sun

Gengxin Miao

Liu Hao

Hao Liu

Chun Yuan

A method for providing recommendations to a user includes assigning one or more item tags from a known set of tags to one or more items of a plurality of items; assigning one or more user tags from the known set of tags to a user; determining at least one taste cluster having one or more cluster tags from the known set of tags, wherein the taste cluster shares at least one shared tag with the one or more user tags and with the one or more item tags; affiliating at least one item of the plurality of items with the taste cluster based on the shared tag; affiliating the user with the taste cluster based on the shared tag; and presenting to the user at least one presented item of the plurality of items affiliated with the taste cluster.

Explainable cluster-based collaborative filtering

This disclosure describes a map-matching module that supports a Global Positioning System (GPS) and provides a user with a best match trajectory corresponding to GPS sampling points taken at a low sampling rate. The best match trajectory is based upon a spatial-temporal analysis.

Map-matching for low-sampling-rate GPS trajectories

Chair backrest

The present invention discloses a train coupler structural health monitoring system. The system includes one or more sensors mounted to or integrated with the train coupler, a data acquisition unit for receiving signal or data from the sensors, and a processing unit for determining the train coupler's structural health based on the received signal or data. Inspections via the system can be performed in real time continuously or periodically while a train is in service. It can also be performed offline while a train is not in service. Inspection method can be either passive, where sensors collect signals without generating excitation signals to the structure, or active, where some sensors are used as actuators to actively send excitation signals to the structure and other sensors or the actuators themselves collect the structural response signals. The data acquisition unit receives signals or data from sensors. The processing unit processes sensor data acquired by the data acquisition unit and determines if there are structural changes or damages.

Train coupler structural health monitoring system

Techniques for providing a trajectory route to multiple geographical locations of interest are described. This disclosure describes receiving global position system (GPS) logs associated with respective individual devices, each of the GPS logs including trajectories connecting a set of geographical locations previously visited by an individual of a respective individual device. A trajectory route service receives a request for a trajectory connecting a set of geographical locations of interest specified by a user. The trajectory route service calculates a proximal similarity between (1) the set of geographical locations of interest specified by the user, and (2) respective sets of geographical locations from the GPS logs. The trajectory route service constructs the requested trajectory with use of at least one of the trajectories from the GPS logs determined at least in part according to the calculated proximal similarities.

Searching similar trajectories by locations

Described is a technology by which a user hums, sings or otherwise plays a user-provided rendition of a ringtone (or ringback tone) through a mobile telephone to a ringtone search service (e.g., a WAP, interactive voice response or SMS-based search platform). The service matches features of the user's rendition against features of actual ringtones to determine one or more matching candidate ringtones for downloading. Features may include pitch contours (up or down), pitch intervals and durations of notes. Matching candidates may be ranked based on the determined similarity, possibly in conjunction with weighting criterion such as the popularity of the ringtone and/or the importance of the matched part. The candidate set may be augmented with other ringtones independent of the matching, such as the most popular ones downloaded by other users, ringtones from similar artists, and so forth.

Query by humming for ringtone search and download

Techniques for analyzing effectiveness of an urban area based on traffic patterns collected from route-oriented vehicles. A process collects sequences of global positioning system (GPS) points in logs and identifies geographical locations to represent the urban area where the route-oriented vehicles traveled. The process models traffic patterns by: partitioning the urban area into regions based at least in part on major roads, segmenting the GPS points from the logs into time slots, and identifying the GPS points associated with transporting a passenger in the route-oriented vehicles. The process models traffic patterns by projecting the identified GPS points onto the regions to construct transitions of the identified GPS points travelling between the regions. Then the process builds a matrix of the regions for each time slot in each day based on a number of the transitions. Each item in the matrix represents an effectiveness of a connection between two regions.

Urban computing of route-oriented vehicles

Described is a technology by which raw GPS data is processed into segments of a trip, with a predicted mode of transportation (e.g., walking, car, bus, bicycling) determined for each segment. The determined transportation modes may be used to tag the GPS data with transportation mode information, and/or dynamically used. Segments are first characterized as walk segments or non-walk segments based on velocity and/or acceleration. Features corresponding to each of those walk segments or non-walk segments are extracted, and analyzed with an inference model to determine probabilities for the possible modes of transportation for each segment. Post-processing may be used to modify the probabilities based on transitioning considerations with respect to the transportation mode of an adjacent segment. The most probable transportation mode for each segment is selected.

Learning transportation modes from raw GPS data

Techniques for detecting outliers in data and determining spatiotemporal causal interactions in the data are discussed. A process collects global positioning system (GPS) points in logs and identifies geographical locations to represent the area where the service vehicles travelled with a passenger. The process models traffic patterns by: partitioning the area into regions, segmenting the GPS points from the logs into time bins, and identifying the GPS points associated with transporting the passenger. The process projects the identified GPS points onto the regions to construct links connecting GPS points located in two or more regions. Furthermore, the process builds a three-dimensional unit cube to represent features of each link. The points farthest away from a center of data cluster are detected as outliers, which represent abnormal traffic patterns. The process constructs outlier trees to evaluate relationships of the outliers and determines the spatiotemporal causal interactions in the data.

Determine spatiotemporal causal interactions in data

Techniques for searching and providing geographical regions are described. The process searches and recommends points of interests based on a user-specified region. Points of interests include spatial objects (e.g., buildings, landmarks, rivers, parks) and their distributions in a geographical region. The process searches and recommends points of interests by partitioning a spatial map into grids to identify representative categories located in each of the grids. In response to the user-specified region, a set of geographical candidates containing the representative categories is retrieved. The process determines whether the user-specified region and the set of geographical candidates include similar or common representative categories and similar or common spatial distributions of the representative categories. Then the process provides the top ranked set of geographical candidates that have similar content information.

Recommending points of interests in a region

Techniques for determining a status of a user are described. A mobile device equipped with sensors may collect sensor data pertaining to transportation modes of the user, tracking locations of the user, identifying environmental noise levels surrounding the user, or speech being spoken in proximity to the user. Features of the collected sensor readings are then used to infer activities the user may be performing. Based at least in part on the multiple inferred activities, a status of the user is determined.

Identifying status based on heterogeneous sensors

Growing community of inventors

Beijing, China

Xing Xie