International Business Machines Corporation

Uber Technologies, Inc.

Shicong Meng

Li Feng Zhang

Jian Tan

Xiaoqiao Meng

Ashley Quitoriano

Rei Chiang

Zhi Li

Kevin Spieser

Parijat Mazumdar

Arun Kwangil Iyengar

Min Li

Liangzhao Zeng

Zhenhua Hu

Isabelle Marie Rouvellou

Rahul P Akolkar

Yonggang Hu

Nicholas C Fuller

Ignacio Silva-Lepe

Alicia Elena Chin

Jacob Edison

Juan Pemberthy

Joshua K Hellerstein

Noah Harold Shaw

Ting Wang

Dor Levi

Xavier Rene Guerin

Awaneesh Verma

Xiao Yu

Junjia He

Emily Reinhold

Minkyong Kim

Yandong Wang

Michael Feiman

A system can receive a request for transport from a computing device of a user and select a service provider to provide transport for the user to a destination location. The system can receive location data from the computing device of the service provider. After the service provider picks up the user, the system can determine whether the service provider progresses toward the destination location in accordance with a set of progress conditions. Based at least in part on determining that the service provider has not progressed toward the destination location in accordance with the set of progress conditions, the system can adjust a fare for providing transport for the user to the destination location.

Real-time service provider progress monitoring

A network system can receive location data from a provider device of a service provider. Using at least the location data in an optimization model, the network system can determine one or more actions for the service provider to optimize one or more metrics. The one or more metrics correspond to at least one of (i) an expected wait time for the service provider over a future period of time, (ii) an expected travel distance between providing services over a future period of time, or (iii) an expected amount of earnings for the service provider over a future period of time. The network system may then transmit a dataset to the provider device to display information corresponding to the one or more actions for the service provider.

Prediction engine for a network-based service

A system can provide a set of expedition proposals that are each selectable by a service provider on a user interface of a computing device to commit the service provider to an expedition. Each expedition can be associated with a configured sequence of tasks to be performed for a given amount of time. Based on a selection of an expedition proposal from the set of expedition proposals, the system can initiate a corresponding expedition for the service provider by (i) matching the service provider with a sequence of tasks, and (ii) transmitting route data to the computing device to cause the user interface on the computing device to display route information for sequential destination locations for the sequence of tasks.

Dynamic route recommendation and progress monitoring for service providers

Service providers can be identified to fulfill service requests of a network-based service. A network system is configured to generate, based on historical data associated with the network-based service, a machine-learned service provider optimization (MLSPO) model for generating service provider optimizations. The optimizations can include action recommendations that optimize one or more service metrics. The MLSPO model can be a reinforcement learning model generated by performing a plurality of simulations utilizing one or more virtual agents. A provider device of a service provider can transmit a set of data to the network system that indicates a current location of the service provider. Based on the current location and the MLSPO model, the network system can generate service provider optimizations. Optimization data can be transmitted to the provider device so that the provider device can display information corresponding to the service provider optimizations.

A network computer system receives request data from computing devices of requesting users in a sub-region of a service area. The system further receives location data from computing devices of drivers operating in the sub-region. Based on the request data and the location data, the system determines a service condition for the sub-region. Based on the service condition indicating that the sub-region is in a driver oversupply state, the system transmits a service instruction to computing devices of a plurality of drivers within the sub-region, the service instruction being associated with a target outside the sub-region and a set of progress conditions. The system then periodically determines, for each driver of the plurality of drivers, an estimated time of arrival (ETA) to the target from a current position of the driver to determine whether the driver is satisfying the set of progress conditions of the service instruction.

A network computing system can configure sets of expedition proposals for service providers, which are each selectable to commit the service provider to a dynamic expedition coordinated in real-time by the network computing system. Partitioned service areas may be scored in accordance with utilization conditions, and a dynamic trajectory can be generated based on the scored service areas for individual service providers. The network computing system can provide navigation instructions to the service provider along an updated recommended route based on the dynamic trajectory, until expiration of the dynamic expedition.

A network computer system provides a service instruction to a computing device. The service instruction can include offers, such as a service request to pick up and transport a user, and recommendations, such as a movement recommendation encouraging the service provider to relocate to another geographic area. The network computer system remotely monitors the computing device to receive a current position of the computing device as the service provider travels within a geographic area. The network computer system remotely monitors the computing device to receive a service state of the service provider. The network computer system periodically determines whether the service provider is making progress towards a target of the service instruction based on the current position of the computing device and a set of progress conditions, including determining whether the service provider satisfied the set of progress conditions in response to a change in the service state.

An embodiment of the invention includes a method for executing commands in a distributed computing environment. The method receives a plurality of distributed commands from one or more devices. The method determines a global command execution order for executing the received plurality of distributed commands. The method dispatches the received plurality of distributed commands to a plurality of servers hosting a plurality of corresponding shards in the distributed computing environment, where a given distributed command corresponds to one or more of a given shard if the given distributed command pertains to a state hosted by the one or more given shard. The method executes, by the one or more given shard, the given distributed command, where the execution is deterministic, and where a result of deterministic execution of the given distributed command is unanimous among the one or more given shard.

Command processing in distributed computing systems

In various embodiments a distributed computing node in a plurality of distributed computing nodes executes transactions in a distributed processing system. In one embodiment, a transaction commit message is received from a client computing node for a transaction. The transaction commit message includes at least an identifier of the transaction and a transaction sequence for the transaction. The transaction sequence indicates a sequence of execution for the transaction on the plurality of distributed computing nodes. An entry within the transaction sequence associated with the distributed computing node is identified. The entry includes a sequence number for executing the transaction on the distributed computing node with respect to other transactions. The transaction is executed based on the sequence number in the entry.

Passive two-phase commit system for high-performance distributed transaction execution

In various embodiments a distributed computing node in a plurality of distributed computing nodes logs transactions in a distributed processing system. In one embodiment, a set of information associated with at least one transaction is recorded in a transaction log. At least a portion of memory in at least one information processing system involved in the transaction is accessed. The portion of memory is directly accessed without involving a processor of the at least one information processing system. The set of information from the transaction log is written to the portion of memory. The set of information is directly written to the portion of memory without involving a processor of the at least one information processing system.

Multi-way, zero-copy, passive transaction log collection in distributed transaction systems

A method to share remote DMA (RDMA) pointers to a key-value store among a plurality of clients. The method allocates a shared memory and accesses the key-value store with a key from a client and receives an information from the key-value store. The method further generates a RDMA pointer from the information, maps the key to a location in the shared memory, and generates a RDMA pointer record at the location. The method further stores the RDMA pointer and the key in the RDMA pointer record and shares the RDMA pointer record among the plurality of clients.

Efficient remote pointer sharing for enhanced access to key-value stores

Distributed game commands in massive multiplayer online games. A game engine receives commands and determines the order of their execution based on a global order policy using sequencers. The sequencers dispatch the commands to appropriate game engine instances on shards hosting game states. Engine instances execute the commands according to the global order established by the sequencers.

Growing community of inventors

Elmsford, NY, United States of America

Shicong Meng