Abstract: A computer-implemented method, a computer system and a computer program product provide differentiated services to spectrum zones based on user activity. The method includes obtaining a current spectrum zone configuration for a physical environment from a server. The method also includes capturing activity data from the physical environment. The method further includes identifying an event of interest in the activity data, wherein the event of interest comprises network requirements. The method also includes determining that the network requirements of the event of interest are not satisfied by the current spectrum zone configuration for the physical environment. Lastly, the method includes modifying the current spectrum zone configuration based on the network requirements.

Abstract: A computer-implemented method, a computer system and a computer program product route meeting sessions through a venue based on device availability. The method includes identifying a plurality of sessions in a venue network, where each session in the plurality of sessions comprises session data that is associated with a network slice. The network slice includes connection requirements. The method also includes receiving a connection request from a user, where the connection request includes a session in the plurality of sessions. The method further includes determining an available device to receive the session data, where the available device satisfies the connection requirements of the network slice. Lastly, the method includes associating the available device with the network slice, where the session data is transmitted to the available device.

Abstract: According to one embodiment, a method, computer system, and computer program product for grouped federated learning is provided. The embodiment may include initializing a plurality of aggregation groups including a plurality of parties and a plurality of local aggregators. The embodiment may also include submitting a query to a first party from the plurality of parties. The embodiment may further include submitting an initial response to the query from the first party or a second party from the plurality of parties to a first local aggregator from the plurality of local aggregators. The embodiment may also include submitting a final response from the first local aggregator or a second local aggregator from the plurality of local aggregators to a global aggregator. The embodiment may further include building a machine learning model based on the final response.

Abstract: A method of managing the adaptive dispatching of a taxi includes receiving a request for a taxi, the received request being from a passenger; scoring a taxi driver based on at least one of an acceptance rate for assignment, a rejection rate for assignment, an idle rate, and a frequency of job acceptance; scoring the passenger based on at least one of a cancellation rate, a booking frequency, an abandonment rate, and a blacklist factor; matching the passenger to a taxi driver based on the taxi driver score and the passenger score; assigning a passenger to a taxi driver based on one of a conditional historical acceptance rate and a stochastic assignment of either chance constraints or a conditional value at risk; and dispatching the taxi driver to the passenger.

Abstract: A computer-implemented method and a computer system for orchestrating federated learning in multi-infrastructures and hybrid infrastructures. An infrastructure federated learning orchestrator deploys a container of an aggregator and containers of parties to respective infrastructures in an infrastructure cluster. The infrastructure federated learning orchestrator creates aggregator and party processes of federated learning across the respective infrastructures. The infrastructure federated learning orchestrator moves federated learning artifacts to the container of the aggregator and the containers of the parties. The infrastructure federated learning orchestrator executes federated learning training commands in the aggregator and party processes. The infrastructure federated learning orchestrator monitors failure events and performance metrics in the aggregator and party processes.

Abstract: A method (and system, apparatus, and computer product) for reporting traffic data includes, in an onboard unit installed in a vehicle, generating a traffic data report packet including information identifying a location of the vehicle in a traffic network and storing the generated traffic data report packet in a transmission queue. The onboard unit stores and maintains the generated traffic data report packet in the transmission queue with other traffic data report packets in a sequence in accordance with potential transmission times associated with each traffic data report packet. At least a portion of the traffic data report packets stored in the transmission queue is selectively transmitted, as a batch transmission to a traffic center server via a communication link.

Abstract: Method and system for secure valuation and access of data streams includes encrypting access to a data stream, storing the encrypted data stream on a secure platform, determining an estimated value of the data stream based on a prediction function, determining an accuracy of the estimated value, storing the estimated value and the accuracy of the estimated value with the data stream on the secure platform and controlling access on the secure platform to the data stream. Encrypting access to the data stream may be done on a blockchain. Access on the secure platform may be controlled by a token system and a value and number of tokens for accessing the data stream is determined based on the accuracy of the estimated value. Data streams may be bundled based on the value and number of tokens for accessing the plurality of data streams determined based on the accuracy of the estimated values.

Abstract: A method for service level management of a transit system is provided. The method may include receiving time series data sets from wireless access points of a wireless network, wherein each time series data set corresponds to a mobile device in the transit system. Spatio-temporal trajectories of each mobile device may be determined based on the time series data sets corresponding to each mobile device. The determined trajectories of a group of individual devices may be clustered. A spatio-temporal trajectory of a vehicle in the transit system may be determined based on the clustered trajectory of the group of devices. A system parameter of the transit system may be adjusted based on the determined trajectory of the vehicle. Passenger transition rates, waiting times, unable-to-board levels, and crowd density levels may be determined with respect to a transit location. A machine learning model may be generated to augment the determinations.

Abstract: A computer system includes one or more processors; and one or more non-transitory memories including computer program code, the one or more memories and the computer program code being configured to, with the one or more processors, cause the computer system to perform operations comprising: providing a first set of data records and a second set of data records in which each data record potentially relates to information associated with at least one transitional object; identifying a set of labelings in which at least one label refers to at least one data record; assigning a likelihood score that an identified label corresponds to a data record that is referred to; determining an identity of the at least one transitional object based on the assigned likelihood score; and outputting the determined identity.

Abstract: A computer system accesses encrypted graph information corresponding to multiple delivery providers and comprising vehicle routes for the delivery providers and forms a complete graph based thereon. The computer system performs an identification of a bottleneck in the complete graph and sends message(s) to any delivery providers affected by the identified bottleneck to alert the affected delivery providers of the identified bottleneck. In another example, the computer system performs, using the complete graph, an identification of possible market share augmentation for the delivery provider(s). The computer system sends message(s) to the delivery provider(s) to alert the delivery provider(s) of the identified possible market share augmentation. As further examples, a given delivery provider can send message(s) to its vehicle(s) to alert the vehicles about the bottleneck or perform market share augmentation.

Abstract: A method is provided for determining a number of current customers in a queue for a first event; estimating a current wait time of the queue for a new customer based at least on the number of current customers in the queue; predicting a future wait time of the queue for the new customer, if the new customer entered the queue after completing at least one second event prior to entering the queue of the first event, wherein estimating the future wait time is based at least on a probability of one or more future customers performing the at least one second event prior to entering the queue; determining an incentive for the new customer to complete the at least one second event prior to entering the queue based at least on the current wait time and the future wait time; and sending the incentive to the customer.

Abstract: Methods and systems may provide for joining an overlay network of a plurality of peer devices and identifying a local preference for an area service available to the plurality of peer devices. Additionally, the local preference may be used to negotiate a common preference for the area service with the plurality of peer devices. In one example, the common preference is a best fit value for the plurality of peer devices on the overlay network.

Abstract: A route-quality learning method, system, and computer program product include collecting a first route for a trip recommended from a first third-party application, collecting a second route for the trip recommended from a second third-party application, and after the trip is completed, estimating best alternatives given completion data of the trip and using the first third-party application and the second third-party application recommendation.

Abstract: An example operation may include one or more of connecting, by a wallet node, to a blockchain network comprised of a plurality of peer nodes, at least one unspent transaction output (UTXO) exchange platform node and at least one secondary UTXO market node, identifying, by the wallet node, a UTXO generated by a peer node of the plurality of the peer nodes, computing, by the wallet node, a new value of the UTXO if the UTXO has at least one characteristic of interest (COI), updating, by the wallet node, a previous value of the UTXO based on an elapsed time between events associated with the at least one COI, submitting, by the wallet node, the new value of the UTXO to the peer node of the plurality of the peer nodes, and executing, by the wallet node, a smart contract to reverse the UTXO if the peer node of the plurality of the peer nodes rejects the computed value of the UTXO.

Abstract: A method of managing the adaptive dispatching of a taxi includes receiving a request for a taxi, the received request being from a passenger; scoring a taxi driver based on at least one of an acceptance rate for assignment, a rejection rate for assignment, an idle rate, and a frequency of job acceptance; scoring the passenger based on at least one of a cancellation rate, a booking frequency, an abandonment rate, and a blacklist factor; matching the passenger to a taxi driver based on the taxi driver score and the passenger score; assigning a passenger to a taxi driver based on one of a conditional historical acceptance rate and a stochastic assignment of either chance constraints or a conditional value at risk; and dispatching the taxi driver to the passenger.

Abstract: A method for providing a forecast includes providing a database storing data at a lowest level in a first dimension, calculating a first forecast at a level that is higher than the lowest level of a first dimension in the database, calculating a forecast for each category within the lowest level of the first dimension, aggregating a second forecast across a category at the lowest level of the first dimension based upon an aggregation of the calculated forecast for the category within the lowest level of the first dimension, determining a difference between the first forecast and the second forecast, and creating a dummy category including a new category at the lowest level of the first dimension.

Abstract: Methods and systems may provide for joining an overlay network of a plurality of peer devices and identifying a local preference for an area service available to the plurality of peer devices. Additionally, the local preference may be used to negotiate a common preference for the area service with the plurality of peer devices. In one example, the common preference is a best fit value for the plurality of peer devices on the overlay network.

Abstract: A computer system includes one or more processors; and one or more non-transitory memories including computer program code, the one or more memories and the computer program code being configured to, with the one or more processors, cause the computer system to perform operations comprising: providing a first set of data records and a second set of data records in which each data record potentially relates to information associated with at least one transitional object; identifying a set of labelings in which at least one label refers to at least one data record; assigning a likelihood score that an identified label corresponds to a data record that is referred to; determining an identity of the at least one transitional object based on the assigned likelihood score; and outputting the determined identity.

Abstract: A method for providing a forecast includes providing a multi-dimensional database storing data at a lowest level in a first dimension, calculating a first forecast at a level that is higher than the lowest level of a first dimension in the database, calculating a forecast for each category within the lowest level of the first dimension, aggregating a second forecast across a category at the lowest level of the first dimension based upon an aggregation of the calculated forecast for the category within the lowest level of the first dimension, determining a difference between the first forecast and the second forecast, creating a dummy category including a new category at the lowest level of the first dimension, and storing the difference in the dummy category at the lowest level of the first dimension.

Abstract: Disclosed are systems, methods, and computer program products that provide a user with alternative options to incident induced traffic by presenting the user with an alternate route to perform other tasks on a task list when travel is delayed by the incident. The method includes receiving a current location, a navigation route, an expected delay due to an incident, and a list of tasks from the user. Each task in the list may include a value and expected duration. The method further includes computing an incentive for each task in the list based on the received information and a probability that the user will re-route to stop at a facility for fulfilling the task, comparing the incentive and probability to determine which task has a minimal incentive and a greater probability that the user will re-route than not re-route to the facility, and presenting the minimal incentive to the user.