Abstract: Techniques for automatically detecting when a ride requester has requested a ride-share ride on behalf of a guest rider using some or all of the communications between the driver and ride requester are described herein. For example, a server can obtain chat logs between a ride requester and a driver and process the chat logs to identify whether the ride requester has requested a ride on behalf of a guest rider. In particular, the server can train an artificial intelligence model (e.g., a machine learning model) to predict potential guest rider behavior. Once trained, the server can obtain chat logs comprising chat messages sent between a driver and a ride requester, and apply a representation of the chat logs as an input to the trained artificial intelligence model to determine whether guest rider behavior is detected.

Abstract: After receiving a trip request, a ridesharing platform system can determine scores for each prior trip request within a time window from features associated with the prior trip request. The ridesharing platform system can determine patterns from corresponding scores and determine a risk for the trip request using on the patterns. The ridesharing platform system can determine whether to accept or decline the trip request based on the risk for the trip request.

Abstract: A route may be recommended, and it may be determined if a vehicle detours from the recommended route. At least one recommend route may be obtained. A current route of a vehicle may be obtained. A variance value may be determined based on the current route and the at least one recommend route. The variance value may be compared to a threshold. It may be determined whether the variance value exceeds the threshold. If the variance value exceeds the threshold, it may be determined that the vehicle has detoured. If the variance value does not exceed the threshold, it may be determined that the vehicle has not detoured.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a first trip order and a trip whitelist. The first trip order comprises a first passenger and first points of interest (POIs). In response to either the first POIs or the first passenger being in the trip whitelist, dispatching a driver to the first trip order. In response to neither the first POIs nor the first passenger being in the trip whitelist, a determination is made whether to add the first POIs or the first passenger to the trip whitelist. In response to a determination not to add the first POIs or the first passenger to the trip whitelist, a trip risk score is determined for the first trip order based on a trip-risk evaluation machine learning model, and a driver is dispatched to the first trip order based on the trip risk score.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a trip order and a driver pool, the driver pool comprising a plurality of drivers. A trip risk category selected among a plurality of trip risk categories can be assigned to the trip order. One or more dispatch rules learned from a trained dispatch machine learning model can be obtained. Based on the one or more dispatch rules, the driver pool can be filtered to obtain a qualified driver pool for the trip order. The qualified driver pool is fed to a dispatch engine which assigns a driver in the qualified driver pool to the trip order.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a trip order comprising a driver assigned to the trip order, a passenger of the trip order, and information about the trip order. Driver features associated with the driver, passenger features associated with the passenger, and trip order features extracted from the information about the trip order can be obtained. A driver-score is determined by a driver-evaluation machine learning model based on the driver features. A risk score for the trip order is determined using a risk-evaluation machine learning model based on the driver-score, the passenger features, and the trip order features. An alert notification is sent to a computing device of the driver based on the risk score.

Abstract: Embodiments of the disclosure provide systems and methods for reviewing performance of computer models for safety analysis in transportation services. The exemplary system includes a communication interface configured to receive log data associated with at least one reported safety event. The log data includes one or more computer models used for predicting the reported safety event and associated with a first feature pattern and a first model performance. The system further includes at least one processor configured to extract features from the log data and determine a second feature pattern and a second model performance of the computer models. The at least one processor is also configured to detect a change in feature pattern based on the first feature pattern and the second feature pattern or a performance degradation based on the first model performance and the second model performance, and to generate an alert to upgrade the computer models.

Abstract: Embodiments of the disclosure provide systems and methods for processing a transportation service request. An exemplary system may include a communication interface configured to receive the transportation service request from a terminal device. The system may further include at least one processor. The at least one processor may be configured to generate a passenger score based on the received transportation service request using a first machine learning model trained with sample passenger data associated with past impacted drivers. The at least one processor may further be configured to generate a trip score based on the generated passenger score and the received transportation service request using a second machine learning model trained with sample trip data associated with the past impacted drivers. The at least one processor may also be configured to allow or block the received transportation service request based on the generated trip score.

Abstract: The present disclosure provides a system for improving security. The system may identify a query associated with a user account, and access an ID graph database to obtain an ID graph relating to the user account by a database driver. The system may also determine whether the user account is a target account type based at least on the ID graph. The ID graph may include a plurality of nodes and a plurality of edges. Each of the plurality of edges may connect two nodes. Each of the plurality of nodes may include at least one of a register ID, a login ID, a payment ID, a background check ID, or a face ID. Each edge that connects two nodes may include at least one of a user type associated with the two nodes, a timestamp when the edge is connected, or source information of the edge.

Abstract: A route may be recommended, and it may be determined if a vehicle detours from the recommended route. At least one recommend route may be obtained. A current route of a vehicle may be obtained. A variance value may be determined based on the current route and the at least one recommend route. The variance value may be compared to a threshold. It may be determined whether the variance value exceeds the threshold. If the variance value exceeds the threshold, it may be determined that the vehicle has detoured. If the variance value does not exceed the threshold, it may be determined that the vehicle has not detoured.

Abstract: After receiving a trip request, a ridesharing platform system can determine scores for each prior trip request within a time window from features associated with the prior trip request. The ridesharing platform system can determine patterns from corresponding scores and determine a risk for the trip request using on the patterns. The ridesharing platform system can determine whether to accept or decline the trip request based on the risk for the trip request.