Abstract: Methods, systems, and apparatus for detecting malicious activities in a ride-hailing platforms are described. An exemplary method comprises: identifying a set of trips from historical data to form training data; training a classifier based on a plurality of features of the set of trips in the training data to identify whether a given trip is malicious or benign; deploying the classifier to classify new trips in the ride-hailing platform for a first period of time to obtain a plurality of malicious trip candidates; storing the plurality of malicious trip candidates in a staging database for a second period of time for data cleansing based on supplementary data collected during the second period of time; fetching, from the staging database, a set of malicious trip candidates that have been stored in the staging database longer than the second period of time; and re-training the classifier.

Abstract: Systems and methods are provided for language-based service hailing. Such system may comprise one or more processors and a memory storing instructions that, when executed by the one or more processors, cause the computing system to obtain a plurality of speech samples, each speech sample comprising one or more words spoken in a language, train a neural network model with the speech samples to obtain a trained model for determining languages of speeches, obtain a voice input, identify at least one language corresponding to the voice based at least on applying the trained model to the voice input, and communicate a message in the identified language.

Abstract: Itineraries may be recommended using rider context information relating to a rider. The rider context information may be obtained from various sources. Location information including an origin and a destination may obtained. A set of itineraries may be generated based on the rider context information. Each itinerary may include at least one mode of transportation to allow the rider to travel from the origin to the destination. Each itinerary in the set of itineraries may be ranked based on the rider context information.

Abstract: A system includes at least one non-transitory storage medium storing a set of instructions and at least one processor in communication with the at least one non-transitory storage medium. When executing the set of instructions, the at least one processor may be directed to cause the system to obtain a service request signal sent from a user terminal via wireless communication, wherein the service request signal encodes identifier data, a first departure location, and a first departure time; retrieve one or more historical records related to the identifier data, wherein a historical record includes a historical departure location, historical departure time and a historical destination location; determine, using a pre-stored destination matching algorithm, a selection probability of the one or more historical destination location; determine, based on the selection probability, a suggested destination location, which is the same as the one or more historical destination locations.

Abstract: The present disclosure relates to methods and systems for determining an estimated time of arrival (ETA). The methods may include obtaining feature data related to an on-demand service order; obtain a parallel computing framework; determining a global ETA model based on the feature data and the parallel computing framework; and determining an ETA for a target route based on the global ETA model.

Abstract: The present disclosure relates to a system and a method for identifying a drunk passenger of a car hailing order. The system may perform the method to: obtain a plurality of samples from historical car hailing orders stored in a database; for each of the plurality of samples, using an application, extract a plurality of features including a passenger feature set, a driver feature set, and an order feature set, wherein the order feature set includes drunk-hotspot-relating features; and train a preliminary classification model based on the plurality of features and the plurality of samples to obtain a drunk model.

Abstract: Systems and methods are provided for ride order dispatching and vehicle repositioning. A method for ride order dispatching and vehicle repositioning, comprises: obtaining information comprising a location of a vehicle, current orders, and a current time; inputting the obtained information to a trained model; and determining action information for the vehicle based on an output of the trained model, the action information comprising: re-positioning the vehicle or accepting a ride order. The model is configured with: receiving information of drivers and information of orders as inputs; obtaining a global state based on the information of drivers, the information of orders, and a global time; and querying a plurality of driver-order pairs and driver-reposition pairs based at least on the obtained global state to determine the action information as the output.

Abstract: Systems and methods are provided for estimating travel time and distance. Such method may comprise obtaining a vehicle trip dataset comprising an origin, a destination, a time-of-day, a trip time, and a trip distance associated with each of a plurality of trips, and training a neural network model with the vehicle trip dataset to obtain a trained model. The neural network model may comprise a first module and a second module, the first module may comprise a first number of neuron layers, the first module may be configured to obtain the origin and the destination as first inputs to estimate a travel distance, the second module may comprise a second number of neuron layers, and the second module may be configured to obtain the information of a last layer of the first module and the time-of-day as second inputs to estimate a travel time.

Abstract: A method of exchanging information with network devices using web browsers includes executing an application on a client device to implement a local web server on the client device, loading in a web browser on the client device a webpage independent of the web browser and including a script for generating a first request to the local web server, accepting the first request from the web browser by the local web server, and sending requested information to the web browser by the local web server. In some embodiments, the method also includes generating a second request to a remote server by the web browser and using the script, where the second request includes the requested information sent to the web browser.

Abstract: The present disclosure relates to a system and method for operating an online to offline service platform. The system may perform the methods to: receive a service order from a first terminal associated with a passenger, the service order including a first identifier corresponding to the passenger and a pick-up location designated by the passenger; determine a second identifier corresponding to a driver accepting the service order; obtain first status corresponding to the first identifier; generate, based on the first status, a first instruction; and send the first instruction to a second terminal associated with the second identifier.

Abstract: The present disclosure includes artificial intelligence systems and methods for identifying grids for a geofence in an area in a map that includes a plurality of independently indexed regions of grids. The map is gridded into a plurality of grids and divided into a plurality of partitions. The methods include obtaining information of the geofence in the map, and determining a boundary grid series of the geofence from the plurality of grids. The methods include identifying at least one enclosed area in the geographical region, and upon determining that an enclosed area crosses two or more partitions, segmenting the enclosed area into two or more sub-areas. The methods also include determining boundary grids for each sub-area, and identifying internal grids in the sub-area for each sub-area. The methods further include identifying grids in the geographical region by collecting the boundary grids and the internal grids.

Abstract: Embodiments of the disclosure provide systems and methods for domain adaptation between a plurality of source domains and a target domain. The artificial intelligence method includes receiving labeled data from the plurality of source domains and unlabeled data from the target domain. The method further includes separately training, by a processor, a plurality of source classifiers each corresponding to a source domain using the labeled data received from the respective source domains. The method also includes selecting a subset of the labeled data received from each source domain based on a similarity between the selected labeled data and the unlabeled data of the target domain. The method additionally includes refining, by the processor, each source classifier using the selected subset of the labeled data, and predicting labels of the unlabeled data using the refined source classifiers.

Abstract: Systems and methods are provided for ride order dispatching. Such method may comprise obtaining information on a location of a vehicle and a time to input into a trained neural network algorithm; and based on a policy generated from the trained neural network algorithm, obtaining action information for the vehicle, the action information comprising: staying at a current position of the vehicle, re-positioning the vehicle, or accepting a ride order.

Abstract: Systems and methods are provided for determining vehicle pick-up location. An exemplary method may comprise obtaining a user's location and a request by the user for transportation to a destination, determining a vehicle to respond to the request, obtaining the determined vehicle's location, and determining a pick-up location for the vehicle to pick up the user based at least on the user's location, the destination's location, and the vehicle's location.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for automatically adjusting strategies. One of the methods includes: determining one or more characteristics of a plurality of complaints, wherein each of the complaints corresponds to an order; classifying the plurality of complaints into a plurality of categories based on the one or more characteristics by using a trained classifier; selecting a category from the plurality of categories based on a number of complaints in the selected category; from a group of strategies each associated with one or more conditions and one or more actions, identifying a candidate strategy causing the complaints of the selected category, wherein the one or more actions are executed in response to the one or more conditions being satisfied; and optimizing the candidate strategy using a reinforcement learning model at least based on a plurality of historical orders.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining a plurality of context-based subscription products in a ride-hailing platform are described. An exemplary method may include: determining a plurality of transportation contexts to which a plurality of context-based subscription products are applicable; obtaining a plurality of historical trip-requesting sessions between a plurality of riders and the ride-hailing platform, and a plurality of historical subscription products offered to the plurality of riders; constructing at least one key performance indicator (KPI) model that predicts a reward for the ride-hailing platform offering the plurality of context-based subscription products to the plurality of riders; constructing an optimization model to maximize a weighted sum of the at least one KPI model; and determining optimal values of the plurality of parameter vectors corresponding to the plurality of context-based subscription products.

Abstract: Electronic devices and methods for recognizing driving behavior are provided. The electronic devices may perform the methods to obtain first electronic signals encoding movement data associated with the electronic device from the at least one sensor at a target time point; operate logic circuits to determine whether the first electronic signals encoding movement data meets a precondition; and upon the first electronic signals encoding movement data meeting the precondition, send second electronic signals encoding movement data within a predetermined time period associated with the target time point to a remote server.

Abstract: A method of echo path delay destination and echo cancellation is described in this disclosure. The method includes: obtaining a reference signal, a microphone signal, and a trained multi-task deep neural network, wherein the multi-task deep neural network comprises a first neural network and a second neural network; generating, using the first neural network of the multi-task deep neural network, an estimated echo path delay based on the reference signal and the microphone signal; updating the reference signal based on the estimated echo path delay; and generating, using the second neural network of the multi-task deep neural network, an enhanced microphone signal based on the microphone signal and the updated reference signal.

Abstract: Systems and methods are disclosed configured to identify a location where current or predicted ride requests exceed a threshold within a time period. Driver location information for one or more drivers is used to identify a driver to satisfy the identified current or predicted ride requests at the location that exceed the threshold within the time period. In response to determining that a driver has at least a first likelihood of accepting a ride request at the location within the time period, item content is selected using a history of establishments frequented by the driver. The selected item of content, associated with a token, is provided for presentation on a display to the driver. In response to determining that the identified driver accepted the ride request at the location within the time period, the token is enabled to be utilized by the identified driver at an entity.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for carpool dual-pricing in ridesharing are provided. An exemplary method comprises: obtaining a machine-learning model trained to generate a probability for a carpool request from a rider to convert to a trip based at least on a pair of price adjustment multipliers applied to the carpool request; determining one or more Key Performance Indicator (KPI) models based on the machine-learning model; constructing an optimization model based on the KPI models, the optimization model comprising a plurality of pairs of price adjustment multipliers as decision variables; and determining optimal values of the plurality of pairs of price adjustment multipliers for the plurality of pricing units by solving the optimization model based on a plurality of historical carpool requests.