Artificial intelligent systems and methods for identifying a drunk passenger by a car hailing order

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.

What is claimed is: 
     
         1 . An artificial intelligent system for identifying a drunk passenger of a car hailing order, comprising:
 at least one storage medium including a drunk model and a set of instructions for identifying a drunk passenger of a car hailing order; and   at least one processor in communication with the storage medium, wherein the at least one processor is directed to cause the system to perform operations including:
 obtaining a car hailing order from a passenger terminal of a passenger; 
 utilizing a drunk model to determine whether the passenger is drunk based on the car hailing order; 
 in response to a determination that the passenger is drunk, transmitting an alert to a driver terminal of a driver of the car hailing order for display on a driver interface of the driver terminal. 
   
     
     
         2 . The artificial intelligent system of  claim 1 , wherein the determining whether the passenger is drunk based on the car hailing order includes:
 obtaining a drunk probability of the passenger, wherein the car hailing order is an input of the drunk model, and the drunk probability is an output of the drunk model;   determining whether the drunk probability is greater than a probability threshold; and   in response to a determination that the drunk probability is greater than the probability threshold, determine that the passenger is drunk.   
     
     
         3 . The artificial intelligent system of  claim 1 , wherein the drunk model is generated based on a plurality of drunk-hotspot-relating features associated with a plurality of drunk hotspots. 
     
     
         4 . The artificial intelligent system of  claim 3 , wherein the operations further include:
 identifying the plurality of drunk hotspots based on a plurality of historical designated-driving orders.   
     
     
         5 . The artificial intelligent system of  claim 4 , wherein the identifying the plurality of drunk hotspots includes:
 obtaining a plurality of historical drunk designated-driving orders from the plurality of historical designated-driving orders, each of the plurality of historical drunk designated-driving orders including a start location; and   determining the plurality of drunk hotspots based on the start locations of the plurality of historical drunk designated-driving orders.   
     
     
         6 . The artificial intelligent system of  claim 5 , wherein the determining the plurality of drunk hotspots based on the start locations of the plurality of historical drunk designated-driving orders includes:
 identifying a plurality of areas based on the start locations of the plurality of historical drunk designated-driving orders; and   for each of the plurality of areas,
 determining whether the area meets a predetermined condition, and 
 in response to a determination that the area meets the predetermined condition, designating the area as one drunk hotspot of the plurality of drunk hotspots. 
   
     
     
         7 . The artificial intelligent system of  claim 6 , wherein the predetermined condition includes at least one of:
 a number of historical drunk designated-driving orders in the area is greater than a number threshold; or   a ratio of a number of historical drunk-complaint car hailing orders to a number of historical drunk designated-driving orders is greater than a ratio threshold.   
     
     
         8 . The artificial intelligent system of  claim 3 , wherein the drunk model is trained by:
 obtaining a plurality of samples from historical car hailing orders stored in a database;   for each of the plurality of samples, using an application, extracting a plurality of features including a passenger feature set, a driver feature set, and an order feature set, wherein the order feature set includes the plurality of drunk-hotspot-relating features; and   train a preliminary classification model based on the plurality of features and the plurality of samples to obtain the drunk model.   
     
     
         9 . The artificial intelligent system of  claim 8 , wherein the plurality of samples includes a positive sample set and a negative sample set, wherein
 the positive sample set includes a plurality of historical drunk car hailing orders, and   the negative sample set includes a plurality of historical non-drunk car hailing orders.   
     
     
         10 . The artificial intelligent system of  claim 8 , wherein the passenger feature set includes a random passenger's essential features and features relating to the random passenger's historical orders,
 the driver feature set includes a random driver's essential features and features relating to the random driver's historical orders, and   the order feature set further includes a random order's essential features.   
     
     
         11 . The artificial intelligent system of  claim 8 , wherein the extracting the plurality of features includes:
 for each of the plurality of samples,
 identify a start location; 
 map the start location to a drunk hotspot; and 
 extract the drunk-hotspot-relating features based on the drunk hotspot. 
   
     
     
         12 . The artificial intelligent system of  claim 8 , wherein the preliminary classification model is a Gradient Boosted Decision Tree (GBDT) model. 
     
     
         13 . An artificial intelligent method for identifying a drunk passenger of a car hailing order, implemented on a computing device including at least one storage medium including a set of instructions, a data exchange port communicatively connected to a network, and at least one processor in communication with the storage medium, the method comprising:
 obtaining a car hailing order from a passenger terminal of a passenger;   utilizing a drunk model to determine whether the passenger is drunk based on the car hailing order;   in response to a determination that the passenger is drunk, transmitting an alert to a driver terminal of a driver of the car hailing order for display on a driver interface of the driver terminal.   
     
     
         14 . The artificial intelligent method of  claim 13 , wherein the determining whether the passenger is drunk based on the car hailing order includes:
 obtaining a drunk probability of the passenger, wherein the car hailing order is an input of the drunk model, and the drunk probability is an output of the drunk model;   determining whether the drunk probability is greater than a probability threshold; and   in response to a determination that the drunk probability is greater than the probability threshold, determine that the passenger is drunk.   
     
     
         15 . The artificial intelligent method of  claim 13 , wherein the drunk model is generated based on a plurality of drunk-hotspot-relating features associated with a plurality of drunk hotspots. 
     
     
         16 . The artificial intelligent method of  claim 15 , wherein the operations further include:
 identifying the plurality of drunk hotspots based on a plurality of historical designated-driving orders.   
     
     
         17 . The artificial intelligent method of  claim 16 , wherein the identifying the plurality of drunk hotspots includes:
 obtaining a plurality of historical drunk designated-driving orders from the plurality of historical designated-driving orders, each of the plurality of historical drunk designated-driving orders including a start location; and   determining the plurality of drunk hotspots based on the start locations of the plurality of historical drunk designated-driving orders.   
     
     
         18 . The artificial intelligent method of  claim 17 , wherein the determining the plurality of drunk hotspots based on the start locations of the plurality of historical drunk designated-driving orders includes:
 identifying a plurality of areas based on the start locations of the plurality of historical drunk designated-driving orders; and   for each of the plurality of areas,
 determining whether the area meets a predetermined condition, and 
 in response to a determination that the area meets the predetermined condition, designating the area as one drunk hotspot of the plurality of drunk hotspots. 
   
     
     
         19 . The artificial intelligent system of  claim 15 , wherein the drunk model is trained by:
 obtaining a plurality of samples from historical car hailing orders stored in a database;   for each of the plurality of samples, using an application, extracting a plurality of features including a passenger feature set, a driver feature set, and an order feature set, wherein the order feature set includes the plurality of drunk-hotspot-relating features; and   train a preliminary classification model based on the plurality of features and the plurality of samples to obtain the drunk model.   
     
     
         20 . A non-transitory readable medium, comprising at least one set of instructions for identifying a drunk passenger of a car hailing order, wherein when executed by at least one processor of an electrical device, the at least one set of instructions directs the at least one processor to perform a method, the method comprising:
 obtaining a car hailing order from a passenger terminal of a passenger;   utilizing a drunk model to determine whether the passenger is drunk based on the car hailing order;   in response to a determination that the passenger is drunk, transmitting an alert to a driver terminal of a driver of the car hailing order for display on a driver interface of the driver terminal.