43 results about "Carpool" patented technology

The invention provides a layered multi-agent car-pooling vehicle scheduling method and device, and relates to the technical field of inter-city passenger transport car-pooling planning, and the method comprises the steps: obtaining passenger demand distribution, vehicle distribution and prediction data of origin and destination cities, combining a driving time matrix, a distance matrix and historical car-pooling data of regions, and carrying out the inter-city passenger transport car-pooling planning. And constructing a hypergraph structure and forming a model constraint. In the city level, the city intelligent agent carries out vehicle scheduling according to passenger and vehicle distribution in the city; and in the global level, the global intelligent agent further implements inter-city vehicle scheduling based on the scheduled state in the city. Through global vehicle and passenger distribution data, passengers and vehicles in the city are firstly matched, and then inter-city vehicles are scheduled according to a matching result, so that related transport mechanisms can configure transport capacity resources in advance. The waiting time of passengers and the empty driving range of drivers are effectively reduced, the problem of unbalanced distribution of passengers and vehicles between cities is recognized and relieved in advance, and meanwhile, the operating profit of a company is improved.

This APP is about live streaming inside and outside of a rideshare to authinticate and determine the saftey of everyone inside of the ride share. This APP will also determine the drivers identity to the passanger so they do not enter the wrong vehicle. This APP will store all video on the cloud. Aslo a code will be generated for each ride so it may be shared. All this is for saftey.

This application discloses a carpooling method, apparatus, electronic device, and storage medium, belonging to the field of Internet technology. The method includes: generating a trip receipt based on trip information uploaded by the driver; the trip information includes at least the origin and destination; sending the trip receipt to the driver; in response to a sharing instruction triggered by the driver, sharing an access identifier corresponding to the trip receipt to a target community group; the access identifier points to a carpooling details page containing the trip receipt; receiving an access request triggered by the passenger via the access identifier, and displaying the carpooling details page on the passenger's end; receiving a carpooling request submitted by the passenger on the carpooling details page, and pushing the carpooling request to the driver. This application embodiment realizes the function of drivers actively inviting passengers to carpool, and through the sharing mechanism of community groups, expands the dissemination range of carpooling information and improves the efficiency of travel matching.

An object of a system according to an embodiment is to improve matching accuracy between a user and a driver and to provide a safe and secure ride sharing service.SOLUTION: A system according to an embodiment includes a collection unit, an analysis unit, a matching unit, a monitoring unit, an analysis unit, a route analysis unit, and an education unit. The collection unit collects information on a user and a driver. The analysis unit analyzes the information collected by the collection unit. The matching unit matches the user and the driver based on the analysis result obtained by the analysis unit. The collection unit collects information inside and outside the vehicle. The monitoring unit monitors information inside and outside the vehicle. The analysis unit analyzes the driving technique. The route analysis unit analyzes the driving route. The teaching department provides the driver with a teaching program.SELECTED DRAWING: Figure 1

The application provides a ride-hailing carpool dynamic matching method based on travel time prediction. The method comprises the following steps: obtaining a data set of ride-hailing orders; constructing a travel time prediction model based on interpretable machine learning; training the travel time prediction model using the data set and the interpretable machine learning model SHAP method to obtain a trained travel time prediction model; constructing a shared network; predicting the travel time of each order by using the trained travel time prediction model; matching carpool orders according to the on-demand carpool dynamic matching algorithm; and dynamically dispatching the matched carpool orders in the direction of carbon emission reduction. The method uses the demand information and location data of passengers, matches the qualified passenger orders through reasonable algorithms and optimization strategies, reduces the empty running and repeated running of vehicles through carpooling, improves the service efficiency of ride-hailing and reduces carbon emissions.

The invention relates to the technical field of passenger transportation, in particular to a passenger flow hub rapid car-pooling method and system, which can obtain passenger flow data of a passenger flow hub, analyze destination statistical data after personnel leave the passenger flow hub, and determine at least one car-pooling direction according to the destination statistical data; all car-pooling directions and car-pooling points of the passenger flow hub are published through a preset public service platform; obtaining the number of people waiting for car pooling at the car pooling point in each time period; and dynamically allocating transport capacity according to the number of people waiting for carpooling, so that the order receiving vehicle can directly drive to the carpooling point to receive passengers. According to the technical scheme, the riding site is clear, a car-pooling driver directly goes to a fixed site to receive passengers, the destination directions of passengers at a boarding site are consistent, continuous traffic flow is formed to be coupled with the passenger flow in the same direction, invalid waiting time and driver and passenger interaction time are reduced, hub evacuation efficiency is improved, and the driving efficiency is improved. And the hub ground traffic flow and the congestion degree are reduced.

The application discloses a dynamic carpooling scheduling method for unmanned electric taxis, which comprises the following steps: obtaining data and performing cleaning; mapping the data in each hexagonal grid; establishing a travel demand feature matrix and a spatial dependence matrix; constructing a spatio-temporal graph convolutional neural network based on an attention mechanism to obtain a travel demand prediction result; setting a constraint condition for single-car matching in a dynamic carpooling scenario; constructing a single-car matching decision model based on distributed deep reinforcement learning based on the travel demand prediction result and the single-car matching constraint condition; designing a Double DQN solving algorithm; performing real-time order matching and idle vehicle scheduling based on the result; notifying the matched vehicles to complete the corresponding orders; and notifying the idle vehicles that have not been matched to perform regional scheduling or charging energy supplementing. In the dynamic carpooling of multiple passengers and a single car, the electric vehicle endurance journey constraint and the vehicle charging energy supplementing demand are considered, so that the quality is improved and the actual operation requirements are met.

The application discloses a scheduling method, system, product, storage medium and equipment of an unmanned shared bus. The method comprises the following steps: receiving a trip request; performing dynamic carpool clustering based on a multi-target cost function; adopting a fuzzy rolling time domain optimization strategy to divide time into a core interval and a fuzzy boundary interval; in each scheduling period, dynamically managing a virtual station according to a multi-factor weighted evaluation model, predicting future requests, and globally optimizing and solving the current and predicted requests; and issuing a scheduling instruction. The application solves the technical problems of rigid virtual station management, low dynamic carpool efficiency, insufficient real-time optimization capability and poor communication security in the prior art, can effectively improve the operation efficiency, user experience and system security of the unmanned microcirculation bus, and is suitable for dynamic response type transfer services in intelligent transportation.

The invention discloses a car-pooling dynamic scheduling method and system for online car-hailing, and relates to the technical field of dynamic scheduling of order dispatching tasks, and the method comprises the steps: collecting real-time order information and working state information of online car-hailing, and constructing a city supply and demand distribution diagram; the order and the online car-hailing car are used as two intelligent agents respectively, and after the two intelligent agents are subjected to one-to-one matching, the fitness of each pair of matched intelligent agents is calculated; performing global stability analysis according to the fitness; and according to an analysis result of the stability, performing global adjustment on a matching result to generate a final scheduling result. According to the overall scheme, the intelligent level and user experience of car sharing service are improved, and efficient, safe and sustainable development of urban shared travel service is promoted.

The present application relates to a kind of online car-hailing carpooling matching method, device, electronic equipment and storage medium, belong to vehicle carpooling matching technical field, wherein the online car-hailing carpooling matching method includes: based on the start position of multiple groups of OD, the multiple groups of OD are hierarchically clustered, obtain first clustering result;Based on the directed line segment and end position formed by the start point and end point of each group of OD in each clustering cluster in the first clustering result, the first clustering result is optimized, obtain second clustering result;Based on the travel time between the end point of each two groups of OD in each clustering cluster in the second clustering result, the second clustering result is optimized, obtain third clustering result, and the third clustering result is used as carpooling matching result.The present application carries out carpooling matching according to actual OD, guarantees the effect of carpooling matching, improves the experience of user carpooling.

The application relates to a trip publishing method, device, equipment, storage medium and computer program product. The method comprises the following steps: in response to a trip configuration operation, displaying a carpool service item; in response to a selection operation on a package service in the carpool service item, displaying a trip time of the package service; the package service is a carpool service in which the number of trips of the same trip within a trip period reaches a preset condition; in response to an address configuration operation, displaying a starting address and a target address corresponding to the same trip; and in response to a trip publishing operation, publishing package trip information; the package trip information is trip information of the package service, which comprises the trip time, the starting address and the target address. The method can improve carpool efficiency.

A system for casual driver ride sharing includes an interface and processor. The interface is to receive a request for a ride from a user, wherein the request includes GPS information for the user. The processor is to determine compatibility between the typical route information and the request for the ride; determine a ranked list based at least in part on the compatibility; and provide a ride offer to a driver of the one or more casual drivers based at least in part on the ranked list.

The invention belongs to the technical field of intelligent transportation, and particularly relates to an urban online car-hailing order dispatching method in a mixed demand environment based on STGAT-PPO. According to the specific technical scheme, through multi-dimensional state representation and a binary action space, a multi-target reward function fusing fast car response penalty and car-pooling mileage saving is constructed, and autonomous balance of strategies is driven; an order sending model is established in combination with a space-time diagram attention network and a near-end strategy optimization algorithm, the space-time diagram attention network is adopted to extract high-dimensional space-time feature representation of a system state, the near-end strategy optimization algorithm is adopted to learn an optimal strategy on the high-dimensional space-time feature representation, and dynamic regulation and control of a service mode are realized. Based on STGAT-PPO joint modeling, the system senses local supply and demand characteristics in real time, and dynamically switches service modes: car pooling is preferentially carried out to improve transport capacity when supply is insufficient, and fast cars are directly dispatched to guarantee experience when supply is sufficient.

A computer-implemented method that, in an embodiment, includes receiving a travel request from a traveler that includes a pickup and destination location and a number of travelers and analyzing the travel request and calculating routes for vehicles that are partially based on the pickup and destination location, the number of travelers, destination locations of travelers located in the vehicles, traffic conditions, minimizing a waiting time for the traveler, minimizing a travel time for the traveler, minimizing a travel time for the travelers located in the vehicles, and optimizing an aggregation of travelers on each of the plurality vehicles. In an embodiment, the plurality of vehicles includes 5 vehicles or more and based on the calculating, the method includes supplying a selected route to a selected vehicle and supplying to the traveler, identification information related to the selected vehicle thereby resulting in transportation of the traveler to the destination location. A systems and methods for ridesharing are provided. The systems and method can include splitting a plurality of GPS locations for a given vehicle into segments, determining a most probable location for each GPS location, and reconstructing the route, for a fleet of ridesharing vehicles.

The application discloses a two-stage carpool matching method and system for connecting taxis at a large traffic hub, and the method comprises the following steps: constructing a hub taxi carpool model by taking the shortest total driving mileage of vehicles and the minimum number of service vehicles as optimization targets, and considering the hub passenger characteristics and parameters including large luggage, departure and arrival time as constraints; obtaining passenger requests, taking the path vector similarity of fused direction and space-time characteristics as a benchmark, and clustering the passenger requests by using an adaptive hierarchical clustering algorithm to obtain passenger request clusters; and solving a carpool path planning problem by using an improved adaptive genetic algorithm based on the hub taxi carpool model and the passenger request clusters, so as to obtain a passenger matching scheme and a carpool driving path. The two-stage carpool matching method can effectively quantify and cluster similar passenger requests, can improve the calculation efficiency by 85%, and can reduce the waiting time and detour distance of passengers.

To provide a vehicle allocation plan for a plurality of passengers ride-sharing a vehicle; more specifically, to provide an efficient vehicle allocation plan for group ride-sharing.SOLUTION: A vehicle allocation system is configured to: register ride-sharing group information that defines a relationship between a plurality of passengers who approve ride-sharing; acquire vehicle allocation reservation information for the plurality of passengers including boarding and disembarking locations; and generate a vehicle allocation plan based on the boarding and disembarking locations included in the plurality of pieces of vehicle allocation reservation information so that a vehicle allocation cost for one or the plurality of vehicles is minimized and only passengers who are approved for ride-sharing based on the ride-sharing group information can ride-share.SELECTED DRAWING: Figure 1

The application discloses a carpool matching method and device and electronic equipment, and belongs to the technical field of transportation. The carpool matching method comprises the following steps: in response to a passenger travel request, obtaining a target activity associated with the passenger travel request, a passenger interest label of a passenger terminal in the target activity scenario, and driver interest labels of a plurality of candidate driver terminals; determining a target driver terminal from the plurality of candidate driver terminals based on the passenger interest label and the driver interest labels of each candidate driver terminal; and outputting a matching order between the passenger terminal and the target driver terminal. The carpool matching method can not only meet the physical travel demand, but also meet the emotional and social needs of users, thereby improving the travel experience and system intelligence in complex scenarios.

The application provides a layered multi-agent carpool vehicle scheduling method and device, and relates to the technical field of intercity passenger carpool planning. The method obtains passenger demand distribution, vehicle distribution and prediction data of starting and ending cities, combines travel time matrix, distance matrix and historical carpool data between regions, constructs a hypergraph structure and forms a model constraint. At the city level, the city agent schedules vehicles according to the passenger and vehicle distribution within the city. At the global level, the global agent further implements intercity vehicle scheduling based on the state after the city scheduling. Through global vehicle and passenger distribution data, the city passengers and vehicles are matched first, and then the intercity vehicles are scheduled according to the matching result, so that the relevant transportation agencies can configure transport resources in advance. The method effectively reduces the passenger waiting time and the driver's empty mileage, identifies and alleviates the imbalance between intercity passenger and vehicle distribution in advance, and improves the company's operating profit.

The invention belongs to the technical field of traffic scheduling and optimization, and discloses an on-demand car-pooling optimization method and device and a storage medium, and the method comprises the steps: receiving a plurality of riding orders and vehicle information from passengers through a car-pooling platform; based on the order receiving probability and the vehicle information, constructing an order cancellation perception car-pooling optimization model, and generating matching between the passenger and the vehicle; and the matching result and the discount travel price are sent to the passenger through the carpooling platform, and the path of the vehicle is determined by the synthesis platform according to the matching condition of the passenger and the vehicle. According to the method, matching, pricing and path decisions in the car-pooling service are jointly optimized, the order cancellation probability problem is clearly considered, profit-oriented decisions are supported, and meanwhile, estimation of too high system income caused by neglecting the cancellation condition is reduced; through a predictive driving approximation and decomposition algorithm, an original problem can be closely approximated and remarkably simplified, the model is solved in real time under an actual scale, and the solving process is accelerated.

This application relates to the field of carpooling demand prediction technology, and particularly to a method, device, electronic device, and storage medium for predicting carpooling demand. The method includes: constructing a feature tensor set based on historical order data, meteorological parameters, and regional static feature data; transforming the target low-dimensional statistical features into target high-dimensional semantic features; and mapping the target high-dimensional semantic features to a target orthogonal subspace to generate a feature set that eliminates redundant temporal correlations. The feature set is then used to optimize the hyperparameters of a pre-constructed ensemble learning gradient boosting tree model until an iteration stopping condition is met, thus constructing a carpooling demand prediction model. This model outputs carpooling demand. This solves the problem that related technologies fail to couple the temporal and spatial dependencies of passenger travel demand, and that the prediction models are sensitive to hyperparameters, making it difficult to adapt to unconventional scenarios and output accurate carpooling demand.

The aim is to make ride-sharing matching easier. [Solution] The server device 200 of the present invention is characterized by having an acquisition means for acquiring information on whether or not a car share user allows a passenger to ride in the vehicle they rent, and a matching means for matching car share users who allow a passenger to ride with ride share users based on the information acquired by the acquisition means. By matching car share users who allow a passenger with ride share users, it is possible to facilitate ride share matching.

The invention discloses a stacked satellite separating device, and relates to the technical field of spaceflight. The stacked satellite separating device is characterized in that the lower surface of a satellite mounting platform is connected with an upper stage of a carrier rocket; the lower surface of the first car-pooling satellite installation platform is connected with the upper end of at least one first locking and separating mechanism framework, and the lower end of each first locking and separating mechanism framework is rotationally connected with the upper surface of the satellite installation platform through a one-way rotation unit. At least one first stacked satellite pressing module is further arranged on the lower surface of the first car-pooling satellite mounting platform; the lower surface of the second car-pooling satellite mounting platform is connected with the upper end of at least one second locking and separating mechanism framework, and the lower end of each second locking and separating mechanism framework is rotationally connected with the upper surface of the satellite mounting platform through a one-way rotation unit; and at least one second stacked satellite pressing module is further arranged on the lower surface of the second car-pooling satellite mounting platform. Carpooling launching of stacked satellites and other satellites can be achieved, and the load space utilization rate is effectively increased.

Ride-sharing system, comprehensive: a memory configured to contain one or more executable instructions; a controller configured to execute the executable instructions; one or more mobile computing devices (57) configured to transmit pickup location data (303) and drop-off location data (306) to the controller; a ride-sharing vehicle (12) configured to transmit vehicle location data to the controller, wherein the ride-sharing vehicle (12) is an autonomous vehicle configured to drive autonomously from one location to another; and the executable instructions of the controller enable the following: Receiving the pickup location data (303) transmitted by the mobile computing device (57); Receiving the drop location data (306) from the one or more mobile computing devices (57); Receiving vehicle location data from the rideshare vehicle (12); based on the pick-up location data (303), drop-off location data (306) and vehicle location data, calculating a ride-sharing priority number (304) for each of the one or more mobile computing devices (57), wherein the ride-sharing priority number (304) is calculated from the following equation: VT = α (RT) − β 1 (PT) − β 2 (JT) − γ (CT) + δ 1 (WT) + δ 2 (WT 2) + ε (DT), where the ride-hailing priority number (304) is calculated from the following weighted variables: expected revenue from serving the customer (RT), customer pick-up time (PT), customer travel time (JT), fee spent serving the customer (CT), customer current wait time (WT), and customer destination suitability (DT), and where α, β1, β2, γ, δ1, δ2, and ε are weighted factors having a default weight value; Transmitting the ride-sharing priority number (304), pick-up location data (303) and drop-off location data (306) to the ride-sharing vehicle (12) for at least one of the one or more mobile computing devices (57); and where the ride-sharing vehicle (12) is configured to: Receiving the ride-sharing priority number (304), pick-up location data (303) and drop-off location data (306) for each of the one or more mobile computing devices (57) from the controller; Select the rideshare priority number (304) with the highest value; and Transfer to a location that matches the pickup location data (303) for the selected rideshare priority number (304).

An electric vehicle includes several features to improve ridesharing and / or package delivery services. The vehicle includes electric motor(s) and / or auxiliary system(s) disposed along or under the floor to increase the size of the cabin without increasing the overall size of the vehicle. The passenger seats are foldable and movable to provide a contiguous cargo space. The side door includes an integrally formed B pillar to provide a larger opening on the side of the vehicle when the side door is open for ingress and egress of both the driver and passengers. Each wheel includes an electroactive suspension system to tilt the vehicle in different directions to facilitate greater ease of ingress and egress and / or loading and unloading of cargo. The vehicle includes a user interface system to assist the driver with package delivery services. The vehicle also connects to a trailer that provides electric propulsion and active steering.

1. Name of this design: Graphical User Interface for Route Comparison in Electronic Devices. 2. Application of this design: This design is intended for use in an electronic device. 3. The key design feature of this product is its graphical user interface. 4. The image or photo that best illustrates the design points: Interface change state diagram 1. 5. Conventional design, omitting rear, left, right, top, and bottom views. 6. Purpose of the graphical user interface: This product design is used for comparing and viewing carpooling routes. Users can compare their own and their fellow passengers' routes through a human-computer interaction when carpooling. 7. Human-computer interaction method of graphical user interface: When the user clicks the "View Route Comparison" control in the middle of the interface in the main view, the interface changes to Figure 1. If the user continues to slide up from this interface, the interface changes to Figure 2.

The application relates to a truck loading and unloading device for logistics carpooling, which comprises a truck cabin and a cabin door. The truck cabin has a cavity, and the cabin door is installed at the cavity opening. The cabin door comprises a pressure bearing part and a limiting part. The pressure bearing part has a first rotating side which is rotatably connected to one side of the cavity opening close to the ground. The side of the truck cabin close to the ground is provided with a driving chamber. A roller is arranged in the driving chamber. The truck cabin is provided with a through hole which is connected to the driving chamber and the cavity. The roller and the pressure bearing part are connected through a follow-up assembly. The length of the pressure bearing part in the direction perpendicular to the first rotating side is greater than the distance from the bottom of the truck cabin to the ground. The cabin door has a closed state and a loading and unloading state. In the loading and unloading state, the side of the pressure bearing part away from the first rotating side is rotated to hang down on the ground. The follow-up assembly controls the roller to be partially lifted into the cavity from the driving chamber through the through hole under the driving of the rotation of the pressure bearing part, and the roller is in abutment with the goods in the cavity. The situation that extra manpower and material resources are consumed during loading and unloading is improved.

The application discloses a trip splicing judgment method based on three-dimensional space-time prisms, and relates to the field of data processing.The method comprises the following steps: modeling a road network as a directed graph, defining the maximum tolerable driving time and the maximum waiting offset time of a passenger for a trip, constructing a three-dimensional space-time prism of the trip and screening candidate trip pairs; calculating the waiting offset according to the pickup sequence, translating the space-time prisms corresponding to the trips along the time axis, and obtaining a space-time overlapping area through three-dimensional Boolean intersection operation; filtering the space-time overlapping area through step-by-step contraction, extracting a local sub-space-time prism from the second pickup point to the first drop-off point as a carpooling feasible region; judging the splicing according to the feasible region, constructing the whole reachable range, and outputting the carpooling splicing result.The application converts the space-time overlap into an effective carpooling space-time range that meets the complete pickup and drop-off process constraints, and improves the reliability and intuitiveness of the splicing judgment model.

The system according to this embodiment aims to provide a safe and secure ride-sharing service. [Solution] The system according to the embodiment comprises a confirmation unit, a provision unit, a monitoring unit, and a resolution unit. The confirmation unit confirms the permission criteria for the driver and vehicle. The provision unit provides information using generating AI. The monitoring unit monitors the vehicle status using connected cars. The resolution unit resolves the needs of both the user and the driver.

Method for assigning a vehicle (108) to a user (106), comprising: Receiving, by a computing device (102), a user ride-sharing request for a vehicle (108) from a plurality of available vehicles (108) from a user (106); Received by the computing device (102), a vehicle risk assessment threshold preference associated with the user (106); Determine, by the computing device (102), a user risk assessment that is associated with the user (106); Determine, by means of the calculating device (102), a vehicle risk assessment that is associated with at least one of the plurality of available vehicles (108); Received, by the computing device (102), a user risk assessment threshold preference associated with each of the plurality of available vehicles (108); Identify, by the computing device (102), one or more vehicles (108) within a subset of the plurality of available vehicles (108) that have an associated vehicle risk rating at or below the vehicle risk rating threshold preference associated with the user (106) and an associated user risk rating threshold preference at or above the user risk rating associated with the user (106); present, to the user (106), one or more ride-sharing options for selecting one of the one or more vehicles (108) from the subset of the plurality of available vehicles (108) for the user ride-sharing request; and Receiving a selection by the user (106) from a user device of one of the one or several vehicles (108).