CN116308653A

CN116308653A - Traffic simulation-based car sharing method and related equipment

Info

Publication number: CN116308653A
Application number: CN202310244474.XA
Authority: CN
Inventors: 朱政; 王晗同; 祝江涛; 陈喜群; 张磊; 赵俊; 杨宝春; 王磊
Original assignee: Zhejiang University ZJU
Current assignee: Zhejiang University ZJU
Priority date: 2023-03-07
Filing date: 2023-03-07
Publication date: 2023-06-23

Abstract

The specification provides a traffic simulation-based carpooling method and related equipment. The method comprises the following steps: acquiring order information of each of a plurality of carpooling orders in a first period; acquiring a traffic simulation result of the target area in a second period based on a traffic simulation model obtained through pre-training; the second period of time includes the first period of time; the traffic simulation result comprises the dynamic traffic condition of the target area in the second period obtained through simulation; and matching at least one corresponding carpool order in the plurality of carpool orders for idle vehicles in the plurality of service vehicles in the target area based on order information of each carpool order and the traffic simulation result.

Description

Traffic simulation-based car sharing method and related equipment

Technical Field

One or more embodiments of the present disclosure relate to the field of intelligent traffic technologies, and in particular, to a traffic simulation-based carpooling method and related devices.

Background

In the carpooling service provided by the network car-contracting company, the same service vehicle is matched with passengers with similar routes, so that the travel cost of the passengers and the total travel mileage of the service vehicle can be reduced, and the network car-contracting company has good economic benefit and environmental benefit. However, the car sharing service mostly has serious waiting and detour problems, which affect the traveling experience of passengers.

Therefore, how to match the most suitable service vehicle for each passenger of the carpool to reduce the waiting time and the detour time of the passenger in the carpool process is a problem to be solved.

Disclosure of Invention

In view of this, one or more embodiments of the present disclosure provide a carpooling method and related devices based on traffic simulation.

In a first aspect, the present disclosure provides a traffic simulation-based carpooling method, the method including:

acquiring order information of each of a plurality of carpooling orders in a first period;

acquiring a traffic simulation result of the target area in a second period based on a traffic simulation model obtained through pre-training; the second period of time includes the first period of time; the traffic simulation result comprises the dynamic traffic condition of the target area in the second period obtained through simulation;

and matching at least one corresponding carpool order in the plurality of carpool orders for idle vehicles in the plurality of service vehicles in the target area based on order information of each carpool order and the traffic simulation result.

In a second aspect, the present disclosure provides a traffic simulation-based carpool device, the device comprising:

The first acquisition unit is used for acquiring order information of each of a plurality of car pooling orders in a first period;

the second acquisition unit is used for acquiring a traffic simulation result of the target area in a second period based on a traffic simulation model obtained through pre-training; the second period of time includes the first period of time; the traffic simulation result comprises the dynamic traffic condition of the target area in the second period obtained through simulation;

and the matching unit is used for matching at least one corresponding carpool order in the plurality of carpool orders for idle vehicles in the plurality of service vehicles in the target area based on the order information of each carpool order and the traffic simulation result.

Accordingly, the present specification also provides a computing device comprising: a memory and a processor; the memory has stored thereon a computer program executable by the processor; and when the processor runs the computer program, the traffic simulation-based carpooling method is executed.

Accordingly, the present specification also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the traffic simulation-based carpooling method as described in the above embodiments.

In summary, according to the traffic simulation method and the traffic simulation device, the traffic simulation result of the target area in a period of time is obtained through simulation by means of the traffic simulation technology, namely the dynamic traffic condition of the target area in the period of time is obtained through simulation. Then, the present application may match at least one of the most appropriate carpool orders for the idle vehicles of the plurality of service vehicles within the target area based on the driving situation of each carpool order under the current traffic simulation result. Therefore, the method and the device provide effective and reliable reference for reasonable matching of the carpool order and the service vehicle through the traffic simulation technology, so that waiting time and detour time of passengers in the carpool process are reduced, the quality of carpool service is improved, further, the operation efficiency of a traffic system can be improved, and the problem of urban traffic jam is effectively solved.

Drawings

FIG. 1 is a flow chart of a carpooling method based on traffic simulation provided by an exemplary embodiment;

FIG. 2 is a flow chart of another traffic simulation-based carpooling method provided by an exemplary embodiment;

FIG. 3 is a schematic illustration of a combination of carpools provided in an exemplary embodiment;

FIG. 4 is a schematic diagram of empty cars and order quantity without a pooling scene provided by an exemplary embodiment;

FIG. 5 is a schematic illustration of empty cars and order quantity in a pooling scene provided by an exemplary embodiment;

FIG. 6 is a schematic structural diagram of a carpool device based on traffic simulation according to an exemplary embodiment;

FIG. 7 is a schematic diagram of a computing device provided in an exemplary embodiment.

Detailed Description

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of the present specification. Rather, they are merely examples of apparatus and methods consistent with aspects of one or more embodiments of the present description as detailed in the accompanying claims.

It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the method may include more or fewer steps than described in this specification. Furthermore, individual steps described in this specification, in other embodiments, may be described as being split into multiple steps; while various steps described in this specification may be combined into a single step in other embodiments.

User information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to herein are both user-authorized or fully authorized information and data by parties, and the collection, use and processing of relevant data requires compliance with relevant laws and regulations and standards of the relevant country and region, and is provided with corresponding operation portals for user selection of authorization or denial.

First, some terms in the present specification are explained for the convenience of understanding by those skilled in the art.

(1) Traffic simulation is an effective method for analyzing and evaluating traffic schemes. By constructing a high-precision and low-cost dynamic traffic simulation model to deduce the traffic space-time state, researchers can be helped to effectively evaluate traffic control schemes, for example, the regions and reasons of traffic jams can be clearly and assisted to analyze and predict, and further, related schemes of urban planning, traffic engineering and traffic management can be accurately evaluated. Traffic simulation technology is an important component of modern intelligent traffic systems.

As described above, in the carpooling service provided by the network about car company, by matching the same service vehicle with passengers having similar routes, the traveling cost of the passengers and the total traveling mileage of the service vehicle can be reduced, and good economic and environmental benefits are achieved. However, conventional supply and demand matching algorithms for matching service vehicles and carpool orders have the following problems: (1) When the method is applied to a scene of a large-scale urban road network or a large number of carpooling orders, the method has the problems of low calculation efficiency or low algorithm applicability. (2) Most supply and demand matching algorithms adopt a static optimization method, and various assumptions and simplification must be made when the whole optimization period is considered, so that the result is distorted. The problems of waiting for the passengers and detouring are caused in the car sharing service, and the traveling experience of the passengers is affected.

Based on the above, the specification provides a technical scheme for matching the most suitable service vehicle for each carpool order through a traffic simulation technology, so that a large number of carpool demands and travel experiences in a large-scale city every day are met.

In implementation, the method and the device can acquire order information of each of a plurality of car pooling orders in a first period, and acquire a traffic simulation result of a target area in a second period based on a traffic simulation model trained in advance, wherein the second period can comprise the first period. Then, based on the order information of each of the plurality of carpool orders and the traffic simulation result, the running information of each of the plurality of carpool orders can be obtained. And finally, matching at least one corresponding carpooling order for the idle vehicles in the plurality of service vehicles in the target area based on the running information of each carpooling order and a preset matching rule.

In the technical scheme, the traffic simulation result of the target area (such as a large-scale urban road network) in a period of time is obtained through simulation by the traffic simulation technology, and the dynamic traffic condition in the period of time is obtained. Then, the method and the device can acquire the driving condition of each car pooling order in the time under the current traffic simulation result. Further, the present application may match at least one of the most appropriate carpool orders for a free vehicle of the plurality of service vehicles within the target area based on the driving condition of each carpool order under the current traffic simulation result. Therefore, the method and the device provide effective and reliable reference for reasonable matching of a large number of carpool orders and service vehicles through the traffic simulation technology, so that waiting time and detour time of passengers in the carpool process are reduced, the quality of carpool service is improved, further, the operation efficiency of a traffic system can be improved, and the problem of urban traffic jam is effectively relieved.

Referring to fig. 1, fig. 1 is a schematic flow chart of a carpooling method based on traffic simulation according to an exemplary embodiment. The method may be applied to a computing device, which may be a smart phone, a tablet computer, a notebook computer, a desktop computer, an on-board computer, or a server, etc., which is not particularly limited in this specification. In an embodiment, the computing device may be a server, a server cluster formed by a plurality of servers, or a cloud computing service center, etc., which is not specifically limited in this specification. The computing device may be, for example, a server of taxi taking software. As shown in fig. 1, the method may specifically include the following steps S101 to S103.

Step S101, order information of each of a plurality of car pooling orders in a first period is acquired.

In one illustrated embodiment, the passenger may submit a corresponding ride share order via the taxi taking software based on his travel requirements. Wherein the order information of each carpool order may include a reserved trip time, a start location and a destination location, etc. In an illustrated embodiment, the order information may also include any other possible information, such as whether the passenger is carrying a pet, whether the passenger accepts a carpool, etc., as this specification is not limited in detail. It should be noted that, the plurality of car sharing orders do not limit the passengers to select only a car sharing for traveling, and the traveling order submitted by each passenger can be used as the car sharing order.

Accordingly, in one illustrated embodiment, the computing device may collect the carpool orders submitted by each passenger on the taxi-taking software and obtain order information for each carpool order.

In an illustrated embodiment, the computing device may periodically obtain the pooling order, for example, obtain the pooling order newly added within 1 hour every 1 hour, obtain the pooling order newly added within half an hour every half an hour, and so on, which is not specifically limited in this specification.

In an illustrated embodiment, the computing device may divide the plurality of collected car pooling orders based on order information for each car pooling order. For example, the computing device may divide the plurality of car pooling orders into corresponding time periods based on the reserved travel time of each car pooling order, respectively.

In an illustrated embodiment, a computing device may obtain order information for each of a plurality of carpool orders over a first period of time. The reserved travel time of the plurality of car pooling orders in the first period is within the first period, and the first period is, for example, 7:00-7:15, or 12:30-13:00, etc.

Illustratively, with the early rush hour example, the reservation travel time for most passengers is substantially within the time period of 7:00-9:00. Further, the computing device may subdivide the period of 7:00-9:00 into 12 periods in units of 10 minutes, specifically including: 7:00-7:10, 7:10-7:20, 7:20-7:30, 7:30-7:40, 7:40-7:50, 7:50-8:00, 8:00-8:10, 8:10-8:20, 8:20-8:30, 8:30-8:40, 8:40-8:50, 8:50-9:00. Illustratively, the first period may be any one of the 12 periods, such as 7:00-7:10, or 7:10-7:20, and so on.

For example, taking 1000 car-pooling orders in a period of 7:00-9:00 as an example, the reserved travel time of 50 car-pooling orders in the 1000 orders is in a period of 7:00-7:10, the reserved travel time of 17 car-pooling orders in the 1000 orders is in a period of 7:10-7:20, the reserved travel time of 25 car-pooling orders in the 1000 orders is in a period of 7:20-7:30, and so on. For example, the computing device obtaining order information for each of a plurality of carpool orders over a first period of time may include: order information of each of the 50 carpooling orders in the period of 7:00-7:10 is obtained. Subsequently, the computing device may match the most suitable service vehicles for the 50 carpool orders in the 7:00-7:10 period, respectively, based on the traffic simulation technique, to maximize the travel experience of the passengers, and so on, and please refer to the description of the following embodiments, which will not be described in detail herein.

In an illustrated embodiment, the computing device may also subdivide the entire period of 7:00-9:00 into 4 periods in 30 minutes, or subdivide the period of 7:00-9:00 into 8 periods in 15 minutes, and so on, as this specification does not specifically limit. In an illustrated embodiment, the time slots may be divided according to actual simulation performance, calculation performance, travel requirements (such as the number of car sharing orders) of the computing device, and the like, which is not specifically limited in this specification.

Step S102, based on a traffic simulation model obtained through pre-training, a traffic simulation result of the target area in a second period is obtained.

As described above, in order to match the most suitable service vehicle for each car sharing order, so as to reduce waiting time and detour time of passengers, the present application may utilize traffic simulation technology to simulate and obtain the traffic condition of the dynamic before and after the reserved travel time, so as to provide accurate and effective reference for the subsequent driver and passenger matching.

It will be appreciated that, based on different travel requirements and traffic conditions, each of the car pool orders will most often not experience only the period of time it has reserved travel time during actual travel, e.g. the reserved travel time for car pool order a is 8:25, within the 8:20-8:30 period described above, but its actual travel may experience 8:15-8:40, or 8:28-8:45 or even longer, etc. Therefore, the practical traveling situation of passengers is fully and comprehensively considered, and the traffic situation of each car sharing order in a longer period of time before and after the reserved traveling time of the car sharing order is simulated, so that the follow-up running situation that each car sharing order is more complete and reliable under the traffic simulation can be supported, and the proper service vehicle is matched for each car sharing order.

In an embodiment, for the plurality of car pooling orders in the first period, the computing device may obtain a traffic simulation result of the target area in the second period based on a traffic simulation model trained in advance. The second period may include the first period, and a period of a previous preset duration and a period of a next preset duration adjacent to the first period. The preset time period may be, for example, 5 minutes, 10 minutes, or 12 minutes, etc., which is not particularly limited in this specification. Illustratively, the first period of time is 8:20-8:30, and the second period of time may be 8:10-8:40, or 8:15-8:35. Illustratively, the first time period is 7:10-7:20, and the second time period may be 7:00-7:30, or 7:05-7:25.

In an embodiment shown, the target area may be an entire city, a certain district or county in a large-scale city, a business center, a plurality of streets, etc., which is not particularly limited in this specification.

In an illustrated embodiment, the traffic simulation result of the target area in the second period may include: the passenger carrying states and positions of the service vehicles in the target area in the second period, and the dynamic change process of traffic flow, average speed, average passing time, traffic light condition, traffic accident condition and the like of all roads in the target area in the second period. For example, the passenger status and location of the plurality of service vehicles within the target area during the second period may include: dynamic changes in the number and location of passengers for each service vehicle within the target area over the second period. In one illustrated embodiment, a service vehicle with a passenger number of 0 may be matched as an idle vehicle to a corresponding carpool order. In an illustrated embodiment, a service vehicle that is not fully loaded (e.g., a service vehicle with a remaining seat of 1) may also participate in a subsequent ride share as an idle vehicle, etc., as this description is not specifically limited.

Again, the data such as the passenger carrying state and the position of the service vehicle, and the traffic flow included in the traffic simulation result are all data obtained by simulating the traffic simulation model before the actual travel of the passengers, and are not actual road traffic data.

In one illustrated embodiment, the training process of the traffic simulation model may be as follows:

(1) And constructing an initial traffic simulation model based on the multi-mode traffic network data and travel demand data in the research area.

In an embodiment, the road network data may include network link topology, speed limit of road segments, number of lanes, start point coordinates and end point coordinates of road segments, etc., which are not particularly limited in this specification. In an illustrated embodiment, the travel demand data may include departure time and start point coordinates, end point coordinates, etc. of a plurality of users, which are not particularly limited in this specification. For example, travel demand data may include travel records collected by a plurality of mobile base stations located within a research area (e.g., all road networks of city a). Illustratively, the road network data may be derived from an open source dataset opentreetmap. For example, road traffic conditions such as road segment speed limit and number of lanes may be constituted by the traffic stop detection data and the floating car data, etc., which are not particularly limited in this specification.

In an illustrated embodiment, the initial traffic simulation model may be a simulation model built based on open source simulation software MATSim. Based on the initial traffic simulation model, a travel plan of the user can be deduced in the simulation, and a traffic track, travel time and the road traffic state of the user are obtained.

(2) And correcting the initial traffic simulation model to obtain a corrected traffic simulation model.

In an embodiment shown, the main road in the study area can be selected as a corrected road section, and the road flow and the road travel time obtained by simulation for the corrected road section are compared with the actual data of the corrected road section. And (3) reducing standard root mean square errors generated by the road flow, the road trip time consumption and the like obtained by simulation of the corrected road section and actual data to be below target values (for example, 15-20%) by adjusting the key origin destination OD (origin-destination) demand and road parameters (such as speed limit, traffic capacity and the like), thereby completing the correction of the initial traffic simulation model and obtaining the corrected traffic simulation model.

The corrected section may include, for example, a highway within the investigation region, a portion of a major ground road, etc., as this specification is not particularly limited.

In an embodiment, the present specification may specifically train to obtain the traffic simulation model through a stand-alone training mode or a distributed training mode, and the like, and the present specification is not limited thereto. It should be noted that the foregoing training process is merely illustrative, and in some possible embodiments, the present disclosure may also train to obtain the traffic simulation model by using any other possible simulation software or method besides MATSim, which is not limited in this disclosure.

Step S103, based on the order information of each of the plurality of car sharing orders and the traffic simulation result, matching at least one car sharing order corresponding to the plurality of car sharing orders for idle vehicles in the plurality of service vehicles in the target area.

In an embodiment, after obtaining the order information of the plurality of car sharing orders in the first period and the traffic simulation result of the target area in the second period, the computing device may obtain the respective driving information of the plurality of car sharing orders based on the order information of the plurality of car sharing orders in the first period and the traffic simulation result of the target area in the second period.

In an illustrated embodiment, the travel information for each of the carpool orders may include one or more of the following: road section information of at least one traveling road section through which each carpool order passes in the target area, a traveling start time and a traveling duration corresponding to each of the at least one traveling road section. By way of example, the link information of each traveling link may include a link name, an average vehicle speed and a transit time of the link, a start point coordinate and an end point coordinate of the link, the number of lanes of the link, speed limit information, the number of red road lamps, and a traffic flow, etc., which are not particularly limited in this specification.

It is emphasized again that the running information of each car pooling order is the running information further predicted based on the traffic condition obtained by simulation before the actual travel of the passengers, and is not the running information in the actual running process.

It should be understood that the driving information of each car sharing order is obtained by only considering the reserved travel time, the starting place and the destination of each order in a simulation manner before the car sharing with other car sharing orders, and is equivalent to the driving information corresponding to the driving of each order individually.

In an embodiment, the computing device may input order information of each of the plurality of car sharing orders in the first period and a traffic simulation result of the target area in the second period to a travel simulation model trained in advance, so as to obtain travel information of each of the plurality of car sharing orders.

In an illustrated embodiment, the computing device may further train to obtain the trip simulation model based on the traffic simulation model obtained by training as described above. The travel simulation model can be used for simulating the daily travel requirements of urban traffic, reserved travel requirements (including carpooling requirements) and the time-space evolution process of service vehicle states, and the like.

In an illustrated embodiment, the computing device may obtain the reserved trip order (including the carpool order) data and the service vehicle data, and add the reserved trip order data and the service vehicle data as additional dynamic OD to the traffic simulation model for simulation, thereby obtaining the trip simulation model. For example, the service vehicle state and position may be initialized first, that is, the service vehicle data may include initial passenger states and initial positions of a plurality of service vehicles in the target area, and then the car pooling order data and the service vehicle data are input as training data to the traffic simulation model, so that the trip simulation model is trained.

In an illustrated embodiment, the carpool order data includes order information for each of a plurality of carpool orders within a plurality of subintervals included in the target period. For example, the carpool order data may include order information for a plurality of carpool orders contained by each of 12 slots (one slot every 10 minutes) in the early peak 7:00-9:00. By way of example, the car pooling order data may include order information of all the car pooling orders of the early peak in the day, week or month, and the like, which is not particularly limited in this specification.

Further, in an embodiment, the average time consumption of each road segment through which the plurality of carpool orders pass may be calculated based on the driving information of each of the plurality of carpool orders. In an illustrated embodiment, if the number of the carpool orders passing through the road section i is J, the traveling information of the J carpool orders on the road section i may be as follows:

wherein,,

for the driving information of J carpool orders on road section i, d _j For the driving starting time t of the J-th car sharing order entering the road section i _j The travel duration (or time consumption) for the j-th carpool order to pass through the road section i. Wherein J is an integer greater than or equal to 1, and less than or equal to J.

Based on this, the computing device may further calculate the average time consumption of the J carpool orders through the road segment i within the specified time window

The following is shown:

in an embodiment shown, the predetermined time window may be a preset maximum waiting time of the passenger, for example, 5 minutes or 10 minutes, etc., which is not particularly limited in this specification.

Further, the computing device may match a free vehicle of the plurality of service vehicles within the target area with a corresponding at least one of the plurality of carpool orders based on the simulated travel information of each of the plurality of carpool orders within the first period.

In an illustrated embodiment, the computing device may match at least one of the plurality of pickup orders that is most appropriate for an idle vehicle of the plurality of service vehicles within the target area based on the respective travel information of the plurality of pickup orders within the first time period and a preset matching rule (e.g., a rule that minimizes a sum of travel times of all pickup vehicles).

In an illustrated embodiment, the computing device may calculate the carpool index for any two of the plurality of carpool orders based on the travel information for each of the plurality of carpool orders over the first period. The computing device may then match a corresponding at least one of the plurality of car pooling orders for an idle vehicle of the plurality of service vehicles within the target area based on the pooling index of any two of the plurality of car pooling orders and a preset matching rule.

In an illustrated embodiment, the carpool index corresponding to any two carpool orders may include a sum of delay times corresponding to any two carpool orders. For example, the delay time may include an waiting time and a driving delay time generated after the carpooling of each order, and so on. The travel delay time is usually generated by the vehicle detouring to pick up another passenger or detouring to finish another passenger.

It should be noted that, when the same carpool order performs carpool index calculation with different carpool orders, that is, when the same carpool order performs carpool with different carpool orders, delay time of the carpool orders may be different. For example, taking 50 carpool orders in the above 7:00-7:10 as an example, when calculating the carpool index of the 1 st carpool order and the 2 nd carpool order, the delay time of the 1 st carpool order may be 10 minutes, and the delay time of the 2 nd carpool order may be 5 minutes (i.e., the carpool index of the 1 st carpool order and the 2 nd carpool order is 15 minutes); when calculating the carpool index of the 1 st carpool order and the 3 rd carpool order, the delay time of the 1 st carpool order may be 4 minutes, and the delay time of the 3 rd carpool order may be 6 minutes (i.e., the carpool index of the 1 st carpool order and the 3 rd carpool order is 10 minutes).

In an illustrated embodiment, the computing device may calculate the split index of any two of the plurality of split orders based on the respective travel information of the plurality of split orders over the first period and in combination with one or more of the respective order information of the plurality of split orders, the location information of the free vehicles in the plurality of service vehicles in the target area, the road network topology of the target area, and the like.

In an illustrated embodiment, the computing device may specifically calculate the carpool index of any two of the plurality of carpool orders based on the calculated average time consumption of each road segment traversed by the plurality of carpool orders, and in combination with one or more of order information of each of the plurality of carpool orders, location information of idle vehicles in the plurality of service vehicles in the target area, road network topology of the target area, and the like.

For example, the computing device may construct the path planning module based on the calculated average time consumption of the road segments of each road segment traversed by the plurality of car pooling orders, the respective order information of the plurality of car pooling orders, the location information of the idle vehicles in the plurality of service vehicles in the target area, and the road network topology of the target area. Through the path planning module, the CH (Contraction Hierarchies) algorithm is utilized to calculate the carpool index of any two carpool orders in the plurality of carpool orders. The CH algorithm is an acceleration technique for finding the shortest path in the graph, and will not be described in detail here. In an illustrated embodiment, the computing device may also calculate the carpool index using any other possible algorithm besides the CH algorithm, which is not specifically limited in this specification.

In an illustrated embodiment, when the computing device matches at least one corresponding carpool order for the idle vehicles in the target area based on the carpool index, the computing device may first combine multiple carpool orders based on the carpool index to obtain multiple carpool combinations, and then match each carpool combination with an appropriate idle vehicle. Wherein, each carpool combination can include at least one carpool order.

In an illustrated embodiment, the computing device may determine a target carpool scheme among the plurality of carpool schemes based on the calculated carpool index for any two of the plurality of carpool orders. The target carpool scheme can comprise a plurality of carpool combinations which are more suitable, and each carpool combination can comprise one or more carpool orders. And under the target carpooling scheme, the sum of carpooling indexes of the carpooling orders is minimum, namely the sum of delay time generated after carpooling of the carpooling orders is minimum.

It will be appreciated that not all of the carpool orders can be consolidated with other carpool orders, taking into account dynamic changes in the travel demand of the passenger and waiting times of the passenger, so the computing device may not be able to carpool the passenger any more, but rather to match the passenger with a dedicated free vehicle for pickup service, with consent from the passenger. Therefore, some of the plurality of car sharing combinations included in the target car sharing scheme may include only one car sharing order, and the subsequent computing device will match one idle car for the one car sharing order individually, so as to flexibly utilize traffic resources and meet the actual demands of users.

In an embodiment, the computing device may obtain a corresponding carpool index matrix based on the calculated carpool indexes of any two carpool orders in the plurality of carpool orders, and construct an integer linear programming model (1) shown below based on the carpool index matrix to solve a suitable order grouping scheme (i.e., the target carpool scheme) so as to minimize the sum of carpool indexes of all orders. Wherein the decision variable is a carpool combination. For example, the computing device may employ a Gurobi optimization solver to solve for the appropriate order grouping scheme. By way of example, any other possible method than the Gurobi optimization solver may be used to solve the above-described suitable order grouping scheme, as this specification is not limited in detail.

Wherein s is _mn A carpool index between a carpool order m and a carpool order n is represented; x is x _mn Decision variables representing 0 or 1, x _mn A value equal to 1 indicates that the carpool order m and the carpool order n can carpool, and vice versa, x _mn A difference of 1 indicates that the carpool order m and the carpool order n cannot be carpooled; c represents the vehicle capacity, or passenger capacity; m is the number of the plurality of carpooling orders in the first period, and M is an integer greater than 1.

Further, after the above-mentioned suitable target carpool scheme is determined, the computing device may match, for a plurality of idle vehicles in a plurality of service vehicles in the target area, corresponding carpool combinations in a plurality of carpool combinations included in the target carpool scheme, so as to minimize a sum of travel times of the plurality of idle vehicles after the plurality of idle vehicles receive the order.

In an illustrated embodiment, the computing device may construct the following assignment model (2) to solve for the appropriate matching scheme based on the above-solved combinations of multiple tiles to minimize the sum of travel times after all matched idle vehicle orders. The decision variable is a vehicle travel plan for the empty vehicle-to-consist combination (or a consist order). For example, the computing device may solve the above-described suitable matching scheme using the hungarian algorithm. By way of example, any other possible algorithm than the hungarian algorithm may be used to solve the above-mentioned suitable matching scheme, which is not specifically limited in this specification.

Wherein r is _vw The travel time between the vehicle v and the destination w is represented. Wherein u is _vw Decision variable which is 0 or 1, u _vw Equal to 1 indicates that the vehicle v is traveling to the destination w, whereas u _vw A value of not equal to 1 indicates that the vehicle v is not traveling to the destination w. Wherein V is the number of idle vehicles in the target area, and V is an integer greater than or equal to 1. Wherein W is a plurality of spellings in a first periodThe number of destinations of the vehicle order, W, is an integer greater than 1. Generally, the number of destinations is equal to the number of car pooling orders, and in some possible embodiments, there may be two destinations for one car pooling order based on the actual needs of the passengers, etc., which is not specifically limited in this specification.

Further, in an embodiment, after solving to obtain the suitable matching schemes of the multiple assembly and the idle vehicles, the computing device may further simulate the connection and delivery of the matched vehicles based on the travel simulation model, so as to simulate the order completion situation of the real vehicles, and obtain the driving end time and the driving end position of each vehicle after receiving the order.

It should be appreciated that after receiving a bill, the matched idle vehicles may update their passenger carrying status to "carried passenger", or "in service", i.e. no longer be idle vehicles; after receiving all the passengers of the carpooling orders in the finished vehicle, the passenger carrying state of the carpooling vehicle can be updated to be 'unloaded', or 'to be served', namely, the carpooling vehicle is taken as an idle vehicle again, and the carpooling matching in the subsequent period can be participated next.

In an illustrated embodiment, the computing device may update the traffic simulation results for the target area based on the above-described simulation results for the docking and delivery of the matched vehicle, including updating information about the passenger status and location of the service vehicle. Further, the computing device may update the car pooling order (e.g., obtain order information of a plurality of car pooling orders in a next period adjacent to the first period) and service vehicle information in the travel simulation model, and complete the car pooling matching of all the car pooling orders in the entire simulation period (e.g., the early peak period of 7:00-9:00) by repeatedly executing the steps S101-S104.

For example, for 50 car pooling orders within a 7:00-7:10 period, the computing device may solve for 25 car pooling combinations corresponding to the 50 car pooling orders, wherein 10 car pooling combinations comprise 3 car pooling orders, 5 car pooling combinations comprise 2 car pooling orders, and 10 car pooling combinations comprise 1 car pooling order. Further, the computing device may take over services for the 25 splice groups that each match one of the idle service vehicles, i.e., a total of 25 idle service vehicles. Further, the computing device can simulate dynamic driving conditions such as connection and delivery of the 25 service vehicles after receiving the orders through the travel simulation model so as to simulate the order completion condition of the real vehicles, and records the task end time and position of each service vehicle obtained through simulation.

In one illustrated embodiment, the vehicle ending the mission among the 25 service vehicles may participate in the match of the ride share during a period of time after the end of the mission. Still exemplified are 12 periods within the early peak period of 7:00-9:00 described above. If the simulation results in the last passenger in the 7:22 finished vehicle for vehicle A in the 25 service vehicles, then vehicle A may participate as an idle vehicle in a carpool match for a plurality of carpool orders over a period of 7:20-7:30. For example, if the simulation results in the last passenger in the 7:37 finished vehicle for vehicle B in the 25 service vehicles, the vehicle B may participate as an idle vehicle in the matching of multiple carpool orders in the 7:30-7:40 period, it should be understood that if the vehicle B is more remote in location when finishing the last order, the vehicle B may not be able to match any of the multiple carpool orders in the 7:30-7:40 period, the vehicle B may then participate in the matching of multiple carpool orders in the 7:40-7:50 period, and so on.

In conclusion, the method and the system integrate the problem of the reserved trip dynamic supply and demand matching optimization of the large-scale city with the traffic simulation based on the idea of model integration, can efficiently and accurately estimate the dynamic traffic state required by dynamic car sharing matching on the scale of a large-scale road network, and improve the authenticity and reliability of reserved trip dynamic supply and demand matching optimization in large-scale city application. In addition, the application aims to provide a generalized idea and flow for fusing the supply and demand matching optimization algorithm with the traffic simulation, and the method has good expansibility.

Referring to fig. 2, fig. 2 is a schematic flow chart of a carpooling method based on traffic simulation according to an exemplary embodiment. The car sharing method and the effect thereof provided by the application will be further elaborated with reference to fig. 2.

As shown in fig. 2, period T _z One of the periods (for example, the first period described above) within the entire simulation period, which may be divided into a total of Z periods, Z being an integer greater than or equal to 1 and less than or equal to Z, Z being an integer greater than 1, may be used. Illustratively, still taking the above-described early peak period (7:00-9:00) as an example, Z is equal to 12, then period T _z May be 7:20-7:30 (z=3), or 7:40-7:50 (z=5), or 8:10-8:20 (z=8), etc. throughout the early peak period. In an illustrated embodiment, if period T _z For the first period (i.e., z=1) in the entire simulation period, e.g., 7:00-7:10, the computing device may initialize various data in the trip simulation model, such as the passenger state and location of the service vehicle, before starting the traffic simulation.

As shown in fig. 2, the computing device acquires a period T _z Multiple car pooling orders within and to time period T _z Order information of each of the plurality of car pooling orders in the system is input into a travel simulation model trained in advance. Further, the computing device may be associated with the period T _z And the traffic simulation results in the corresponding relevant time period (such as the second time period) are input into a travel simulation model trained in advance, so that the driving information of the plurality of car pooling orders under the traffic simulation results is obtained through simulation. Illustratively, in a period T _z For example, 7:20-7:30, and period T _z The corresponding correlation period may be 7:10-7:40, or may be 7:15-7:35, etc., as this specification is not specifically limited.

As shown in fig. 2, the computing device outputs a period T of time for the trip simulation module to output _z The running information of each of the plurality of car pooling orders in the system is input to a supply and demand matching module, so that the most suitable service vehicles are matched for the plurality of car pooling orders respectively, and the matching results of the plurality of car pooling orders are output. In one illustrated embodiment, the supply and demand matching module may be a functional module in a processor of the computing device that integrates the building of the carpool index matrix, the integer linear programming model, and the fingers described aboveAnd dispatching a model to solve the function of a proper car sharing matching scheme.

As shown in fig. 2, the computing device obtains a period T by solving through a supply and demand matching module _z After the matching results of the plurality of car pooling orders in the simulation period, whether the current period is the last period in the simulation period at this time or not can be judged, namely whether Z is equal to Z or not is judged.

In an illustrated embodiment, if Z is equal to Z, then the period T is output ₁ To period T _Z And (3) matching results of all the car sharing orders in the car sharing system, and ending the car sharing matching based on the traffic simulation. For example, still taking the above Z equal to 12 as an example, if z=12, the computing device directly outputs the period T ₁ To period T ₁₂ Matching results of all the car sharing orders (for example, 1000 car sharing orders) in the interior (7:00-9:00) are finished, and the car sharing matching based on the traffic simulation is finished.

In an illustrated embodiment, if Z is not equal to Z, the computing device then enters into the carpool matching of the next period, updates the order information and the traffic simulation result of the current period, and obtains the carpool matching results of the plurality of carpool orders of the current period through the travel simulation model and the supply and demand matching module until z=z, thereby completing the carpool matching for all the carpool orders in the whole simulation period. For example, still taking the above Z equal to 12 as an example, if z=2, the computing device may then execute the process for the next period (period T ₃ ) A car pool match for a plurality of car pool orders within, comprising: acquisition period T ₃ Multiple orders within, acquisition period T ₃ The corresponding traffic simulation result of the relevant time period is used for obtaining the time period T through the travel simulation model and the supply and demand matching module ₃ The results of the matching of the carpools for the plurality of carpool orders within then the computing device then proceeds to execute the matching for the next time period (time period T ₄ ) Car-sharing matches for multiple car-sharing orders within, and so on, until z=12.

Therefore, the reservation travel dynamic supply and demand matching based on the traffic simulation is completed through continuous iterative interaction of the traffic simulation and the matching algorithm, so that waiting time and detour time of passengers in the car sharing process are greatly reduced, and the car sharing service quality is improved.

For example, 1000 carpool orders are included in the early peak (7:00-9:00), and each carpool order actually includes 1 person as an example, the carpool grouping result of the 1000 carpool orders may be as shown in fig. 3, and fig. 3 is a schematic diagram of a carpool combination provided by an exemplary embodiment.

As shown in fig. 3, the period of 7:00-7:30 contains 251 carpool orders, and the carpool grouping result of the 251 carpool orders includes: 94 order combinations containing only 1 order, 38 order combinations containing 2 orders, and 27 order combinations containing 3 orders. Specifically, if the early peak (7:00-9:00) is divided into 12 periods, the order grouping result in 7:00-7:30 shown in fig. 3 may be the order grouping result integrating all orders included in 3 periods of 7:00-7:10,7:10-7:20 and 7:20-7:30, and the following periods of 7:30-8:00, 8:00-8:30 and 8:30-9:00 will not be repeated.

As shown in fig. 3, the period of 7:30-8:00 contains 249 carpool orders, and the carpool grouping result of the 249 carpool orders includes: 87 order combinations containing only 1 order, 33 order combinations containing 2 orders, and 32 order combinations containing 3 orders.

As shown in FIG. 3, 258 carpool orders are included in the 8:00-8:30 period, and the carpool grouping result of the 258 carpool orders comprises: 99 order combinations containing only 1 order, 30 order combinations containing 2 orders, and 33 order combinations containing 3 orders.

As shown in fig. 3, the period of 8:30-9:00 contains 242 carpool orders, and the carpool grouping result of the 242 carpool orders includes: 96 order combinations containing only 1 order, 25 order combinations containing 2 orders, and 32 order combinations containing 3 orders.

As shown in fig. 3, considering factors such as waiting time of passengers and delay of travel time in the car, most of the car sharing orders cannot be used for sharing cars with other car sharing orders at last, and the rest car sharing orders can be used for sharing cars with other 1 car sharing orders or 2 car sharing orders.

By way of example, taking 12 time slots within the early peak (7:00-9:00) as an example, the computing device may perform a traffic simulation based car pool match for each time slot for 2.5 minutes, then it may take 30 minutes to complete a car pool match for all orders (e.g., 1000 car pool orders) within the 12 time slots. It should be understood that, based on the hardware performance of the computing device and the different adopted car sharing matching algorithm, the specific execution time of the traffic simulation and the car sharing matching algorithm may also be different, for example, may be 2 minutes or 3 minutes, etc., which is not specifically limited in this specification.

Referring to fig. 4, fig. 4 is a schematic diagram of empty cars and order numbers without a pooling scene according to an exemplary embodiment. As shown in fig. 4, in a scenario where no pooling is allowed (i.e., vehicle capacity c is equal to 1 as described above), at least 260 service vehicles are required to fulfill all 1000 orders within the early peak (7:00-9:00).

Referring to fig. 5, fig. 5 is a schematic diagram of empty cars and order numbers in a carpool scene according to an exemplary embodiment. As shown in fig. 5, in the carpooling scene, by the carpooling method based on traffic simulation provided by the specification, the requirements of all 1000 orders in the early peak (7:00-9:00) can be met by only 210 service vehicles, so that the scale of the reserved travel service fleet in a large-scale city can be effectively reduced, the running efficiency of the fleet is improved, and traffic jam is prevented.

In summary, according to the traffic simulation method and the traffic simulation device, the traffic simulation result of the target area in a period of time is obtained through simulation by means of the traffic simulation technology, and the dynamic traffic condition in the period of time is obtained. Then, the method and the device can acquire the driving condition of each car pooling order in the time under the current traffic simulation result. Further, the present application may match at least one of the most appropriate carpool orders for a free vehicle of the plurality of service vehicles within the target area based on the driving condition of each carpool order under the current traffic simulation result. Therefore, the method and the device provide effective and reliable reference for reasonable matching of the carpool order and the service vehicle through the traffic simulation technology, so that waiting time and detour time of passengers in the carpool process are reduced, the quality of carpool service is improved, further, the operation efficiency of a traffic system can be improved, and the problem of urban traffic jam is effectively solved. It should be noted that, in the prior art, the traffic simulation technology is mostly used for the purpose of traffic control or the effect test of traffic control algorithms, and the application combines the reserved car sharing dynamic supply and demand matching algorithm with the traffic simulation technology, so as to fully play the roles of the traffic simulation technology in the aspects of large-scale road network calculation, dynamic traffic supply and demand deduction and the like.

Corresponding to the implementation of the method flow, the embodiment of the specification also provides a carpooling device based on traffic simulation. Referring to fig. 6, fig. 6 is a schematic structural diagram of a carpool device based on traffic simulation according to an exemplary embodiment. The apparatus 30 may be applied to a computing device, such as a server of taxi taking software. As shown in fig. 6, the apparatus 30 includes:

a first obtaining unit 301, configured to obtain order information of each of a plurality of carpool orders in a first period;

a second obtaining unit 302, configured to obtain a traffic simulation result of the target area in a second period based on a traffic simulation model obtained by training in advance; the second period of time includes the first period of time; the traffic simulation result comprises the dynamic traffic condition of the target area in the second period obtained through simulation;

and a matching unit 303, configured to match at least one corresponding carpool order in the plurality of carpool orders for idle vehicles in the plurality of service vehicles in the target area based on order information of each of the plurality of carpool orders and the traffic simulation result.

In an illustrated embodiment, the second period includes the first period, and a period of a previous preset duration and a period of a subsequent preset duration adjacent to the first period.

In an illustrated embodiment, the order information for each of the plurality of carpool orders includes: the reserved travel time, the starting place position and the destination position of each carpool order; the reserved travel time of each carpooling order is within the first period.

In an illustrated embodiment, the traffic simulation results for the target area over the second period of time include: the passenger carrying states and positions of the plurality of service vehicles in the target area in the second period, and average vehicle speeds and passing time lengths of the plurality of road sections in the second area, which correspond to each other in the second period.

In an illustrated embodiment, the matching unit 303 is specifically configured to:

based on the order information of each of the plurality of carpool orders and the traffic simulation result, obtaining the running information of each of the plurality of carpool orders; the travel information for each of the carpool orders includes one or more of the following: road section information of at least one traveling road section through which each carpool order passes in the target area, and a traveling start time and a traveling duration corresponding to each road section in the at least one traveling road section;

And matching at least one corresponding carpool order in the plurality of carpool orders for idle vehicles in the plurality of service vehicles in the target area based on the running information of each carpool order and a preset matching rule.

and inputting order information of each of the plurality of car pooling orders in the first period and traffic simulation results of the target area in the second period into a travel simulation model trained in advance to obtain running information of each of the plurality of car pooling orders.

calculating the carpool index of any two carpool orders in the plurality of carpool orders based on the respective driving information of the plurality of carpool orders; the carpool indexes corresponding to the arbitrary two carpool orders comprise the sum of delay time corresponding to the arbitrary two carpool orders;

and matching at least one corresponding carpool order in the plurality of carpool orders for idle vehicles in the plurality of service vehicles in the target area based on carpool indexes of any two carpool orders in the plurality of carpool orders and a preset matching rule.

In one illustrated embodiment, the delay time includes an waiting time and a driving delay time generated after the carpooling.

calculating delay time corresponding to any two of the plurality of car pooling orders based on the running information of each of the plurality of car pooling orders, the order information of each of the plurality of car pooling orders, the position information of idle vehicles in the plurality of service vehicles in the target area and the road network topology of the target area;

and determining the sum of the delay time corresponding to each of the two car sharing orders as the car sharing index of the two car sharing orders.

determining a target carpool scheme among a plurality of carpool schemes based on carpool indexes of any two carpool orders in the plurality of carpool orders; the target carpool scheme comprises a plurality of carpool combinations, each carpool combination comprises one or more carpool orders; under the target carpooling scheme, the sum of carpooling indexes of the plurality of carpooling orders is minimum;

and respectively matching a plurality of idle vehicles in the plurality of service vehicles in the target area with corresponding car sharing combinations in the plurality of car sharing combinations.

In an illustrated embodiment, the apparatus 30 further comprises:

and the updating unit 304 is configured to simulate, based on the travel simulation model, a driving end time and a driving end position of the plurality of idle vehicles after receiving the order, and update a traffic simulation result of the target area.

In an illustrated embodiment, the apparatus 30 further comprises:

a third acquiring unit 305 for acquiring the carpooling order data and the service vehicle data; the car pooling order data comprise order information of each of a plurality of car pooling orders in a plurality of subintervals contained in a target period, and the service vehicle data comprise initial passenger carrying states and initial positions of a plurality of service vehicles in a target area;

and the training unit 306 is configured to input the car pooling order data and the service vehicle data as training data to the traffic simulation model, and train to obtain the trip simulation model.

The implementation process of the functions and roles of the units in the above device 30 is specifically described in the above corresponding embodiments of fig. 1 to 5, and will not be described in detail herein. It should be understood that the above-mentioned apparatus 30 may be implemented by software, or may be implemented by hardware or a combination of hardware and software. Taking software implementation as an example, the device in a logic sense is formed by reading corresponding computer program instructions into a memory through a CPU (Central Process Unit, central processing unit) of the device. In addition to the CPU and the memory, the device in which the above apparatus is located generally includes other hardware such as a chip for performing wireless signal transmission and reception, and/or other hardware such as a board for implementing a network communication function.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the units or modules may be selected according to actual needs to achieve the purposes of the present description. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

The apparatus, units, modules illustrated in the above embodiments may be implemented in particular by a computer chip or entity or by a product having a certain function. A typical implementation device is a computer, which may be in the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or a combination of any of these devices.

Corresponding to the method embodiments described above, embodiments of the present specification also provide a computing device. Referring to fig. 7, fig. 7 is a schematic structural diagram of a computing device according to an exemplary embodiment. By way of example, the computing device 1000 may be a server of taxi taking software. As shown in fig. 7, the computing device 1000 may include a processor 1001 and memory 1002, and may further include an input device 1004 (e.g., keyboard, etc.) and an output device 1005 (e.g., display, etc.). The processor 1001, memory 1002, input devices 1004, and output devices 1005 may be connected by a bus or other means. As shown in fig. 7, the memory 1002 includes a computer-readable storage medium 1003, which computer-readable storage medium 1003 stores a computer program executable by the processor 1001. The processor 1001 may be a general purpose central processing unit, a microprocessor, or an integrated circuit for controlling the execution of the above method embodiments. The processor 1001 may execute the steps of the traffic simulation-based carpooling method in the embodiment of the present specification when running the stored computer program, including: acquiring order information of each of a plurality of carpooling orders in a first period; acquiring a traffic simulation result of the target area in a second period based on a traffic simulation model obtained through pre-training; the second period of time includes the first period of time; the traffic simulation result comprises the dynamic traffic condition of the target area in the second period obtained through simulation; based on the order information of each of the plurality of carpool orders and the traffic simulation result, obtaining the running information of each of the plurality of carpool orders; and matching at least one corresponding carpool order in the plurality of carpool orders for idle vehicles in the plurality of service vehicles in the target area based on the respective driving information of the plurality of carpool orders and a preset matching rule, and the like.

For a detailed description of each step of the traffic simulation-based carpooling method, please refer to the previous contents, and a detailed description thereof will not be provided herein.

Corresponding to the above method embodiments, embodiments of the present description further provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the traffic simulation based carpooling method in the embodiments of the present description. Please refer to the above description of the corresponding embodiments of fig. 1-5, and detailed descriptions thereof are omitted herein.

The foregoing description of the preferred embodiments is provided for the purpose of illustration only, and is not intended to limit the scope of the disclosure, since any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the disclosure are intended to be included within the scope of the disclosure.

In a typical configuration, the terminal device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data.

Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Moreover, embodiments of the present description may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Claims

1. A carpooling method based on traffic simulation, the method comprising:

2. The method of claim 1, the second period comprising the first period, and a period of a previous preset duration and a period of a subsequent preset duration adjacent to the first period.

3. The method of claim 1, the order information for each of the plurality of car pooling orders comprising: the reserved travel time, the starting place position and the destination position of each carpool order; the reserved travel time of each carpooling order is within the first period.

4. The method of claim 1, the traffic simulation results for the target area over a second period of time comprising: the passenger carrying states and positions of the plurality of service vehicles in the target area in the second period, and average vehicle speeds and passing time lengths of the plurality of road sections in the second area, which correspond to each other in the second period.

5. The method of claim 1, the matching a corresponding at least one of the plurality of car pooling orders for an idle vehicle of a plurality of service vehicles within the target area based on order information of each of the plurality of car pooling orders and the traffic simulation result, comprising:

6. The method of claim 5, wherein the obtaining the driving information of each of the plurality of car pooling orders based on the order information of each of the plurality of car pooling orders and the traffic simulation result comprises:

7. The method of claim 6, the matching a corresponding at least one of the plurality of car pooling orders for an idle vehicle of the plurality of service vehicles within the target area based on the respective travel information of the plurality of car pooling orders and a preset matching rule, comprising:

calculating the carpool index of any two carpool orders in the plurality of carpool orders based on the respective driving information of the plurality of carpool orders; the carpool indexes corresponding to the arbitrary two carpool orders comprise the sum of delay time corresponding to the arbitrary two carpool orders; the delay time comprises waiting time and running delay time generated after the car is assembled;

8. The method of claim 7, the calculating a carpool index for any two of the plurality of carpool orders based on travel information for each of the plurality of carpool orders, comprising:

9. The method of claim 8, the matching a corresponding at least one of the plurality of taxi sharing orders for an idle vehicle of the plurality of service vehicles within the target area based on the taxi sharing index of any two of the plurality of taxi sharing orders and a preset matching rule, comprising:

10. The method of claim 9, the method further comprising:

and based on the travel simulation model, simulating to obtain the running end time and the running end position of the plurality of idle vehicles after order receiving, and updating the traffic simulation result of the target area.

11. The method of claim 6, the method further comprising:

acquiring car pooling order data and service vehicle data; the car pooling order data comprise order information of each of a plurality of car pooling orders in a plurality of subintervals contained in a target period, and the service vehicle data comprise initial passenger carrying states and initial positions of a plurality of service vehicles in a target area;

and inputting the carpooling order data and the service vehicle data as training data into the traffic simulation model to obtain the travel simulation model.

12. A traffic simulation-based carpool device, the device comprising:

the second acquisition unit is used for acquiring a traffic simulation result of the target area in a second period based on a traffic simulation model obtained through pre-training; the second period of time includes the first period of time; the traffic simulation result comprises the dynamic traffic condition of the target area in the second period obtained by simulation;

13. A computing device, comprising: a memory and a processor; the memory has stored thereon a computer program executable by the processor; the processor, when running the computer program, performs the method of any one of claims 1 to 11.

14. A computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any of claims 1 to 11.