Shared travel service compensation scheme determination method

Abstract

The invention discloses a shared travel service compensation scheme determination method, and relates to the technical field of traffic transportation, and the method comprises the steps: obtaining travel demand information; the acceptable additional riding time information corresponding to each passenger is obtained, and the acceptable additional riding time information is used for representing the relation between the acceptable additional riding time of the passenger and the compensation amount; according to the travel demand information and the acceptable extra riding time information, a target optimization model is constructed, and the target optimization model is used for representing a vehicle path planning scheme under the target of expected profit maximization and a compensation amount scheme corresponding to the passenger; the target optimization model is solved, a target vehicle path planning scheme and a target compensation amount scheme are obtained, and the target compensation amount scheme comprises the target compensation amount for each passenger. Therefore, the optimization effect and the service quality of the comprehensive shared transportation service can be improved.

Description

Technical Field

[0001] This application relates to the field of transportation technology, and in particular to a method for determining a compensation scheme for shared mobility services. Background Technology

[0002] With the development of society and the economy, people's demand for transportation is increasing. Based on this, integrated shared mobility (ISM) services are being applied more and more widely. ISM services can integrate freight transportation into passenger journeys, enabling shared travel for parcels and passengers, and improving the utilization rate of transportation resources.

[0003] In related technologies, integrated shared transportation services are typically optimized through vehicle route optimization. The problem with these technologies is that they do not consider the impact of additional travel time during cargo loading on passenger satisfaction, which is detrimental to improving the optimization effectiveness and service quality of integrated shared transportation services.

[0004] Therefore, the relevant technologies still need to be improved and developed. Summary of the Invention

[0005] The main purpose of this application is to provide a method for determining compensation schemes for shared mobility services, aiming to solve the technical problem in related technologies that only consider vehicle route optimization and do not consider the impact of additional travel time during cargo transportation on passenger satisfaction, which is not conducive to improving the optimization effect and service quality of integrated shared transportation services.

[0006] To achieve the above objectives, the first aspect of this application provides a method for determining a compensation scheme for shared mobility services, wherein the method includes:

[0007] Obtain travel demand information, including passenger travel demand and parcel delivery demand. Each passenger travel demand includes the passenger's departure point, destination, pickup time window, drop-off time window, and number of passengers. Each parcel delivery demand includes the parcel's pickup location, pickup time window, loading service time, drop-off location, drop-off time window, and unloading service time.

[0008] Obtain the acceptable additional travel time information for each of the above-mentioned passengers, wherein the acceptable additional travel time information is used to characterize the relationship between the acceptable additional travel time of the above-mentioned passengers and the compensation amount.

[0009] Based on the above travel demand information and the above acceptable additional travel time information, a target optimization model is constructed. The above target optimization model is used to characterize the vehicle route planning scheme and the corresponding compensation amount scheme for the above passengers under the goal of maximizing expected profit.

[0010] Solve the above objective optimization model to obtain the objective vehicle route planning scheme and the objective compensation amount scheme, wherein the objective compensation amount scheme includes the objective compensation amount for each of the above passengers.

[0011] Optionally, the above acceptable additional travel time information is an acceptable additional travel time curve;

[0012] The above-mentioned acquisition of acceptable additional travel time information for each of the aforementioned passengers includes:

[0013] Obtain the preset initial curve and the satisfaction survey data corresponding to each of the above passengers, wherein the satisfaction survey data represents the satisfaction of the above passengers with the extra travel time and the corresponding compensation amount.

[0014] Based on the aforementioned satisfaction survey data, the initial curve was adjusted to obtain the acceptable additional travel time curve for each of the aforementioned passengers.

[0015] Optionally, the above objective optimization model is a two-stage stochastic programming model;

[0016] The first stage of the two-stage stochastic programming model described above is used to determine the optimal compensation scheme to maximize expected profit;

[0017] The second stage of the two-stage stochastic programming model is used to determine the vehicle route planning scheme and the compensation amount scheme for each passenger based on the optimal compensation scheme determined in the first stage.

[0018] Optionally, the target optimization model constructed above based on the aforementioned travel demand information and the aforementioned acceptable additional travel time information includes:

[0019] Based on the above travel demand information and the above acceptable additional travel time information, a first-stage objective function and a second-stage objective function are constructed. The second-stage objective function is used to characterize the profit determined based on each vehicle route planning scheme and target compensation amount scheme under the above travel demand information and the above acceptable additional travel time information. The first-stage objective function is the expected value of the second-stage objective function.

[0020] Obtain the objective constraints, and construct the two-stage stochastic programming model based on the objective constraints, the objective function of the first stage, and the objective function of the second stage.

[0021] Optionally, the above target constraints include vehicle planning constraints and compensation amount constraints;

[0022] The above vehicle planning constraints include vehicle trip integrity constraints, flow conservation constraints, constraints on the number of service vehicles to meet demand, service time constraints, passenger capacity constraints, and freight capacity constraints.

[0023] The aforementioned compensation amount constraints are used to constrain the compensation amount for the aforementioned passengers based on the aforementioned acceptable additional travel time information.

[0024] Optionally, the above objective constraints may also include boundary constraints on decision variables.

[0025] Optionally, solving the above-mentioned objective optimization model to obtain the target vehicle route planning scheme and the target compensation amount scheme includes:

[0026] The two-stage stochastic programming model described above is processed using the sample average approximation method and transformed into a sample average approximation problem.

[0027] To address the aforementioned problem of approximating the average of samples, the compensation amount scheme and the vehicle routing scheme are iteratively solved to obtain the target vehicle routing scheme and the target compensation amount scheme.

[0028] A second aspect of this application provides a system for determining a compensation scheme for shared mobility services, wherein the system comprises:

[0029] The first information acquisition module is used to acquire travel demand information, which includes passenger travel demand and parcel delivery demand. Each passenger travel demand includes the passenger's departure point, destination, pickup time window, drop-off time window and number of passengers. Each parcel delivery demand includes the parcel's pickup location, pickup time window, loading service time, drop-off location, drop-off time window and unloading service time.

[0030] The second information acquisition module is used to acquire the acceptable additional travel time information for each of the above-mentioned passengers, wherein the acceptable additional travel time information is used to characterize the relationship between the acceptable additional travel time of the above-mentioned passengers and the compensation amount.

[0031] The model building module is used to build a target optimization model based on the above travel demand information and the above acceptable additional travel time information. The target optimization model is used to characterize the vehicle route planning scheme and the corresponding compensation amount scheme for the above passengers under the goal of maximizing expected profit.

[0032] The model solving module is used to solve the above-mentioned target optimization model to obtain the target vehicle route planning scheme and the target compensation amount scheme, wherein the above-mentioned target compensation amount scheme includes the target compensation amount for each of the above-mentioned passengers.

[0033] A third aspect of this application provides a smart terminal, which includes a memory, a processor, and a shared mobility service compensation scheme determination program stored in the memory and executable on the processor. When the shared mobility service compensation scheme determination program is executed by the processor, it implements any of the steps of the shared mobility service compensation scheme determination method.

[0034] A fourth aspect of this application provides a computer-readable storage medium storing a shared mobility service compensation scheme determination program, which, when executed by a processor, implements any of the steps of the shared mobility service compensation scheme determination method.

[0035] As can be seen from the above, in this application's solution, travel demand information is obtained, including passenger travel demand and parcel delivery demand. Each passenger travel demand includes the passenger's departure point, destination, pickup time window, drop-off time window, and number of passengers. Each parcel delivery demand includes the parcel's pickup location, pickup time window, loading service time, drop-off location, drop-off time window, and unloading service time. Information on the acceptable additional travel time for each passenger is obtained, representing the relationship between the passenger's acceptable additional travel time and the compensation amount. A target optimization model is constructed based on the travel demand information and the acceptable additional travel time information, representing the vehicle route planning scheme and the compensation amount scheme for each passenger under the objective of maximizing expected profit. The target optimization model is solved to obtain the target vehicle route planning scheme and the target compensation amount scheme, whereby the target compensation amount scheme includes the target compensation amount for each passenger.

[0036] Compared with existing technologies, the solution in this application does not only consider the vehicle route optimization problem, but also combines travel demand information and passengers' corresponding acceptable additional travel time information to construct a target optimization model. It comprehensively considers the impact of vehicle route planning and the additional travel time generated during cargo loading on passenger satisfaction, constructs a corresponding target optimization model, and optimizes and solves it, which is conducive to improving the optimization effect and service quality of integrated shared transportation services. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a flowchart illustrating a method for determining a compensation scheme for shared mobility services provided in an embodiment of this application;

[0039] Figure 2 This is a schematic diagram of a CSA method processing flow provided in an embodiment of this application;

[0040] Figure 3 This is a schematic diagram of the components of a shared mobility service compensation scheme determination system provided in an embodiment of this application;

[0041] Figure 4 This is a block diagram illustrating the internal structure of a smart terminal provided in an embodiment of this application. Detailed Implementation

[0042] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of this application with unnecessary detail.

[0043] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0044] It should also be understood that the terminology used in this application specification is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0045] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0046] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to classification." Similarly, the phrases "if determined" or "if classified to [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once classified to [the described condition or event]," or "in response to classification to [the described condition or event]."

[0047] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0048] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0049] Currently, integrated shared mobility (ISM) services are becoming increasingly widespread. Based on ISM services, existing passenger transport systems, such as ride-hailing, taxis, buses, and urban rail transit, can be utilized to meet urban parcel delivery needs. Integrating freight into passenger journeys not only helps reduce the number of freight vehicles, mileage, and related transport externalities, but also promotes the efficient use of existing passenger transport services and infrastructure, as passengers and goods can share the same road space and vehicles for part of their journey.

[0050] However, the ISM (Integrated Shared Transportation) service model presents challenges to the optimization process of service design, travel pricing, order allocation, and vehicle route planning. Related technologies typically optimize integrated shared transportation services through vehicle route optimization. Specifically, in the process of vehicle route optimization in these technologies, it is usually assumed that passengers have a fixed maximum travel time to avoid long detours to pick up other passengers or packages. However, in reality, passengers' acceptance of extended travel time due to "carpooling" between passengers and packages may largely depend on whether they receive travel fare compensation or discounts, and their tolerance for excess ride duration (ERD) may be related to the amount of compensation. From the perspective of service operators, revenue generated from package delivery can be shared with passengers in the form of compensation, achieving higher profitability while ensuring customer satisfaction.

[0051] Therefore, in this application, travel demand information is obtained, including passenger travel demand and parcel delivery demand. Each passenger travel demand includes the passenger's departure point, destination, pickup time window, drop-off time window, and number of passengers. Each parcel delivery demand includes the parcel's pickup location, pickup time window, loading service time, drop-off location, drop-off time window, and unloading service time. Information on the acceptable additional travel time for each passenger is obtained, representing the relationship between the passenger's acceptable additional travel time and the compensation amount. A target optimization model is constructed based on the travel demand information and the acceptable additional travel time information, representing the vehicle route planning scheme and the compensation amount scheme for each passenger under the objective of maximizing expected profit. The target optimization model is solved to obtain the target vehicle route planning scheme and the target compensation amount scheme, whereby the target compensation amount scheme includes the target compensation amount for each passenger.

[0052] Compared with existing technologies, the solution in this application does not only consider the vehicle route optimization problem, but also combines travel demand information and passengers' corresponding acceptable additional travel time information to construct a target optimization model. It comprehensively considers the impact of vehicle route planning and the additional travel time generated during cargo loading on passenger satisfaction, constructs a corresponding target optimization model, and optimizes and solves it, which is conducive to improving the optimization effect and service quality of integrated shared transportation services.

[0053] Exemplary methods

[0054] like Figure 1 As shown in the embodiment of this application, a method for determining a compensation scheme for shared mobility services is provided. Specifically, the method includes the following steps:

[0055] Step S100: Obtain travel demand information, wherein the travel demand information includes passenger travel demand and parcel delivery demand. Each passenger travel demand includes the passenger's departure point, destination, pickup time window, drop-off time window, and number of passengers. Each parcel delivery demand includes the parcel's pickup location, pickup time window, loading service time, drop-off location, drop-off time window, and unloading service time.

[0056] In one application scenario, the aforementioned travel demand information can be collected based on actual needs, such as by collecting user order information. In another application scenario, the needs of random passengers and parcel delivery can be considered, without further specific limitations.

[0057] This application embodiment further describes the above-mentioned method for determining the compensation scheme for shared mobility services based on a specific application scenario. Specifically, under the conditions of random passenger and parcel transportation demand, the optimal service compensation scheme is determined by considering the passengers' flexible tolerance for additional travel time, so as to maximize the expected profit of the service provider.

[0058] Specifically, an ISM service provider operates a fleet K of on-demand vehicles within a city area, offering daily door-to-door passenger and parcel transportation services, with parking available within the service area. On a typical operating day, the service provider receives a large number of transportation requests from customers, distributed spatially and temporally. Uncertain demand primarily refers to the uncertainty of known passenger and parcel demand input data. The realization of uncertain demand scenarios is represented by ω (i.e., travel demand information), which can be viewed as a set of random variables consisting of passenger ride requests and parcel delivery requests. Each passenger ride request (i.e., passenger ride demand) is associated with a departure point, destination, pickup time window, drop-off time window, and number of passengers, while each parcel delivery request (i.e., including delivery requests) has a pickup location, pickup time window, loading service time, drop-off location, drop-off time window, and unloading service time. Let... and These represent the passenger's departure point and destination, respectively. and These indicate the pickup and delivery locations for the package, respectively. For ease of representation, they are arranged as follows: and The index of the sequentially arranged positions. (With starting point) The destination of a passenger or package can be determined using location i+σ. ω It is represented as , where σ is the σ value. ω The total number of passenger and package requests. For simplicity, the origin / pickup location index of the passenger / package request is also used to represent the corresponding passenger / package request. Additionally, passenger / package... The requested pickup or parcel collection time window is [e] i ,l i ], where e i and l i These represent the earliest pick-up or pickup time and the latest drop-off or delivery time, respectively. Correspondingly, passenger / parcel requests... The time window for dropping off or delivering passengers is represented as .ask The number of passengers is expressed as ask The number of packages is expressed as Package Request The service durations for loading and unloading are respectively denoted by δ. i and express.

[0059] A vehicle can simultaneously serve multiple passenger and parcel transport requests, depending on the vehicle's (k∈K) capacity for passengers and parcels, respectively. and This indicates that, in addition to carpooling between passengers, this application embodiment also allows for "carpooling" between passengers and packages, so that packages can be transported by idle vehicles and vehicles already serving passengers. When there are passengers on board, the vehicle can detour to pick up other passengers or packages. From the request... The income obtained is used in R i This indicates that if a request is denied service, a penalty P will be incurred. i The travel time and cost from one location i to another location j are represented by t. ij and κ ij express.

[0060] Step S200: Obtain the acceptable additional travel time information for each of the above-mentioned passengers, wherein the acceptable additional travel time information is used to characterize the relationship between the acceptable additional travel time of the above-mentioned passengers and the compensation amount.

[0061] Detours to accommodate other needs (other ride requests or delivery requests) may result in additional travel time for passengers. Service operators may compensate passengers affected by this extra travel time under a price compensation plan. Each passenger has an Acceptable Extra Travel Time (AERD), which is the maximum extra travel time a passenger can tolerate at a given compensation amount. The value of the AERD is not fixed but varies depending on the compensation amount provided by the service provider. Therefore, each passenger will have an associated AERD profile, meaning the AERD changes with the compensation amount and may be non-linear.

[0062] In this embodiment, the acceptable additional travel time information corresponding to the passenger is used to characterize the AERD. Specifically, the aforementioned acceptable additional travel time information can be in the form of a list, a curve, or a function, and is not specifically limited here.

[0063] In this embodiment of the application, the above-mentioned acceptable additional travel time information is an acceptable additional travel time curve;

[0064] The above-mentioned acquisition of acceptable additional travel time information for each of the aforementioned passengers includes:

[0065] Obtain the preset initial curve and the satisfaction survey data corresponding to each of the above passengers, wherein the satisfaction survey data represents the satisfaction of the above passengers with the extra travel time and the corresponding compensation amount.

[0066] Based on the aforementioned satisfaction survey data, the initial curve was adjusted to obtain the acceptable additional travel time curve for each of the aforementioned passengers.

[0067] The aforementioned preset initial curve can be set and adjusted according to actual needs, and the passenger satisfaction survey data can be obtained from prior research.

[0068] In a specific application scenario, the operator will compensate passengers for ERD (Excessive Demand) incurred during their ISM (In-Service Transaction) trip due to additional pickups, deliveries, or picking up other passengers. Specifically, a phased compensation plan will be provided, including both fixed and variable amounts. Therefore, the compensation will follow a piecewise linear function relative to the ERD, which can approximate any general form of linear or nonlinear compensation function. The passenger price compensation scheme proposed in this application embodiment is characterized by a piecewise function, where [0, h] M ] represents the ERD interval under consideration, which is discretized into M arbitrary intervals represented by (M-1) breakpoints, where the breakpoints are determined by h. 1 h 2 h 3 , ..., h m , ..., h M-1 For ease of representation, let h be defined. 0 If := 0, then the compensation scheme can be represented by the vector x:={x0,x1,x2,...,x...}. m ,...,x M} represents, where x0 represents a fixed compensation amount (the specific value can be set and adjusted according to actual needs), x m , This indicates that when ERDh falls within the interval (h m-1 ,h m The amount of compensation per unit of ERD. Therefore, the compensation amount c provided to the passenger who generates ERDh can be calculated according to the following formula (1):

[0069]

[0070] Furthermore, in this embodiment, passenger satisfaction with the ISM service is determined by comprehensively considering the passenger's acceptable additional travel time curve (i.e., the AERD curve). In one application scenario, the passenger's AERD information is determined based on their corresponding demographic data. Specifically, it is assumed that a passenger in a ride request is associated with an AERD profile. Let... This indicates that passenger i is compensated in amount c. i The AERD (Maximum Acceptable Additional Travel Time) is given below. The AERD profile for request i can then be represented by the following general function:

[0071]

[0072] Specifically, the AERD curve can be a nonlinear continuous function, such as the indifference curve in utility theory, or a discontinuous function, such as a step function, or other functional forms, without specific limitations here. For example, the specific curve form can be... Where α i ,β i and γ i These are parameters related to passengers' personal attribute preferences. These parameters can be determined through passenger preference surveys to define the specific form and parameters of the passenger's acceptability curve for additional travel distance compensation. In one application scenario, setting these parameters to preset initial values ​​yields the corresponding initial curve. Adjusting the initial curve according to each passenger's personal attribute preference parameters yields the corresponding AERD curve for that passenger.

[0073] Specifically, a pre-set questionnaire can be used, including multiple hypothetical compensation levels, allowing passengers to rate their satisfaction with these compensation levels and thus understand their preferences and choices in different situations. For data collection, such surveys can be integrated into ride-hailing apps, requiring passengers to input their expected additional travel distance under different compensation levels when selecting combined passenger-parcel transportation services. The collected data will be used to analyze and determine the optimal mathematical form and parameters of the AERD curve. For example, regression analysis can be used to determine the relationship between satisfaction and compensation amount. By analyzing the obtained model parameters, the AERD satisfaction curve can be adjusted and calibrated to accurately reflect the true reactions and preferences of different passengers to different compensation levels.

[0074] Step S300: Construct a target optimization model based on the above travel demand information and the above acceptable additional travel time information, wherein the above target optimization model is used to characterize the vehicle route planning scheme and the above compensation amount scheme for the passengers under the target of maximizing expected profit.

[0075] In this embodiment of the application, an optimal compensation scheme x is determined under a given random demand, so that the service operator maximizes the expected profit in all realizations of uncertain demand, thereby satisfying the following conditions for each demand scenario ω: each transportation request is served by at most one vehicle; the additional waiting time for each passenger under the compensation plan does not exceed the maximum acceptable additional waiting time for that passenger; and the required vehicle capacity and time constraints are met.

[0076] Specifically, the above-mentioned objective optimization model is a two-stage stochastic programming model;

[0077] The first stage of the two-stage stochastic programming model described above is used to determine the optimal compensation scheme to maximize expected profit;

[0078] The second stage of the two-stage stochastic programming model is used to determine the vehicle route planning scheme and the compensation amount scheme for each passenger based on the optimal compensation scheme determined in the first stage.

[0079] Furthermore, the target optimization model constructed based on the aforementioned travel demand information and the aforementioned acceptable additional travel time information includes:

[0080] Based on the above travel demand information and the above acceptable additional travel time information, a first-stage objective function and a second-stage objective function are constructed. The second-stage objective function is used to characterize the profit determined based on each vehicle route planning scheme and target compensation amount scheme under the above travel demand information and the above acceptable additional travel time information. The first-stage objective function is the expected value of the second-stage objective function.

[0081] Obtain the objective constraints, and construct the two-stage stochastic programming model based on the objective constraints, the objective function of the first stage, and the objective function of the second stage.

[0082] Among them, the above-mentioned target constraints include vehicle planning constraints and compensation amount constraints;

[0083] The above vehicle planning constraints include vehicle trip integrity constraints, flow conservation constraints, constraints on the number of service vehicles to meet demand, service time constraints, passenger capacity constraints, and freight capacity constraints.

[0084] The aforementioned compensation amount constraints are used to constrain the compensation amount for the aforementioned passengers based on the aforementioned acceptable additional travel time information.

[0085] Furthermore, the aforementioned objective constraints also include boundary constraints for decision variables. It should be noted that other constraints may also be included, and the specific constraints can be set and adjusted according to actual needs; no specific limitations are imposed here.

[0086] In a specific application scenario provided in this application embodiment, a two-stage stochastic programming model is constructed. The first stage maximizes the service operator's expected profit by determining the optimal compensation scheme x. The second stage, given the compensation scheme determined in the first stage, maximizes the operator's profit by determining service demand, the compensation amount for each passenger, and vehicle route planning, while ensuring that a specific demand ω is met. To facilitate model construction, we use a directed graph G. ω =(V ω E ωLet ω be the occurrence of a certain demand, and let ω be the occurrence of a certain demand. Then, let ω be the occurrence of a certain demand, and ... 2σ ω +1 and node 0 represent the origin and destination of the warehouse, respectively; they are physically located at the same point. Each node in the network... All correspond to the service time window of the relevant passenger demand i [e i ,l i Service duration δ i Passenger load Package load Income amount R i and penalty amount P i Each edge Both are related to the path from node i to j. Travel time t ij and travel costs κ ij The settings for each parameter value are related and contain the following information:

[0087] Service duration: δ i =0,

[0088] Passenger count and parcel load capacity: and

[0089] Income: R i =0,

[0090] Punishment: P i =0,

[0091] Regarding the decision variable, in this embodiment of the application, a binary decision variable z is defined. i Indicates whether request i (i.e., the i-th request) is served; a binary decision variable. Indicates whether vehicle k travels directly from one node i (i.e., the i-th node) to another node j; a continuous decision variable. The continuous variable represents the time when vehicle k starts service at node i. and Let h represent the passenger and freight loads of vehicle k after it has served node i. i and c iThese are continuous variables, representing the actual ERD of passenger i's transportation request and the compensation given to the passenger, respectively. It should be noted that in this embodiment, the above decision variables are variables that need to be determined by solving the objective optimization model. Solving these decision variables can determine the target vehicle route planning scheme and the target compensation amount scheme. It should also be noted that in this embodiment, i and j only represent index values ​​or sequence values; the specific meaning of the corresponding parameters needs to be determined by referring to the overall parameter set.

[0092] Furthermore, the objective functions for the two stages of the above two-stage stochastic programming model can be represented by the following formulas (3) and (4):

[0093] Phase 1:

[0094]

[0095] Phase Two:

[0096]

[0097] The corresponding constraints are shown in the following formulas (5)-(20):

[0098]

[0099] The first-stage objective function (3) in the model represents maximizing the operator's expected profit under non-negativity constraints before the uncertain demand is realized. This objective is defined based on the optimal objective function value of the second-stage problem given by equations (4)-(20). The second-stage objective function (4) is to maximize the service provider's profit under the scenario of random passenger and parcel transportation demand. For each demand ω realized, the ISM service operator will further determine the demand, the compensation amount for each service passenger, and the vehicle route planning to maximize the total profit. Constraint (5) specifies the origin and destination constraints for each vehicle, which are used to specify the starting point and ending point of each vehicle to ensure that all trips have a clear start and end to guarantee the integrity of the process, i.e., the vehicle trip integrity constraint. Equation (6) is the flow conservation constraint, which ensures that the number of vehicles departing from any node is equal to the number of vehicles entering that node, ensuring the balance of vehicle flow in the network, with no vehicle loss or arbitrary generation. Constraints (7) and (8) guarantee that each request can be served by the same vehicle at most once, i.e., the service vehicle number constraint for the demand. Constraint (9) ensures that each passenger drop-off or pickup request occurs before the corresponding passenger drop-off or pickup time, guaranteeing the correctness of the logic and the feasibility of the service. Constraint (10) guarantees that each node satisfies the corresponding time window, ensuring the timeliness of the service and customer satisfaction. Constraint (11) updates the service time of each request on the vehicle route, maintaining the accuracy and continuity of the schedule. That is, the service time constraints include constraints (9)-(11). Constraints (12) and (13) respectively represent updating the passenger capacity and cargo capacity based on the actual route traveled by the vehicle. Constraints (14) and (15) are vehicle capacity limits, ensuring that the vehicle's carrying capacity is not exceeded. Constraints (12)-(13) characterize the passenger capacity constraints and cargo capacity constraints. Constraints (16) and (17) calculate the actual ERD and the corresponding passenger compensation amount, that is, the compensation amount constraint, which connects the decision-making of the first and second phase problems. Constraint (18) defines the passenger's ARD profile. Constraint (19) guarantees that the passenger's requested ERD cannot exceed the ARD limit. Constraint (20) defines the range of decision variables in the second stage, providing clear boundaries for solving the model, namely, decision variable boundary constraints.

[0100] Step S400: Solve the above target optimization model to obtain the target vehicle route planning scheme and the target compensation amount scheme, wherein the above target compensation amount scheme includes the target compensation amount for each of the above passengers.

[0101] Specifically, solving the above-mentioned objective optimization model yields the target vehicle route planning scheme and the target compensation amount scheme, including:

[0102] The two-stage stochastic programming model described above is processed using the sample average approximation method and transformed into a sample average approximation problem.

[0103] To address the aforementioned problem of approximating the average of samples, the compensation amount scheme and the vehicle routing scheme are iteratively solved to obtain the target vehicle routing scheme and the target compensation amount scheme.

[0104] To address the "curse of dimensionality" and the additional complexity introduced by nonlinear AERD constraints, this embodiment first employs the sample average approximation (SAA) method to transform the original two-stage stochastic programming model into an SAA problem. The expected total profit is then approximated using sample average estimation. Where Ω represents the total sample set fulfilled by the random demand ω, and φ ω The probability of a scenario occurring is used. The sample average approximation method is primarily used to address the computational challenges of two-stage stochastic programming models, especially when facing the curse of dimensionality and nonlinear constraints. This method estimates the model's expected total profit using a set of random samples. First, we collect and preprocess data. Real-time and historical traffic, passenger demand, and freight transport data are collected from the city's transportation management bureau's API interface and online ride-hailing service database. Before importing all data into the system, automated scripts check data integrity and consistency, filling missing values ​​with the average of previous and subsequent time points, and correcting or excluding outliers according to business rules. The goal of this stage is to ensure that subsequent analysis and model building are based on an accurate and reliable data foundation. Next, in the demand fulfillment sample generation stage, based on historical data, we generate a large number of demand fulfillment samples using the Monte Carlo method. Each scenario's passenger and parcel demand includes specific relevant parameter values ​​from the time and location of the demand to the demand quantity. These samples reflect possible demand scenarios, such as samples representing demand scenarios under different weather conditions, holidays, and weekdays. Each scenario is weighted according to its frequency of occurrence in historical data, ensuring that the sample set truly reflects the diversity and uncertainty of urban transportation. Based on these samples, we can transform the stochastic programming model into a deterministic problem, and then approximate the expected profit using a sample set drawn from real-world data. When constructing the optimization model, each sample scenario is treated as an independent instance. In each potential scenario, we consider factors such as vehicle quantity limits, time window constraints, and passenger-cargo matching constraints to maximize the operator's profit. Our goal is to determine the optimal compensation scheme, the best service request response, vehicle route planning, and specific passenger compensation plan (DPV scheme) while ensuring profit maximization.

[0105] In this embodiment of the application, in order to solve the above-mentioned SAA problem, an iterative hybrid algorithm is provided based on the heuristic of adaptive large neighborhood search (ALNS) and efficient compensation scheme adjustment (CSA). Specifically, this algorithm can be called the ALNS-CSA algorithm, which is used for further iterative solution.

[0106] The ALNS heuristic algorithm has been widely used to solve many vehicle routing problems. This method iteratively selects different deletion and insertion operators to update the solution, adjusting the selection probability of the operators based on the performance of previous iterations to explore a large solution space and find a near-optimal solution. Although this algorithm is effective for vehicle routing problems, the combination of compensation scheme design decisions and AERD profiles makes it difficult to directly apply ALNS to SAA problems. Therefore, we will first decompose the optimization process of the compensation scheme and the solution (DPV, demand serving, passenger compensation, and vehicle routing) plan by relaxing the AERD constraints. This is achieved by replacing the elastic AERD profile function with a fixed value of the maximum AERD, i.e. Therefore, the optimization of the DPV plan will be independent of the compensation scheme design, which can be further decomposed into multiple DPV subproblems, each corresponding to a DPV plan. The DPV subproblems are a variant of PDP and can be efficiently solved using ALNS. However, due to the relaxation of the AERD constraints, the resulting DPV solution may be infeasible for the original SAA problem. We will then restore the feasibility of the DPV solution while minimizing the compensation cost using a tailored CSA method. The ALNS and CSA methods will be used iteratively until a pre-specified number of iterations is reached.

[0107] Table 1 below is a pseudocode illustration of an iterative solution based on the ALNS-CSA algorithm provided in this application embodiment. As shown in Table 1, in this application embodiment, when iteratively solving based on the ALNS-CSA algorithm, an arbitrary compensation scheme is first used to start the iteration. In each iteration, the ALNS heuristic algorithm is first used to determine the DPV plan, while relaxing the AERD constraints under a specific compensation scheme. Based on the DPV plan, the CSA method is subsequently used to update the compensation scheme to restore the feasibility of the DPV plan and minimize the compensation cost. The new DPV plan and compensation scheme are evaluated to make them acceptable and become existing and optimal schemes. The selection probability of the ALNS operator is adaptively updated according to the performance of the solution. Each operator will continuously update its corresponding score after each iteration. Operators with better performance will have correspondingly higher scores, and the weights related to the scores will also be continuously updated to guide the use of different competing operators in the algorithm iteration. This process will iterate until the iteration number threshold is reached (which can be set and adjusted according to actual needs, and is not specifically limited here). It should be noted that the adaptive improvements to the DPV program will lay the foundation for subsequent compensation scheme updates.

[0108] Table 1

[0109]

[0110] Where n represents the number of iterations, n max This represents a preset threshold for the number of iterations (the specific value can be set and adjusted according to actual needs). Furthermore, for new DPV solutions, this embodiment provides a CSA method to update the corresponding compensation scheme, restoring the feasibility of the obtained DPV solution relative to the AERD constraint, while reducing the total compensation cost. Specifically, each passenger in the DPV solution has a gap between their ERD and actual AERD, called the passenger's AERD deviation. Based on the current compensation scheme and ERD, the received compensation amount and the corresponding passenger i's actual AERD can be calculated first. Then, passenger i's AERD deviation is:

[0111]

[0112] Δh i The value represents the passenger's AERD deviation, and there are three possible scenarios:

[0113] Case 1: Δh i The value is less than 0, indicating insufficient passenger compensation, which violates the AERD constraint. In this case, some compensation should be added. m This is to ensure that more compensation is provided to the passengers involved, thereby increasing the AERD value and eliminating the violation.

[0114] Case 2: Δh i =0, indicating precise compensation for the passenger, satisfying the AERD constraint. Under the current compensation plan, the passenger's ERD is exactly equal to the AERD.

[0115] Case 3: Δh i If the value is greater than 0, the passenger receives excess compensation, and the AERD constraint is satisfied. While maintaining the validity of the AERD constraint, the compensation component x can be reduced. m This reduces compensation costs.

[0116] According to the above definition, the AERD deviation of the DPV scheme is the sum of the AERD deviations of all passengers served by the DPV scheme, as shown in the following formula (22):

[0117]

[0118] This AERD deviation will be used to calculate the corresponding score of the ALNS operator, thereby correcting the operator's weights. Therefore, the detour time information generated by passengers can be considered in the algorithm update. This corrected adaptive weight adjustment method will be compared with the traditional weight adjustment method that does not incorporate AERD deviation information in application examples.

[0119] The passenger group served by the DPV program

[0120] To further determine the compensation component x m To determine the adjustment amount, we first calculate the compensation deviation, that is, the amount by which each passenger is undercompensated or overcompensated. Let... c i Let Δc be the minimum compensation required for passenger i to accept the current ERD. i :

[0121] Δc i = c i -c i =FunH -1 (h i )-c i (twenty three)

[0122] In the formula FunH -1 (·) is the inverse function of the AERD profile function FunH(·). For a non-zero Δc i Passengers with the value can adjust the compensation component x according to the under-compensation / over-compensation amount in formula (23). m This will increase / decrease the compensation received by the passenger to keep the passenger's AED / ERD consistent with their ERD.

[0123] Figure 2This is a schematic diagram of a CSA method processing flow provided in an embodiment of this application, such as... Figure 2 As shown, in the CSA method provided in this application embodiment, based on the current compensation scheme x and DPV plan {Ψ ω} ω∈Ω We first based on Δc i The value of γ is determined by whether it is greater than 0, equal to 0, or less than 0. This divides the passengers served by the DPV plan into three groups, γ1, γ2, and γ3, representing the sets of passengers that are under-compensated, fully compensated, and over-compensated, respectively. To avoid violating the AERD constraint, we first focus on under-compensated passengers in set γ1, iteratively checking each passenger and increasing the compensation component until there are no under-compensated passengers. Then, we check over-compensated passengers in set γ3, iteratively checking each passenger and decreasing the compensation component until no feasible reduction is allowed. Each time we make any adjustment to the compensation scheme, the three passenger sets γ1, γ2, and γ3 are updated accordingly. Unlike increasing adjustments within an interval, decreasing adjustments are performed within a bounded interval. The process was performed within the ERD breakpoint. index For precise compensation of passenger m in set γ2 i The maximum value is set to avoid passengers in set Υ2 violating the AERD constraint.

[0124] Thus, by characterizing the relationship between passengers' acceptable extra travel time and compensation amount, higher profitability can be achieved while ensuring customer satisfaction. Specifically, based on the solution of this embodiment, the shared mobility service can be optimized, such as determining the optimal compensation price and demand scheduling for new passenger-freight intermodal shared mobility. Based on accurately calculated predicted demand, resources can be dynamically allocated to reduce waiting time and improve service efficiency. In this embodiment, data collection includes the request time, location, destination, and user preferences of passengers and parcels. This data can be collected in real time through the API interface of the urban traffic management system and stored in a central database. Data processing can use statistical analysis and machine learning models to predict travel demand, and the optimization model adjusts resource allocation based on the given demand data. The mathematical model in this embodiment is a price compensation scheme optimization model. Based on the transportation demand of passengers and parcels, the price compensation scheme optimization model uses a mixed integer programming method to optimize the compensation price scheme for detour passengers and the specific vehicle route planning to minimize operating costs while ensuring passenger service quality.

[0125] As can be seen from the above, the method for determining the compensation scheme for shared mobility services provided in this application does not only consider the vehicle route optimization problem, but also constructs a target optimization model by combining travel demand information and the passenger's corresponding acceptable additional travel time information. It comprehensively considers the impact of vehicle route planning and the additional travel time generated during cargo loading on passenger satisfaction, constructs a corresponding target optimization model, and optimizes and solves it, which is conducive to improving the optimization effect and service quality of the comprehensive shared transportation service.

[0126] In this embodiment, the effectiveness of the above-mentioned method for determining the compensation scheme for shared mobility services is verified based on a specific application scenario. Specifically, the test instance is adapted from the standard DARP instance of Cordeau and Laporte (2003). Five baseline instances (R1a, R7a, R2a, R3a, R4a) with different request numbers are selected as basic instances to generate test instances under different scenarios. Each test instance is modified from a basic instance and includes four different scenarios. The total number of requests in each scenario is set to be consistent with the corresponding basic instance, but proportionally divided into passenger and package requests. The test instance is named rr_nr, where rr is the ratio of passenger requests to package requests in each scenario, and nr is the total number of requests in each scenario. For example, test instance 3_24 is modified based on the baseline instance R1a, and each scenario contains 24 requests, of which package delivery accounts for one-quarter of the total demand. The four scenarios in the specific instance share some common model parameters. In addition to the parameters in the passenger AERD function indicating the uncertain demand in different scenarios, there are some common model parameters: fleet size and per passenger / package request. The location and time window (in minutes) are set according to the baseline instance, and the number of passengers requested for each ride is [number missing]. Package request The load is a randomly generated positive integer, and Loading and unloading service time (Unit: min), Passenger capacity per vehicle Parcel carrying capacity of each vehicle Penalty for refusing a passenger's service request (P) i =5, (Unit: USD), Service penalty for rejecting package request P i =2, (Unit: US dollars), travel time t ij The calculation method is to divide the distance (i,j) by 0.83 km / min (i.e., the average vehicle speed is set to 50 km / h), and the travel cost κ is calculated. ijThe calculation method involves multiplying the distance (i,j) by $0.5 per kilometer. Note that the distance between nodes is calculated in Euclidean distance (unit: km). This is achieved by multiplying the edge (i,j) by $0.5 per kilometer. ω The income is calculated by multiplying the direct distance by $2.5 per kilometer. i , By using edge (i,i+σ) ω The direct distance is multiplied by $1 per kilometer to calculate each transport request. Income earned.

[0127] For each generated instance, the ALNS-CSA algorithm was executed 5 times, and the average calculation results are shown in Table 2 below.

[0128] Table 2

[0129]

[0130] In Table 2, the first three columns represent the instance, expected profit result, and corresponding CPU time, respectively. The fourth column shows the profit difference between the modified adaptive weight adjustment method and the traditional weight adjustment method. CPU time represents the time spent by the computer processor executing our algorithm program once; here, the average of five executions is used.

[0131] As shown in Table 2, expected profits decrease as the proportion of parcel requests in total demand increases. This is because serving passenger ride requests generates more revenue than parcel delivery requests. A larger parcel-to-passenger ratio indicates more carpooling or multiple passengers sharing a vehicle for passenger-parcel ride-sharing. This results in fewer options for merging parcels on routes due to passenger AERD restrictions. Instances with a smaller parcel ratio have a higher frequency of passenger-parcel carpooling compared to instances with a larger ratio. This means fewer constraints need to be considered in terms of passenger ride experience. Therefore, there is a greater opportunity to merge parcel requests, and consequently, more opportunities to merge parcel requests. This is because if a vehicle has dedicated parcel carrying capacity, it can not only be used for passenger-to-passenger ride-sharing but also to aggregate parcel delivery requests through additional detours. This can be done even when passenger capacity is at its maximum, thus providing more opportunities for efficient parcel delivery. Therefore, more alternative vehicle route plans need to be evaluated, requiring more computation time to obtain the optimal solution that effectively integrates and coordinates passenger rides and parcel deliveries. It can be inferred that the arrangement of candidate parcel demand ratios is crucial to the deployment of the ISM service.

[0132] Furthermore, the effectiveness of the proposed improved adaptive weighting technique was evaluated by comparing its performance with conventional methods, based on the percentage differences between the respective expected profit solutions. Overall, the results show that by implementing the method provided in the embodiments of this application, the performance of the solutions is significantly enhanced, with all differences exceeding 2.00%.

[0133] Exemplary device

[0134] like Figure 3 As shown in the figure, corresponding to the above-mentioned method for determining the compensation scheme for shared mobility services, this application embodiment also provides a system for determining the compensation scheme for shared mobility services, the above-mentioned system for determining the compensation scheme for shared mobility services includes:

[0135] The first information acquisition module 310 is used to acquire travel demand information, wherein the travel demand information includes passenger travel demand and parcel delivery demand. Each passenger travel demand includes the passenger's departure point, destination, pickup time window, drop-off time window and number of passengers. Each parcel delivery demand includes the parcel's pickup location, pickup time window, loading service time, drop-off location, drop-off time window and unloading service time.

[0136] The second information acquisition module 320 is used to acquire the acceptable additional travel time information for each of the above-mentioned passengers, wherein the acceptable additional travel time information is used to characterize the relationship between the acceptable additional travel time of the above-mentioned passengers and the compensation amount.

[0137] The model building module 330 is used to build a target optimization model based on the above travel demand information and the above acceptable additional travel time information. The target optimization model is used to characterize the vehicle route planning scheme and the compensation amount scheme for the above passengers under the goal of maximizing expected profit.

[0138] The model solving module 340 is used to solve the above-mentioned target optimization model to obtain the target vehicle route planning scheme and the target compensation amount scheme, wherein the above-mentioned target compensation amount scheme includes the target compensation amount for each of the above-mentioned passengers.

[0139] Therefore, it is not just about optimizing vehicle routes, but about building a target optimization model by combining travel demand information and passengers' acceptable additional travel time information. It comprehensively considers the impact of vehicle route planning and the additional travel time generated during cargo loading on passenger satisfaction, builds a corresponding target optimization model, and optimizes and solves it, which is conducive to improving the optimization effect and service quality of integrated shared transportation services.

[0140] It should be noted that the specific structure and implementation of the above-mentioned shared mobility service compensation scheme determination system and its various modules or units can be referred to the corresponding descriptions in the above method embodiments, and will not be repeated here.

[0141] It should be noted that the division of the various modules in the above-mentioned shared mobility service compensation scheme is not unique and is not intended as a specific limitation.

[0142] Based on the above embodiments, this application also provides a smart terminal, the principle block diagram of which can be as follows: Figure 4 As shown. The aforementioned smart terminal includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a program for determining a shared mobility service compensation scheme. The internal memory provides an environment for the operation of the operating system and the program for determining the shared mobility service compensation scheme in the non-volatile storage medium. The network interface of the smart terminal is used for communication with external terminals via a network connection. When the shared mobility service compensation scheme determination program is executed by the processor, it implements the steps of any of the aforementioned shared mobility service compensation scheme determination methods. The display screen of the smart terminal can be a liquid crystal display (LCD) or an e-ink display.

[0143] Those skilled in the art will understand that Figure 4 The block diagram shown is only a partial structural diagram related to the solution of this application and does not constitute a limitation on the smart terminal on which the solution of this application is applied. The specific smart terminal may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0144] In one embodiment, a smart terminal is provided, the smart terminal including a memory, a processor, and a shared mobility service compensation scheme determination program stored in the memory and executable on the processor. When the shared mobility service compensation scheme determination program is executed by the processor, it implements the steps of any shared mobility service compensation scheme determination method provided in the embodiments of this application.

[0145] This application also provides a computer-readable storage medium storing a shared mobility service compensation scheme determination program. When the shared mobility service compensation scheme determination program is executed by a processor, it implements the steps of any of the shared mobility service compensation scheme determination methods provided in this application.

[0146] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0147] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the above device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above device can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0148] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0149] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0150] In the embodiments provided in this application, it should be understood that the disclosed systems / terminal devices and methods can be implemented in other ways. For example, the system / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units described above is merely a logical functional division, and in actual implementation, it can be divided in other ways. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0151] If the integrated modules / units described above are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0152] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions are not in essence a departure from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for determining a compensation scheme for shared mobility services, characterized in that, The method includes: Obtain travel demand information, wherein the travel demand information includes passenger travel demand and parcel delivery demand. Each passenger travel demand includes the passenger's departure point, destination, pickup time window, drop-off time window, and number of passengers. Each parcel delivery demand includes the parcel's pickup location, pickup time window, loading service time, drop-off location, drop-off time window, and unloading service time. Obtain the acceptable additional travel time information for each of the passengers, wherein the acceptable additional travel time information is used to characterize the relationship between the passenger's acceptable additional travel time and the compensation amount; A target optimization model is constructed based on the travel demand information and the acceptable additional travel time information, wherein the target optimization model is used to characterize the vehicle route planning scheme and the corresponding compensation amount scheme for the passenger under the goal of maximizing expected profit. Solve the target optimization model to obtain the target vehicle route planning scheme and the target compensation amount scheme, wherein the target compensation amount scheme includes the target compensation amount for each passenger.

2. The method for determining the compensation scheme for shared mobility services according to claim 1, characterized in that, The acceptable additional travel time information is an acceptable additional travel time curve; The step of obtaining the acceptable additional travel time information for each of the passengers includes: Obtain a preset initial curve and the satisfaction survey data corresponding to each passenger, wherein the satisfaction survey data represents the passenger's satisfaction with the extra travel time and the corresponding compensation amount. Based on the satisfaction survey data, the initial curve is adjusted to obtain the acceptable additional travel time curve for each passenger.

3. The method for determining the compensation scheme for shared mobility services according to claim 1, characterized in that, The objective optimization model is a two-stage stochastic programming model; The first stage of the two-stage stochastic programming model is used to determine the optimal compensation scheme to maximize the expected profit. The second stage of the two-stage stochastic programming model is used to determine the vehicle route planning scheme and the compensation amount scheme for each passenger based on the optimal compensation scheme determined in the first stage.

4. The method for determining the compensation scheme for shared mobility services according to claim 3, characterized in that, The step of constructing a target optimization model based on the travel demand information and the acceptable additional travel time information includes: Based on the travel demand information and the acceptable additional travel time information, a first-stage objective function and a second-stage objective function are constructed. The second-stage objective function is used to characterize the profit determined based on each vehicle route planning scheme and the target compensation amount scheme under the travel demand information and the acceptable additional travel time information. The first-stage objective function is the expected value of the second-stage objective function. Obtain the target constraints, and construct the two-stage stochastic programming model based on the target constraints, the objective function of the first stage, and the objective function of the second stage.

5. The method for determining the compensation scheme for shared mobility services according to claim 4, characterized in that, The target constraints include vehicle planning constraints and compensation amount constraints; The vehicle planning constraints include vehicle trip integrity constraints, flow conservation constraints, constraints on the number of service vehicles to meet demand, service time constraints, passenger capacity constraints, and cargo capacity constraints. The compensation amount constraint is used to constrain the compensation amount for the passenger based on the acceptable additional travel time information.

6. The method for determining a compensation scheme for shared mobility services according to claim 5, characterized in that, The objective constraints also include decision variable boundary constraints.

7. The method for determining the compensation scheme for shared mobility services according to claim 3, characterized in that, Solving the target optimization model to obtain the target vehicle route planning scheme and the target compensation amount scheme includes: The two-stage stochastic programming model is processed using the sample average approximation method, transforming it into a sample average approximation problem. To address the sample average approximation problem, the compensation amount scheme and vehicle route planning scheme are iteratively solved to obtain the target vehicle route planning scheme and the target compensation amount scheme.

8. A system for determining compensation schemes for shared mobility services, characterized in that, The system includes: The first information acquisition module is used to acquire travel demand information, wherein the travel demand information includes passenger travel demand and parcel delivery demand. Each passenger travel demand includes the passenger's departure point, destination, pickup time window, drop-off time window and number of passengers. Each parcel delivery demand includes the parcel's pickup location, pickup time window, loading service time, drop-off location, drop-off time window and unloading service time. The second information acquisition module is used to acquire the acceptable additional travel time information for each passenger, wherein the acceptable additional travel time information is used to characterize the relationship between the passenger's acceptable additional travel time and the compensation amount. The model building module is used to build a target optimization model based on the travel demand information and the acceptable additional travel time information, wherein the target optimization model is used to characterize the vehicle route planning scheme and the corresponding compensation amount scheme for the passenger under the goal of maximizing expected profit. The model solving module is used to solve the target optimization model to obtain the target vehicle route planning scheme and the target compensation amount scheme, wherein the target compensation amount scheme includes the target compensation amount for each passenger.

9. A smart terminal, characterized in that, The smart terminal includes a memory, a processor, and a shared mobility service compensation scheme determination program stored in the memory and executable on the processor. When the shared mobility service compensation scheme determination program is executed by the processor, it implements the steps of the shared mobility service compensation scheme determination method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a shared mobility service compensation scheme determination program, which, when executed by a processor, implements the steps of the shared mobility service compensation scheme determination method as described in any one of claims 1 to 7.

Images