Dynamic class line passenger transport resource matching system and method based on cloud platform

Abstract

The invention provides a dynamic class line passenger transport resource matching system and method based on a cloud platform, and relates to the technical field of resource matching, and the method comprises the steps: obtaining all passenger travel demand information in the cloud platform in real time, carrying out the data cleaning of all passenger travel demand information, and generating a travel demand set; performing route aggregation according to the historical passenger flow route set and the travel demand set to obtain a response passenger flow cluster, and determining a dynamic passenger transport corridor set according to the response passenger flow cluster; a vehicle transport capacity unit is generated according to the passenger transport vehicle information, a self-adaptive transport capacity map is constructed according to the vehicle transport capacity unit, passenger transport matching is performed through the self-adaptive transport capacity map and the dynamic passenger transport corridor set, and a passenger transport response unit is generated; and generating a vehicle scheduling instruction packet for scheduling the passenger transport vehicle according to the passenger transport response unit. According to the invention, the real-time performance and the accuracy of passenger transport scheduling can be effectively improved, and the adaptive capability and the service response capability of passenger transport resources to passenger flow changes are enhanced.

Description

Technical Field

[0001] This application relates to the field of resource matching technology, and more specifically, to a dynamic scheduled passenger transport resource matching system and method based on a cloud platform. Background Technology

[0002] With the continuous advancement of urbanization and the increasing diversification of residents' travel needs, existing passenger transport dispatching systems typically collect passenger travel information and combine existing passenger transport routes and vehicle resources to uniformly manage and dispatch passenger vehicles, thereby responding to passenger travel demands. Related technologies generally analyze passenger flow distribution based on historical passenger flow data and generate corresponding vehicle operation routes and dispatching instructions according to the current vehicle location, passenger status, and established operating rules to support the normal operation of passenger transport services.

[0003] However, in existing passenger transport scheduling technologies, vehicle dispatching typically relies on fixed routes or makes decisions based on single historical passenger flow data. This makes it difficult to reflect real-time changes in passenger travel demand in a timely manner, and the perception of vehicle capacity status is limited. This results in a low degree of matching between passenger flow organization and capacity allocation, affecting overall dispatching efficiency and service quality. Therefore, how to effectively improve the real-time performance and accuracy of passenger transport scheduling, and enhance the adaptability and service responsiveness of passenger resources to changes in passenger flow, is a problem facing the industry. Summary of the Invention

[0004] This application provides a dynamic scheduled passenger transport resource matching system and method based on a cloud platform, which can effectively improve the real-time performance and accuracy of passenger transport scheduling, and enhance the adaptability and service response capability of passenger transport resources to changes in passenger flow.

[0005] Firstly, this application provides a dynamic scheduled passenger transport resource matching method based on a cloud platform, the matching method comprising the following steps: Real-time acquisition of all passenger travel demand information from the cloud platform, data cleaning of all passenger travel demand information, and generation of travel demand set; Obtain the historical passenger flow route set, aggregate routes based on the historical passenger flow route set and the travel demand set to obtain various responsive passenger flow clusters, and then generate a dynamic passenger transport corridor set for passenger vehicle travel through each responsive passenger flow cluster. Real-time acquisition of passenger vehicle information from the cloud platform; generation of multiple passenger vehicle capacity units based on the passenger vehicle information; construction of an adaptive capacity map of passenger vehicle operation based on all vehicle capacity units; passenger matching of the dynamic passenger corridor set based on the adaptive capacity map; generation of various passenger response units for dynamic routes. Vehicle dispatch instruction packages for dispatching passenger vehicles are generated based on each passenger transport response unit.

[0006] In this embodiment, real-time acquisition of all passenger travel demand information in the cloud platform is achieved by deploying a set of microservices on the cloud platform to acquire all passenger travel demand information in real time.

[0007] In this embodiment, route aggregation is performed based on the historical passenger flow route set and the travel demand set to obtain various response passenger flow clusters, specifically including: Feature extraction is performed on the travel demand set to obtain feature vectors for each demand; Based on the historical passenger flow route set and various demand feature vectors, similarity matching is performed to obtain the similarity of each passenger flow. Each response passenger flow cluster is determined based on the similarity of each passenger flow.

[0008] In this embodiment, the dynamic passenger corridor set for passenger vehicle travel is generated through each responding passenger flow cluster, specifically including: For each responding passenger flow cluster, multiple virtual sites are constructed based on the responding passenger flow cluster, thereby obtaining all the virtual sites constructed for each responding passenger flow cluster; Corridor capacity planning is performed on all virtual sites to obtain multiple corridor capacity requirements; A dynamic set of passenger corridors is generated based on all corridor capacity demands.

[0009] In this embodiment, the dynamic passenger corridor set refers to a set of passenger routes that includes passenger demand.

[0010] In this embodiment, generating a vehicle capacity unit for multiple passenger vehicles based on the passenger vehicle information specifically includes: Feature extraction is performed on the passenger vehicle information to obtain multiple vehicle capacity features; For each vehicle's capacity characteristics, a corresponding vehicle capacity unit is generated based on the vehicle capacity characteristics, thereby obtaining multiple passenger vehicle capacity units.

[0011] In this embodiment, the passenger transport matching of the dynamic passenger transport corridor set based on the adaptive capacity map to generate each passenger transport response unit of the dynamic route specifically includes: A passenger transport efficiency matrix is ​​constructed using the adaptive capacity map and the dynamic passenger transport corridor set. Determine the passenger matching scheme based on the passenger efficiency matrix; The dynamic route's various passenger response units are generated based on the passenger matching scheme.

[0012] In this embodiment, the passenger transport response unit refers to all schedulable entities in the dynamic passenger transport system that perform a single passenger transport task.

[0013] In this embodiment, the vehicle dispatching instruction package generated according to each passenger transport response unit specifically includes: Extract the spatiotemporal task chain of each passenger response unit; The vehicle dispatch instruction package for dispatching passenger vehicles is generated based on the spatiotemporal task chain of each passenger transport response unit.

[0014] Secondly, this application provides a cloud-based dynamic scheduled passenger transport resource matching system for executing a cloud-based dynamic scheduled passenger transport resource matching method, the matching system comprising: The demand acquisition module is used to acquire all passenger travel demand information in the cloud platform in real time, clean the data of all passenger travel demand information, and then generate a travel demand set. The corridor determination module is used to obtain the historical passenger flow route set, perform route aggregation based on the historical passenger flow route set and the travel demand set, obtain each responding passenger flow cluster, and then generate a dynamic passenger transport corridor set for passenger vehicle travel through each responding passenger flow cluster. The passenger transport response module is used to acquire passenger vehicle information from the cloud platform in real time, generate multiple passenger vehicle capacity units based on the passenger vehicle information, construct an adaptive capacity map of passenger vehicle operation based on all vehicle capacity units, perform passenger transport matching on the dynamic passenger transport corridor set based on the adaptive capacity map, and generate each passenger transport response unit of the dynamic route. The instruction generation module is used to generate vehicle dispatch instruction packages for dispatching passenger vehicles based on each passenger transport response unit.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The system acquires real-time passenger travel demand information from the cloud platform, performs data cleaning on this information, and generates a travel demand set. It also acquires historical passenger flow route sets, aggregates routes based on these sets and the travel demand set to obtain various responsive passenger flow clusters, and generates a dynamic passenger transport corridor set for passenger vehicles through these clusters. Furthermore, it acquires real-time passenger vehicle information from the cloud platform, generates multiple vehicle capacity units based on this information, constructs an adaptive capacity map for passenger vehicle operation based on all vehicle capacity units, performs passenger matching on the dynamic passenger transport corridor set based on the adaptive capacity map, and generates various passenger response units for dynamic routes. Finally, it generates vehicle dispatch instruction packages for dispatching passenger vehicles based on each passenger response unit.

[0016] Therefore, this application demonstrates two key advantages: First, by collecting the travel needs of each target passenger in real time and cleaning the information, duplicate and abnormal demand data can be effectively eliminated, improving the accuracy and completeness of the travel demand data. This results in a high-quality set of travel demands, providing a reliable data foundation for subsequent passenger flow analysis, route aggregation, and passenger transport scheduling. Second, by acquiring historical passenger flow route sets and combining them with the real-time generated travel demand sets for route aggregation analysis, the distribution patterns of passenger flow in time and space can be uncovered. Demands with similar travel characteristics can be grouped into responsive passenger flow clusters, and passenger corridors for passenger vehicles can be dynamically determined accordingly. This avoids the limitations of fixed-route scheduling and improves the rationality of passenger flow organization and vehicle operation routes. Dynamic adaptability enhances overall passenger transport service efficiency. Then, by acquiring real-time information on each passenger vehicle and generating corresponding vehicle capacity units, an adaptive capacity map is constructed. Combined with dynamic passenger corridor sets for passenger matching, this comprehensively reflects the real-time distribution and changing status of capacity resources, achieving precise matching between capacity and passenger demand. This avoids uneven capacity allocation and scheduling delays, thereby enhancing the passenger transport system's adaptability to dynamic passenger flow changes. Finally, by generating corresponding vehicle scheduling instruction packages based on each passenger response unit, passenger matching results can be directly converted into executable scheduling instructions, enabling rapid and accurate vehicle scheduling. This ensures the timeliness and consistency of scheduling decisions, thereby improving the overall operational efficiency of the passenger transport system.

[0017] In summary, the technical solution adopted in this application can effectively improve the real-time performance and accuracy of passenger transport scheduling, and enhance the adaptability and service response capabilities of passenger transport resources to changes in passenger flow. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, 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 for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is an exemplary flowchart of a dynamic scheduled passenger transport resource matching method based on a cloud platform provided in this application; Figure 2 This is a flowchart illustrating the process of generating a dynamic set of passenger corridors for multiple passenger vehicle trips, as provided in this application. Figure 3 This is a flowchart illustrating the various passenger response units for generating dynamic bus routes, provided in this application. Figure 4This is a module structure diagram of a dynamic scheduled passenger transport resource matching system based on a cloud platform, provided in this application. Detailed Implementation

[0020] 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 some embodiments of this application, and not all 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.

[0021] This application provides a dynamic scheduled passenger transport resource matching system and method based on a cloud platform. Its core is to acquire all passenger travel demand information from the cloud platform in real time, perform data cleaning on all passenger travel demand information, and then generate a travel demand set; acquire historical passenger flow route sets, and aggregate routes based on the historical passenger flow route sets and the travel demand set to obtain various responsive passenger flow clusters, and then generate a dynamic passenger transport corridor set for passenger vehicle travel through these various responsive passenger flow clusters; acquire passenger vehicle information from the cloud platform in real time, generate multiple passenger vehicle capacity units based on the passenger vehicle information, construct an adaptive capacity map of passenger vehicle operation based on all vehicle capacity units, perform passenger transport matching on the dynamic passenger transport corridor set based on the adaptive capacity map, and generate various passenger transport response units for dynamic scheduled routes; and generate vehicle dispatch instruction packages for dispatching passenger vehicles based on each passenger transport response unit.

[0022] Example 1: To better understand the above technical solution, the following will provide a detailed description of the technical solution in conjunction with the accompanying drawings and specific implementation methods. (Refer to...) Figure 1 As shown in the figure, this is an exemplary flowchart of a dynamic scheduled passenger transport resource matching method based on a cloud platform according to this embodiment of the present application. The matching method includes the following steps: In step S1, all passenger travel demand information in the cloud platform is acquired in real time, and the data of all passenger travel demand information is cleaned to generate a travel demand set.

[0023] In this embodiment, real-time acquisition of all passenger travel demand information in the cloud platform is achieved by deploying a set of microservices on the cloud platform to obtain all passenger travel demand information in the cloud platform in real time. Specifically, a microservice architecture can be used to deploy a demand access service, which collects the boarding coordinates, destination coordinates, travel time, and number of passengers from the target passengers, and records the order time of the current target passenger. The boarding coordinates, destination coordinates, order time, travel time, and number of passengers of the target passenger are used as the passenger travel demand of the target passenger, thereby obtaining the passenger travel demand of each target passenger.

[0024] In practical implementation, all passenger travel demand information is cleaned to generate a travel demand set. Specifically, for each passenger's travel demand, the boarding coordinates, destination coordinates, order time, travel time, and number of passengers are verified. The boarding coordinates and destination coordinates are verified to be within the preset service range, the travel time is verified to be greater than the order time, and the number of passengers is verified to be greater than 0. Passenger travel demands that do not meet the verification criteria are marked as invalid and sent to manual review. Fingerprints are then generated for the remaining passenger travel demands, such as (passenger ID, origin, destination, number of passengers, travel time, order time). These fingerprints are used as set elements to generate the travel demand set. It should be noted that the travel demand set is a collection of all passenger travel fingerprints, and the scope of this set includes all passenger travel fingerprints whose order time is within ten minutes.

[0025] In step S2, a set of historical passenger flow routes is obtained, and routes are aggregated based on the set of historical passenger flow routes and the set of travel demands to obtain various responsive passenger flow clusters. Then, a set of dynamic passenger transport corridors for passenger vehicle travel is generated through these various responsive passenger flow clusters.

[0026] In practical implementation, the historical passenger flow route set is obtained by querying the historical passenger flow information of the past week through historical passenger flow traffic records. Each historical passenger flow route has a corresponding historical average time window, historical passenger departure area, historical passenger arrival area, and historical average passenger volume. Among them, the historical time window refers to the time interval with the largest passenger volume in a day; the historical average time window refers to the average of the historical time windows within a week. Thus, each historical passenger flow route and its corresponding historical average time window, historical passenger departure area, historical passenger arrival area, and historical average passenger volume are used as the historical passenger flow route set.

[0027] In this embodiment, the route aggregation based on the historical passenger flow route set and the travel demand set to obtain various responsive passenger flow clusters can be achieved through the following steps: Feature extraction is performed on the travel demand set to obtain feature vectors for each demand; Based on the historical passenger flow route set and various demand feature vectors, similarity matching is performed to obtain the similarity of each passenger flow. Each response passenger flow cluster is determined based on the similarity of each passenger flow.

[0028] In specific implementation, firstly, features can be extracted from the travel demand set to obtain various demand feature vectors. Specifically, for each passenger's travel fingerprint in the travel demand set, the origin and destination points can be converted into strings using the GeoHash algorithm. These strings are then mapped to numerical features using hashing techniques. Travel time is converted into minutes within a day, and sine and cosine transforms are used to preserve periodicity. Passenger ID is not included in the features; passenger quantity is directly used as a feature. All extracted features are used as vector elements to form a feature vector, which is then used as the demand feature vector for that passenger's travel fingerprint, thus obtaining various demand feature vectors. Next, similarity matching can be performed between the historical passenger flow route set and each demand feature vector to obtain passenger flow similarity. Specifically, for each historical passenger flow route in the historical passenger flow route set, a historical passenger flow route is selected. For each demand feature vector, the travel time feature in the demand feature vector can be compared with the historical average time window of that historical passenger flow route to obtain time similarity. Distance can be calculated by adding the upper and lower limits of the historical average time window, dividing the result by 2, and using this result as the center point of the historical average time window. Then, subtracting the lower limit from the upper limit of the historical average time window, dividing the result by 2, and using this result as the time window width, yields the time similarity distance. The absolute value of the difference between the travel time characteristic and the center point of the historical average time window is then divided by the time window width. This result represents the time similarity distance, which measures the relative degree to which demand time deviates from the center of the historical time window. Next, subtracting the historical average passenger flow from the number of passengers, taking the absolute value, and dividing this absolute value by the historical average passenger flow, yields the passenger flow scale difference, which measures the relative degree to which the number of passengers deviates from the historical average scale. The distance from the origin to the historical passenger departure area is calculated using the Euclidean distance formula, thus the origin similarity can be obtained using the following formula:

[0029] in, Indicates the similarity of starting points; This represents the distance from the origin to the historical passenger departure area. Thus, based on the above steps, the destination similarity can also be obtained. Then, the time similarity distance, passenger flow scale difference, origin similarity, and destination similarity of the demand feature vector are geometrically averaged, and the result is used as the passenger flow similarity of the demand feature vector to the historical passenger flow route. Thus, the passenger flow similarity of each demand feature vector to the set of historical passenger flow routes can be obtained. It should be noted that passenger flow similarity is used to measure the degree of matching between passenger travel demand and historical passenger flow routes.

[0030] In addition, in specific implementation, each response passenger flow cluster can be determined based on the similarity of each passenger flow. That is, for each historical passenger flow route in the historical passenger flow route set, the passenger flow similarity corresponding to each historical passenger flow route is sorted from largest to smallest. The demand feature vector corresponding to the passenger flow similarity with the first ranking is extracted and labeled. The above steps are performed on all historical passenger flow routes until all demand feature vectors are labeled. Then, all demand feature vectors labeled by the historical passenger flow route are taken as response passenger flow clusters, thus obtaining each response passenger flow cluster. It should be noted that a response passenger flow cluster refers to a set with similar travel characteristics.

[0031] Preferably, in this embodiment, a dynamic passenger corridor set for passenger vehicle travel is generated by each responding passenger flow cluster, referring to... Figure 2 As shown in the figure, this is a schematic diagram of the process of generating a dynamic passenger corridor set for multiple passenger vehicle trips in some embodiments of this application. In this embodiment, generating a dynamic passenger corridor set for multiple passenger vehicle trips can be achieved by the following steps: In step S21, for each responding passenger flow cluster, multiple virtual sites are constructed based on the responding passenger flow cluster, thereby obtaining all the virtual sites constructed for each responding passenger flow cluster. In step S22, corridor capacity planning is performed on all virtual sites to obtain multiple corridor capacity requirements; In step S23, a dynamic set of passenger corridors for passenger vehicle travel is generated based on all corridor capacity demands.

[0032] In practical implementation, firstly, for each responding passenger flow cluster, multiple virtual stations can be constructed based on the cluster. This yields all the virtual stations constructed for each responding passenger flow cluster. Specifically, for each responding passenger flow cluster, all starting points are extracted to form a set containing the passenger count for each point, and all ending points are extracted to form a set containing the passenger count for each point. The DBSCAN clustering algorithm is applied, defining a neighborhood radius of 300m (acceptable walking distance), to obtain all boarding and alighting hotspots. This results in a set of boarding and alighting hotspot areas. For all boarding and alighting hotspots in these sets, a filtering process is performed, prioritizing those located on main roads and secondary roads. All pick-up and drop-off hotspots on main roads and secondary roads (avoiding highways and no-stopping zones), and on roads where temporary parking is permitted, are designated as virtual stations, thus obtaining various virtual stations. Then, corridor capacity planning can be performed on all virtual stations to obtain multiple corridor capacity demands. That is, all demand feature vectors are assigned to each virtual station, meaning each passenger corresponds to two virtual stations. Through route planning algorithms, various passenger routes are obtained. For each passenger route, the total passenger flow is calculated, and the starting and ending virtual stations corresponding to that route are determined. The first virtual station reached by the passenger route is the starting virtual station, and the last virtual station reached by the passenger route is the ending virtual station. A virtual station is used as the terminating virtual station to obtain the total passenger distance. The travel time of all passengers on this route is extracted, the timeline is divided into 1-minute intervals, and the passenger demand at each minute is counted. The maximum value is selected to obtain the required capacity value, i.e., the maximum number of passengers that the route needs to accommodate. The total passenger flow, total passenger distance, and required capacity value of this route are then used as vector elements and merged into a single vector. This vector is used as the corridor capacity demand for this route, thus obtaining the capacity demand for each corridor. It should be noted that corridor capacity demand refers to the passenger resources allocated to meet the travel needs of all passengers within the route. Finally, based on all corridor capacity demands... Generate a dynamic passenger corridor set for passenger vehicle travel. That is, for each passenger route, set the passenger route as a triple containing: (route ID, virtual station set, passenger identifier). Mark the corridor capacity demand corresponding to the passenger route in the triple, thus obtaining a quadruple, such as: (route ID, virtual station set, passenger identifier, corridor capacity demand). Output the quadruple, and use the output result as the dynamic passenger corridor, thus obtaining each dynamic passenger corridor. Merge all the dynamic passenger corridors as set elements into a set to obtain the dynamic passenger corridor set for passenger vehicle travel. It should be noted that the dynamic passenger corridor set refers to a set of passenger routes containing passenger demand.

[0033] In step S3, passenger vehicle information in the cloud platform is acquired in real time, and multiple passenger vehicle capacity units are generated based on the passenger vehicle information. An adaptive capacity map of passenger vehicle operation is constructed based on all the vehicle capacity units. Passenger matching is performed on the dynamic passenger corridor set based on the adaptive capacity map to generate each passenger response unit of the dynamic route.

[0034] In practice, passenger vehicle information is acquired in real time from the cloud platform. For each passenger vehicle, the vehicle ID, vehicle capacity, current passenger capacity, current vehicle coordinates, current speed, current operating status, and vehicle model can be extracted from the cloud platform. This information vector is then used as the vehicle information vector for that passenger vehicle. By combining all the vehicle information vectors, a set of information vectors is formed, which is then used as the passenger vehicle information.

[0035] In this embodiment, generating multiple passenger vehicle capacity units based on the passenger vehicle information can be achieved through the following steps: Feature extraction is performed on the passenger vehicle information to obtain multiple vehicle capacity features; For each vehicle's capacity characteristics, a corresponding vehicle capacity unit is generated based on the vehicle capacity characteristics, thereby obtaining multiple passenger vehicle capacity units.

[0036] In specific implementation, firstly, feature extraction is performed on the passenger vehicle information to obtain multiple vehicle capacity features. That is, for each passenger vehicle, the capacity feature can be obtained by subtracting the current number of passengers carried by the vehicle from its rated passenger capacity. The current working status of the vehicle is numerically encoded: 1 for working and 0 for idle, to obtain the working status feature. Thus, the vehicle ID, capacity feature, vehicle model, working status feature, and current coordinates of the passenger vehicle are used as the vehicle capacity features of the passenger vehicle, thereby obtaining multiple vehicle capacity features. Then, for each vehicle capacity feature, a corresponding vehicle capacity unit is generated based on the vehicle capacity feature, thereby obtaining multiple vehicle capacity units for passenger vehicles. That is, for each passenger vehicle, a basic capacity unit for the passenger vehicle is generated, including: basic identifier, vehicle capacity, location information, and vehicle status. The vehicle capacity features of the passenger vehicle are mapped to the basic capacity unit to obtain the vehicle capacity unit of the passenger vehicle, thereby obtaining multiple vehicle capacity units for passenger vehicles.

[0037] In practical implementation, an adaptive capacity map of passenger vehicle operation is constructed based on all vehicle capacity units. That is, the urban area can be divided into regular grids, and all virtual stations can be marked in the regular grids to obtain a passenger map. Then, each vehicle capacity unit is marked in the passenger map. In other words, the vehicle capacity features are mapped in the form of text boxes in each vehicle capacity unit. The ball with the working status feature of 0 is marked as green, and the ball with the working status feature of 1 is marked as red. Each vehicle capacity unit and each virtual station is updated in real time to obtain an adaptive capacity map of passenger vehicle operation.

[0038] Preferably, in this embodiment, passenger matching is performed on the dynamic passenger corridor set based on the adaptive capacity map to generate each passenger response unit of the dynamic route, with reference to... Figure 3 As shown in the figure, this is a flowchart illustrating the various passenger response units for generating dynamic bus routes in some embodiments of this application. The various passenger response units for generating dynamic bus routes in this embodiment can be implemented using the following steps: In step S31, a passenger transport efficiency matrix is ​​constructed using the adaptive capacity map and the dynamic passenger transport corridor set; In step S32, a passenger matching scheme is determined based on the passenger efficiency matrix; In step S33, each passenger response unit of the dynamic route is generated according to the passenger matching scheme.

[0039] In practical implementation, firstly, a passenger transport efficiency matrix can be constructed using an adaptive capacity map and a dynamic passenger transport corridor set. Specifically, for each dynamic passenger transport corridor in the dynamic passenger transport corridor set, the Euclidean distance between the starting virtual station in the dynamic passenger transport corridor and the coordinates of each vehicle capacity unit in the adaptive capacity map is calculated to obtain the distance from each vehicle capacity unit to the starting virtual station of the dynamic passenger transport corridor. Then, its exponential decay function is calculated to obtain the spatial matching degree of each vehicle capacity unit. Finally, the capacity feature of each vehicle capacity unit is divided by the required capacity value, and the result is used as the capacity matching degree of each vehicle capacity unit. When the value is greater than 1, it is set to 1. For each vehicle capacity unit of the dynamic passenger corridor, the spatial matching degree and capacity matching degree of the vehicle capacity unit of the dynamic passenger corridor are multiplied, the result is divided by 2, and the result is used as the matching efficiency value. This gives the matching efficiency value of each vehicle capacity unit of the dynamic passenger corridor. Thus, the matching efficiency values ​​of each vehicle capacity unit corresponding to all dynamic passenger corridors are obtained. All the matching efficiency values ​​can then be used as matrix elements to construct a passenger transport efficiency matrix. Then, the passenger transport matching scheme can be determined based on the passenger transport efficiency matrix. That is, for each dynamic passenger corridor in the dynamic passenger corridor set... The process involves sorting all matching efficiency values ​​corresponding to the dynamic passenger corridor in the passenger transport efficiency matrix from largest to smallest. The vehicle capacity unit corresponding to the highest-ranked matching efficiency value is extracted and marked as the matching unit of that dynamic passenger corridor. Then, the capacity characteristics of this matching unit are compared with the required capacity value of the dynamic passenger corridor. If the capacity characteristic is greater than the required capacity value, unit matching for that dynamic passenger corridor stops; if the capacity characteristic is less than the required capacity value, unit matching continues until the required capacity value of the dynamic passenger corridor is less than the sum of the capacity characteristics of all matching units. This yields the required capacity of the dynamic passenger corridor. There are matching units, thus obtaining each matching unit of the dynamic passenger transport corridor set. The dynamic passenger transport corridor set and the corresponding matching units are used as passenger transport matching schemes. Finally, each passenger transport response unit of the dynamic route can be generated according to the passenger transport matching scheme. That is, for each dynamic passenger transport corridor in the dynamic passenger transport corridor set, the dynamic passenger transport corridor is associated with each corresponding matching unit. The departure timetable is generated according to the matching efficiency value of each matching unit. The larger the matching efficiency value, the earlier the departure time. All passenger vehicles in the departure timetable of the dynamic passenger transport corridor are used as passenger transport response units, thus obtaining each passenger transport response unit of the dynamic route.

[0040] It should be noted that in this application, the passenger efficiency matrix is ​​used to describe the matching suitability between each dynamic passenger corridor in the dynamic passenger corridor set and each available capacity unit; the passenger response unit refers to all schedulable entities in the dynamic passenger system that perform a passenger transport task. In step S4, a vehicle dispatch instruction package for dispatching passenger vehicles is generated based on each passenger response unit.

[0041] In this embodiment, generating a vehicle dispatch instruction package for dispatching passenger vehicles based on each passenger response unit can be achieved through the following steps: Extract the spatiotemporal task chain of each passenger response unit; The vehicle dispatch instruction package for dispatching passenger vehicles is generated based on the spatiotemporal task chain of each passenger transport response unit.

[0042] In specific implementation, firstly, the spatiotemporal task chain of each passenger transport response unit is extracted. That is, for each passenger transport response unit, all timestamps of the passenger transport response unit are extracted, the current vehicle position and timestamp t1 are extracted, the historical average driving speed of the passenger vehicle is obtained, the timestamp t2 when the vehicle arrives at the starting virtual station of the corresponding dynamic passenger transport corridor from the current position is calculated, and then the timestamp t3 when the vehicle arrives at the ending virtual station of the dynamic passenger transport corridor is calculated. The empty-running transfer time is obtained by subtracting t1 from t2, and the passenger-carrying service time is obtained by subtracting t2 from t3. Thus, the spatiotemporal task chain of the passenger transport response unit is obtained, such as: Task: Empty-running transfer, required time: [t1, t2]; Task: Passenger transport service, required time: [t2, t3], thus obtaining the spatiotemporal task chain of each passenger transport response unit. It should be noted that the spatiotemporal task chain is a driving prediction of passenger vehicles based on historical driving speeds. Then, a vehicle dispatch instruction package for dispatching passenger vehicles can be generated based on the spatiotemporal task chain of each passenger transport response unit. That is, based on the spatiotemporal task chain of each passenger transport response unit, each spatiotemporal task chain can be converted into a vehicle dispatch instruction, such as: current time t1, current coordinates, current task (empty shuttle), start time t1, and end time t2. Thus, the vehicle dispatch instructions of each spatiotemporal task chain are merged into a set to generate a vehicle dispatch instruction package for dispatching each passenger vehicle.

[0043] Therefore, this application demonstrates two key advantages: First, by collecting the travel needs of each target passenger in real time and cleaning the information, duplicate and abnormal demand data can be effectively eliminated, improving the accuracy and completeness of the travel demand data. This results in a high-quality set of travel demands, providing a reliable data foundation for subsequent passenger flow analysis, route aggregation, and passenger transport scheduling. Second, by acquiring historical passenger flow route sets and combining them with the real-time generated travel demand sets for route aggregation analysis, the distribution patterns of passenger flow in time and space can be uncovered. Demands with similar travel characteristics can be grouped into responsive passenger flow clusters, and passenger corridors for passenger vehicles can be dynamically determined accordingly. This avoids the limitations of fixed-route scheduling and improves the rationality of passenger flow organization and vehicle operation routes. Dynamic adaptability enhances overall passenger transport service efficiency. Then, by acquiring real-time information on each passenger vehicle and generating corresponding vehicle capacity units, an adaptive capacity map is constructed. Combined with dynamic passenger corridor sets for passenger matching, this comprehensively reflects the real-time distribution and changing status of capacity resources, achieving precise matching between capacity and passenger demand. This avoids uneven capacity allocation and scheduling delays, thereby enhancing the passenger transport system's adaptability to dynamic passenger flow changes. Finally, by generating corresponding vehicle scheduling instruction packages based on each passenger response unit, passenger matching results can be directly converted into executable scheduling instructions, enabling rapid and accurate vehicle scheduling. This ensures the timeliness and consistency of scheduling decisions, thereby improving the overall operational efficiency of the passenger transport system.

[0044] In summary, the technical solution adopted in this application can effectively improve the real-time performance and accuracy of passenger transport scheduling, and enhance the adaptability and service response capabilities of passenger transport resources to changes in passenger flow.

[0045] Example 2: This application provides a dynamic scheduled passenger transport resource matching system based on a cloud platform, referencing... Figure 4 As shown in the figure, this is a modular structure diagram of a dynamic scheduled passenger transport resource matching system based on a cloud platform according to this embodiment of the present application. The matching system includes: The demand acquisition module 100 is used to acquire all passenger travel demand information in the cloud platform in real time, clean the data of all passenger travel demand information, and then generate a travel demand set. The corridor determination module 200 is used to obtain a set of historical passenger flow routes, aggregate routes based on the set of historical passenger flow routes and the set of travel demands, obtain various responsive passenger flow clusters for passenger travel, and then generate a dynamic set of passenger transport corridors for passenger vehicle travel through various responsive passenger flow clusters. The passenger transport response module 300 is used to acquire passenger vehicle information in the cloud platform in real time, generate multiple passenger vehicle capacity units based on the passenger vehicle information, construct an adaptive capacity map of passenger vehicle operation based on all vehicle capacity units, perform passenger transport matching on the dynamic passenger transport corridor set based on the adaptive capacity map, and generate each passenger transport response unit of the dynamic route. The instruction generation module 400 is used to generate vehicle dispatch instruction packages for dispatching passenger vehicles based on each passenger response unit.

[0046] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0047] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compactdisc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0048] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

Claims

1. A dynamic bus line passenger transport resource matching method based on a cloud platform, characterized in that, The matching method includes the following steps: Real-time acquisition of all passenger travel demand information from the cloud platform, data cleaning of all passenger travel demand information, and generation of travel demand set; Obtain the historical passenger flow route set, aggregate routes based on the historical passenger flow route set and the travel demand set to obtain various responsive passenger flow clusters, and then generate a dynamic passenger transport corridor set for passenger vehicle travel through each responsive passenger flow cluster. Real-time acquisition of passenger vehicle information from the cloud platform; generation of multiple passenger vehicle capacity units based on the passenger vehicle information; construction of an adaptive capacity map of passenger vehicle operation based on all vehicle capacity units; passenger matching of the dynamic passenger corridor set based on the adaptive capacity map; generation of various passenger response units for dynamic routes. Vehicle dispatch instruction packages for dispatching passenger vehicles are generated based on each passenger transport response unit.

2. The dynamic bus line passenger resource matching method based on a cloud platform according to claim 1, characterized in that, Real-time acquisition of all passenger travel demand information from the cloud platform is achieved by deploying a set of microservices on the cloud platform to acquire all passenger travel demand information from the cloud platform in real time.

3. The dynamic bus line passenger resource matching method based on a cloud platform according to claim 1, characterized in that, Based on the historical passenger flow route set and the travel demand set, route aggregation is performed to obtain various passenger flow clusters that respond to passenger travel, specifically including: Feature extraction is performed on the travel demand set to obtain feature vectors for each demand; Based on the historical passenger flow route set and various demand feature vectors, similarity matching is performed to obtain the similarity of each passenger flow. Each response passenger flow cluster is determined based on the similarity of each passenger flow.

4. The dynamic bus line passenger resource matching method based on a cloud platform according to claim 1, characterized in that, The dynamic passenger corridor set generated from each responding passenger flow cluster specifically includes: For each responding passenger flow cluster, multiple virtual sites are constructed based on the responding passenger flow cluster, thereby obtaining all the virtual sites constructed for each responding passenger flow cluster; Corridor capacity planning is performed on all virtual sites to obtain multiple corridor capacity demands; A dynamic set of passenger corridors is generated based on all corridor capacity demands.

5. The dynamic bus line passenger resource matching method based on a cloud platform according to claim 1, characterized in that, The dynamic passenger corridor set refers to a set of passenger routes that includes passenger demand.

6. The dynamic scheduled passenger transport resource matching method based on a cloud platform as described in claim 1, characterized in that, Generating multiple passenger vehicle capacity units based on the passenger vehicle information specifically includes: Feature extraction is performed on the passenger vehicle information to obtain multiple vehicle capacity features; For each vehicle's capacity characteristics, a corresponding vehicle capacity unit is generated based on the vehicle capacity characteristics, thereby obtaining multiple passenger vehicle capacity units.

7. The dynamic scheduled passenger transport resource matching method based on a cloud platform as described in claim 1, characterized in that, Based on the adaptive capacity map, passenger transport matching is performed on the dynamic passenger transport corridor set to generate dynamic bus routes. Specifically, each passenger transport response unit includes: A passenger transport efficiency matrix is ​​constructed using the adaptive capacity map and the dynamic passenger transport corridor set. Determine the passenger matching scheme based on the passenger efficiency matrix; The dynamic route's various passenger response units are generated based on the passenger matching scheme.

8. The dynamic scheduled passenger transport resource matching method based on a cloud platform as described in claim 1, characterized in that, The passenger transport response unit refers to all schedulable entities in a dynamic passenger transport system that perform a single passenger transport task.

9. The dynamic scheduled passenger transport resource matching method based on a cloud platform as described in claim 1, characterized in that, The vehicle dispatch instruction package generated based on each passenger transport response unit specifically includes: Extract the spatiotemporal task chain of each passenger response unit; The vehicle dispatch instruction package for dispatching passenger vehicles is generated based on the spatiotemporal task chain of each passenger transport response unit.

10. A cloud-based dynamic scheduled passenger transport resource matching system, used to execute the cloud-based dynamic scheduled passenger transport resource matching method as described in any one of claims 1 to 9, characterized in that, The matching system includes: The demand acquisition module is used to acquire all passenger travel demand information in the cloud platform in real time, clean the data of all passenger travel demand information, and then generate a travel demand set. The corridor determination module is used to obtain the historical passenger flow route set, perform route aggregation based on the historical passenger flow route set and the travel demand set, obtain each responding passenger flow cluster, and then generate a dynamic passenger transport corridor set for passenger vehicle travel through each responding passenger flow cluster. The passenger transport response module is used to acquire passenger vehicle information from the cloud platform in real time, generate multiple passenger vehicle capacity units based on the passenger vehicle information, construct an adaptive capacity map of passenger vehicle operation based on all vehicle capacity units, perform passenger transport matching on the dynamic passenger transport corridor set based on the adaptive capacity map, and generate each passenger transport response unit of the dynamic route. The instruction generation module is used to generate vehicle dispatch instruction packages for dispatching passenger vehicles based on each passenger transport response unit.

Images