A method and system for dynamic scheduling of shared electric bicycles based on an intelligent scheduling model

Abstract

This invention discloses a dynamic scheduling method and system for shared electric bicycles based on an intelligent scheduling model. The method includes: acquiring the three-frequency positioning signals of the shared electric bicycles; performing ionospheric error elimination processing using a pre-constructed ionospheric error elimination model; obtaining electric bicycle positioning information by combining multipath interference compensation; acquiring real-time road traffic data and analyzing traffic flow spatial dependence to construct a three-dimensional traffic state network; predicting congestion trends for future periods using the three-dimensional traffic state network to obtain real-time traffic condition prediction data; predicting vehicle demand for future periods based on real-time and historical vehicle demand using an intelligent scheduling model; generating a vehicle scheduling plan by combining electric bicycle positioning information; and planning and optimizing scheduling routes based on real-time traffic condition prediction data and the vehicle scheduling plan to generate the optimal vehicle scheduling route that conforms to real-time traffic conditions. This method improves the adaptability between shared electric bicycle scheduling plans and vehicle demand.

Description

Technical Field

[0001] This invention relates to the technical field of electric bicycle scheduling, and in particular to a dynamic scheduling method and system for shared electric bicycles based on an intelligent scheduling model. Background Technology

[0002] Currently, the efficient scheduling and dynamic optimization of shared mobility resources have become an important part of modern urban transportation. With the promotion of green transportation, shared electric bicycles, as one of the important tools of green transportation, face a significant challenge in terms of how to rationally schedule them.

[0003] The scheduling problem of shared electric bicycles refers to how to allocate vehicles to areas with high demand as much as possible, allowing users to pick up or park nearby, while ensuring a balanced distribution of vehicles within the area to avoid situations where some areas have an oversupply of vehicles and others have a shortage. Current shared electric bicycle scheduling methods are usually based on data statistics or manual judgment. However, the demand for shared electric bicycles changes dynamically with changes in users, areas, and traffic conditions. Scheduling methods that rely on human experience and static data are difficult to cope with real-time demand fluctuations in complex traffic scenarios, resulting in uneven vehicle distribution, high empty running rates, and poor user experience. For example, shared electric bicycles often experience "tidal" supply and demand imbalances during peak hours, making it difficult for users to find vehicles. Furthermore, vehicle scheduling requires manual intervention and cannot adapt well to the dynamic changes in vehicle demand. Summary of the Invention

[0004] To address the problem that existing electric bicycle dispatching methods cannot effectively adapt to dynamically changing user needs, this application provides a shared electric bicycle dynamic dispatching method and system based on an intelligent dispatching model. This method can comprehensively analyze user needs and traffic conditions by constructing an intelligent dispatching model, predict future electric bicycle usage demand, and make vehicle dispatching decisions, thereby improving the adaptability between shared electric bicycle dispatching schemes and vehicle demand.

[0005] Firstly, the above-mentioned inventive objective of this application is achieved through the following technical solution: A dynamic scheduling method for shared electric bicycles based on an intelligent scheduling model, the method comprising: The three-frequency positioning signals of shared electric bicycles are obtained, and ionospheric error elimination processing is performed through a pre-constructed ionospheric error elimination model. Combined with multipath interference compensation, the shared electric bicycles are located to obtain electric bicycle positioning information. Real-time road traffic data is acquired and traffic flow spatial dependency analysis is performed to construct a three-dimensional traffic state network. The congestion trend in future time periods is predicted through the three-dimensional traffic state network to obtain real-time traffic prediction data. The pre-trained intelligent scheduling model predicts vehicle demand for future periods based on real-time and historical vehicle demand, and generates a vehicle scheduling plan by combining the electric bicycle location information. Based on the real-time traffic prediction data and the vehicle dispatching scheme, the dispatching routes of electric bicycles are planned and optimized to generate the optimal vehicle dispatching routes that conform to the real-time traffic conditions.

[0006] In a preferred embodiment, this application can be further configured as follows: the step of planning and optimizing the dispatching routes of electric bicycles based on the real-time traffic prediction data and the vehicle dispatching scheme to generate the optimal vehicle dispatching route that conforms to the real-time traffic conditions includes: According to the vehicle dispatching plan, obtain the idle vehicle data of several dispatching points closest to the target vehicle location, select the target dispatching points based on the profit maximization objective, and plan the corresponding vehicle dispatching routes; By combining the real-time traffic prediction data, the vehicle dispatching routes for each target dispatching point are optimized to obtain the optimal vehicle dispatching routes that coordinate the use of idle vehicles by multiple target dispatching points and conform to the real-time traffic conditions.

[0007] In a preferred embodiment, this application can be further configured as follows: before the pre-trained intelligent scheduling model predicts vehicle demand for future periods based on real-time and historical vehicle demand, and generates a vehicle scheduling plan in conjunction with the electric bicycle location information, it further includes: Acquire users' historical vehicle usage data and historical regional vehicle usage data, train the data through a hybrid neural network, and analyze user vehicle usage trends and historical regional vehicle usage trends; Based on the user vehicle usage trends and historical regional vehicle usage trends, the correlation between different time points and vehicle demand is comprehensively analyzed, and an intelligent scheduling model is constructed based on the correlation between time points and vehicle demand.

[0008] In a preferred embodiment, this application can be further configured as follows: the pre-trained intelligent scheduling model predicts vehicle demand for future periods based on real-time and historical vehicle demand, and generates a vehicle scheduling scheme by combining the electric bicycle location information, specifically including: The system acquires user vehicle search requests and performs real-time user demand analysis. It then uses the intelligent scheduling model to predict user demand for future time periods and generates vehicle demand prediction results based on users. The system obtains historical vehicle demand within a defined area, uses the intelligent scheduling model to predict user demand for future periods, and generates a vehicle demand prediction result based on the region. The vehicle demand forecast results based on users and the vehicle demand forecast results based on regions are comprehensively analyzed to verify the vehicle forecast results, and a vehicle dispatching plan is generated by combining the electric bicycle location information.

[0009] In a preferred embodiment, this application can be further configured as follows: acquiring real-time road traffic data and performing traffic flow spatial dependency analysis, constructing a three-dimensional traffic state network, and predicting congestion trends for future periods through the three-dimensional traffic state network to obtain real-time traffic prediction data, specifically includes: Real-time road traffic data is acquired and spatial dependency analysis of traffic flow is performed based on graph neural networks to construct a three-dimensional traffic state network. The real-time road traffic data includes road segment speed, lane occupancy rate, and queue length. Historical road traffic data is acquired, and based on the current road traffic data and the historical road traffic data, the congestion trend for future periods is predicted through the three-dimensional traffic state network to obtain real-time traffic prediction data.

[0010] In a preferred embodiment, this application can be further configured as follows: before obtaining the tri-frequency positioning signal of the shared electric bicycle, performing ionospheric error elimination processing through a pre-constructed ionospheric error elimination model, and locating the shared electric bicycle in conjunction with multipath interference compensation to obtain the electric bicycle positioning information, the following steps are included: The Beidou tri-frequency positioning signals of shared electric bicycles are acquired and preprocessed. An ionospheric error elimination model is constructed based on the ionospheric delay equation, and the preprocessed tri-frequency positioning signals are subjected to ionospheric error elimination processing. Obtain the BeiDou three-frequency observation values ​​of shared electric bicycles, calculate the ionospheric relative delay of the BeiDou three-frequency observation values, set up a multipath estimation delay-locked loop, and optimize the ionospheric error elimination model.

[0011] In a preferred embodiment, this application can be further configured as follows: The acquisition of the three-frequency positioning signal of the shared electric bicycle, the ionospheric error elimination processing through a pre-constructed ionospheric error elimination model, and the positioning of the shared electric bicycle by combining multipath interference compensation to obtain the electric bicycle positioning information specifically include: The three-frequency positioning signals of the shared electric bicycle are acquired in real time and input into the ionospheric error elimination model for preliminary ionospheric error elimination processing to obtain dual-frequency positioning data of the shared electric bicycle with ionospheric error elimination. The timing deviation compensation process for the dual-frequency positioning data is performed by the multipath estimation delay-locked loop, and the shared electric bicycle is located based on the compensated dual-frequency positioning data to obtain the electric bicycle positioning information fused from the multi-frequency data.

[0012] Secondly, the above-mentioned inventive objective of this application is achieved through the following technical solutions: A shared electric bicycle dynamic scheduling system based on an intelligent scheduling model, the system being applied to the aforementioned shared electric bicycle dynamic scheduling method based on an intelligent scheduling model, the system comprising: The vehicle positioning module is used to acquire the three-frequency positioning signals of the shared electric bicycle, perform ionospheric error elimination processing through a pre-built ionospheric error elimination model, and combine multipath interference compensation to locate the shared electric bicycle and obtain the electric bicycle positioning information. The traffic prediction module is used to acquire real-time road traffic data and perform spatial dependency analysis of traffic flow, construct a three-dimensional traffic state network, and predict the congestion trend in future time periods through the three-dimensional traffic state network to obtain real-time traffic prediction data. The vehicle dispatching module is used to predict vehicle demand for future periods based on real-time and historical vehicle demand using a pre-trained intelligent dispatching model, and to generate a vehicle dispatching plan by combining the electric bicycle location information. The route optimization module is used to plan and optimize the dispatch routes of electric bicycles based on the real-time traffic prediction data and the vehicle dispatch plan, and generate the optimal vehicle dispatch route that conforms to the real-time traffic conditions.

[0013] Thirdly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-described dynamic scheduling method for shared electric bicycles based on an intelligent scheduling model.

[0014] Fourthly, the above-mentioned objectives of this application are achieved through the following technical solutions: A computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described dynamic scheduling method for shared electric bicycles based on an intelligent scheduling model.

[0015] In summary, this application includes at least one of the following beneficial technical effects: 1. This application uses an ionospheric error elimination model to process the three-frequency positioning signals of shared electric bicycles to eliminate ionospheric errors. Combined with multipath interference compensation technology, it achieves accurate positioning of shared electric bicycles and obtains accurate electric bicycle positioning information. In addition, it constructs a three-dimensional traffic state network based on actual road traffic data and traffic flow spatial dependence to analyze congestion trends in future time periods, so that the vehicle scheduling plan is consistent with the actual road conditions. Combined with an intelligent scheduling model, it predicts the vehicle demand in future time periods based on actual user demand and historical vehicle demand. Combined with electric bicycle positioning information, it generates a vehicle scheduling plan, which can adapt to dynamic user demand and improve the adaptability between the scheduling plan and vehicle demand. Furthermore, it combines real-time road conditions and vehicle scheduling plan to perform scheduling route planning and optimization, generating the optimal vehicle scheduling route that conforms to the actual road conditions and improving the rationality of vehicle scheduling route planning. 2. This application prioritizes the selection of available vehicle data from multiple nearest dispatch points based on the vehicle demand of the target location, and filters the target dispatch points and plans corresponding vehicle dispatch routes based on the goal of maximizing profits. By dynamically calling available vehicles from one or more dispatch points, each location can be dispatched in a timely manner to meet the vehicle demand. Furthermore, by combining real-time traffic prediction data, the vehicle dispatch routes are optimized so that when multiple target dispatch points coordinate to dispatch available vehicles, profits can be maximized and the vehicle demand of the location can be met. 3. This application also performs ionospheric error elimination processing on the BeiDou positioning phase signal of shared electric bicycles through an ionospheric error elimination model, calculates the relative ionospheric delay through three-frequency observations, and sets up a multipath estimation delay lock-in loop to reduce interference between multipath errors and improve positioning accuracy. The setting of the multipath estimation delay lock-in loop makes the positioning of the ionospheric error elimination model more accurate. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the accompanying drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to scale.

[0017] Figure 1 This is a flowchart illustrating the implementation of the shared electric bicycle dynamic scheduling method based on an intelligent scheduling model in this embodiment.

[0018] Figure 2 This is a flowchart illustrating the implementation of step S10 of the shared electric bicycle dynamic scheduling method in this embodiment.

[0019] Figure 3 This is a flowchart illustrating the implementation of step S20 of the shared electric bicycle dynamic scheduling method in this embodiment.

[0020] Figure 4 This is a flowchart illustrating the implementation of step S30 of the shared electric bicycle dynamic scheduling method in this embodiment.

[0021] Figure 5 This is a flowchart illustrating the implementation of step S40 of the shared electric bicycle dynamic scheduling method in this embodiment.

[0022] Figure 6 This is a structural block diagram of the shared electric bicycle dynamic scheduling system based on the intelligent scheduling model in this embodiment.

[0023] Figure 7 This is a schematic diagram of the internal structure of a computer device used to implement a dynamic scheduling method for shared electric bicycles. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0026] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this 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.

[0027] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0028] In one embodiment, such as Figure 1 As shown, this application discloses a dynamic scheduling method for shared electric bicycles based on an intelligent scheduling model, which specifically includes the following steps: S10: Obtain the three-frequency positioning signals of the shared electric bicycle, perform ionospheric error elimination processing through a pre-constructed ionospheric error elimination model, and combine multipath interference compensation to locate the shared electric bicycle and obtain the electric bicycle positioning information.

[0029] Specifically, such as Figure 2 As shown, this embodiment includes the following steps before locating the electric bicycle: S101: Acquire the BeiDou tri-frequency positioning signal of the shared electric bicycle and perform data preprocessing. Construct an ionospheric error elimination model based on the ionospheric delay equation, and perform ionospheric error elimination processing on the preprocessed tri-frequency positioning signal.

[0030] Specifically, the three-frequency positioning signals B1I / B2a / B3I are acquired by BeiDou-3 satellites and preprocessed such as cycle slip detection. An ionospheric error elimination model is constructed based on the ionospheric delay equation, and the ionospheric error elimination process is applied to the preprocessed three-frequency positioning signals using the ionospheric error elimination model.

[0031] The ionospheric delay equation is shown in equation (1): (1) in, Indicates dual-frequency observations. Represents the relative ionospheric delay factor. express Frequency band signals, express Frequency band signal.

[0032] Furthermore, the observation values ​​between each pair of the three-frequency positioning signals are calculated using formula (1), and differential processing technology is used to perform differential processing on the three-frequency observation values ​​of the same period to eliminate the ionospheric error between the three-frequency positioning signals.

[0033] S102: Obtain the BeiDou three-frequency observation values ​​of shared electric bicycles, calculate the ionospheric relative delay of the BeiDou three-frequency observation values, set up a multipath estimation delay-locked loop, and optimize the ionospheric error elimination model.

[0034] Specifically, using BeiDou three-frequency observations, the ground vertical ionospheric delay of satellite signals in different frequency bands is calculated using the Klobuchar model. The relative delay between each pair of observations is calculated to set the estimated delay of the corresponding path, and the setting parameters of the multipath estimation locking delay loop are obtained. The multipath estimation locking delay loop is superimposed on the ionospheric error elimination model to double lock the ionospheric error elimination results, optimize the model, and complete the training of the ionospheric error elimination model.

[0035] In this embodiment, step S10 includes: S103: Real-time acquisition of the three-frequency positioning signals of shared electric bicycles, input into the ionospheric error elimination model for ionospheric error elimination processing, and obtain the three-frequency positioning data of shared electric bicycles with ionospheric error elimination.

[0036] Specifically, the three-frequency positioning signals of shared electric bicycles are acquired in real time through the BeiDou satellite positioning system. These signals are then input into the ionospheric error elimination model for ionospheric error elimination processing. The ionospheric error is eliminated by calculating the observed values ​​and using differential processing, resulting in the three-frequency positioning data of the shared electric bicycles after ionospheric error elimination.

[0037] S104: The timing deviation of the three-frequency positioning data is compensated by multipath estimation delay-locked loop. The shared electric bicycle is located based on the compensated three-frequency positioning data to obtain the electric bicycle positioning information fused by multi-frequency data.

[0038] Specifically, a pre-set multipath estimation delay lock-in loop is used to perform relative estimation delay calculation on the three-frequency positioning data and corresponding timing deviation compensation, so that the compensated three-frequency positioning data eliminates timing deviations, achieves accurate positioning of shared electric bicycles, and obtains electric bicycle positioning information fused from multi-frequency data.

[0039] S20: Acquire real-time road traffic data and perform spatial dependency analysis of traffic flow, construct a three-dimensional traffic state network, predict congestion trends in future periods through the three-dimensional traffic state network, and obtain real-time traffic prediction data.

[0040] Specifically, such as Figure 3 As shown, step S20 includes: S201: Acquire real-time road traffic data and perform spatial dependency analysis of traffic flow based on graph neural networks to construct a three-dimensional traffic state network. The real-time road traffic data includes road segment speed, lane occupancy rate, and queue length.

[0041] Specifically, real-time road traffic data, including road segment speed, lane occupancy, and queue length, are acquired to construct a three-dimensional traffic state network. Based on graph neural networks, the spatial dependence of traffic flow is analyzed and modeled to form a three-dimensional traffic state network.

[0042] S202: Obtain historical road traffic data, and based on current and historical road traffic data, predict congestion trends for future periods through a three-dimensional traffic state network to obtain real-time traffic prediction data.

[0043] Specifically, using historical and current road traffic data as reference samples, the three-dimensional traffic state network is analyzed for road congestion at different time points, and the road traffic characteristics corresponding to each time point are formed. When the current road traffic situation reaches the corresponding time point, the road traffic characteristics summarized from historical road traffic data are used as the congestion trend prediction results for future periods, thus obtaining real-time traffic prediction data.

[0044] S30: Based on real-time and historical vehicle demand, a pre-trained intelligent scheduling model is used to predict vehicle demand for future periods and generate a vehicle scheduling plan by combining the location information of electric bicycles.

[0045] Specifically, such as Figure 4 As shown, before generating the vehicle dispatching plan, the following steps are also included: S301: Acquire user's historical vehicle usage data and historical regional vehicle usage data, train the data through a hybrid neural network, and analyze user's vehicle usage trends and historical regional vehicle usage trends.

[0046] Specifically, based on historical user usage data obtained from the user side and historical regional usage data obtained from popular deployment areas, a hybrid neural network combining LSTM and GNN is used to analyze user usage trends and historical regional usage trends. The LSTM network is used to analyze usage trends based on usage time and frequency, while the GNN network is used to analyze usage demand or traffic flow in different regions at different time periods.

[0047] S302: Based on user vehicle usage trends and historical regional vehicle usage trends, comprehensively analyze the correlation between different time points and vehicle demand, and build an intelligent scheduling model based on the correlation between time points and vehicle demand.

[0048] Specifically, based on user usage trends and historical regional usage trends, a comprehensive analysis is conducted to determine the relationship between different time points and vehicle demand. This includes user usage habits at different time points and usage habits in each region at different time points. For example, in a certain business district, the usage frequency is highest between 12-2 pm and 6-8 pm. According to historical pedestrian traffic statistics, there are approximately more than 100 shared electric bicycles in circulation. An intelligent scheduling model is constructed based on the relationship between time points and vehicle demand, and special time points such as holidays and important events are marked.

[0049] In this embodiment, step S30 further includes: S303: Obtain user vehicle search requests, perform real-time user demand analysis, predict user demand for future periods through an intelligent scheduling model, and generate user-based vehicle demand prediction results.

[0050] Specifically, by analyzing the user's clicks and dwell time on the shared electric bicycle search page, the system obtains the user's search request. It also performs real-time user demand analysis based on the user's input search page address, including the location, time of use, and distance to the nearest available vehicle. An intelligent scheduling model then predicts future user demand based on this real-time demand. This involves statistically analyzing historical user demand, obtaining usage time and volume for each area or location, and then scheduling the corresponding number of vehicles at the corresponding time point in the future, either with reference to historical usage or within a pre-defined reserved range. This generates a user-based vehicle demand prediction result.

[0051] S304: Obtain historical vehicle demand within the designated area, predict user demand for future periods using an intelligent scheduling model, and generate regional vehicle demand prediction results.

[0052] Specifically, multiple dispatch areas are defined within the electronic fence, such as popular business districts, schools, office buildings, or subway entrances. Historical vehicle demand for each defined area is obtained, including historical vehicle usage and usage time. The relationship between historical vehicle usage and usage time is analyzed through an intelligent dispatch model. At the corresponding time node in the future period, the number of vehicles that can be dispatched within the set reserved range, based on the historical vehicle usage, is used as the result of the user demand prediction for the future period based on the area.

[0053] S305: The vehicle demand forecast results based on users and the vehicle demand forecast results based on regions are comprehensively analyzed to verify the vehicle forecast results and generate a vehicle dispatching plan by combining the location information of electric bicycles.

[0054] Specifically, the system comprehensively analyzes user-based and region-based vehicle demand predictions to obtain the proportion of user-based actual demand predictions to the corresponding region's vehicle demand predictions. If the proportion exceeds a preset threshold, the current vehicle prediction result is verified, and region-based predictions can be used in conjunction with e-bike location information for vehicle dispatching. If the proportion does not exceed the preset threshold, the current vehicle prediction result is not verified, and user-based actual demand predictions will be used as the basis for vehicle dispatching. The vehicle dispatching scheme, based on the vehicle prediction results, obtains the location information of idle vehicles at other dispatch points near or closest to the dispatch location. With the goal of maximizing benefits, it coordinates the dispatching of the predicted number of shared e-bikes from one or more dispatch points to the target dispatch location.

[0055] S40: Based on real-time traffic forecast data and vehicle dispatching plans, perform route planning and optimization for electric bicycles to generate the optimal vehicle dispatching route that conforms to real-time traffic conditions.

[0056] Specifically, such as Figure 5As shown, step S40 includes: S401: Based on the vehicle dispatching plan, obtain the idle vehicle data of several dispatching points closest to the target vehicle location, select the target dispatching point based on the profit maximization objective, and plan the corresponding vehicle dispatching route.

[0057] Specifically, according to the vehicle dispatching plan, the available vehicle data of one or more dispatching points closest to the target vehicle location is obtained. If the available vehicles at a dispatching point meet the vehicle dispatching requirements, that dispatching point is selected first for vehicle dispatching. If the available vehicles at a dispatching point do not meet the vehicle dispatching requirements, the available vehicles at multiple dispatching points are combined in a coordinated manner until the vehicle dispatching requirements are met. Based on the dispatching objective of maximizing profits, that is, minimizing vehicle dispatching costs or minimizing the total dispatching distance, the target dispatching point is selected from all dispatching points, and the corresponding vehicle dispatching route is planned according to the distance and road between the target dispatching point and the target vehicle location.

[0058] S402: Combining real-time traffic prediction data, optimize the vehicle dispatching routes for each target dispatching point to obtain the optimal vehicle dispatching routes that meet real-time traffic conditions and allow multiple target dispatching points to coordinate the use of idle vehicles.

[0059] Specifically, real-time traffic prediction data is obtained during vehicle dispatching, and the vehicle dispatching routes for each target dispatching point are optimized, such as avoiding congested road sections or selecting the least congested road sections. If the cost of dispatching multiple target dispatching points together is lower than the cost of dispatching them individually, then the route of dispatching multiple target dispatching points together is selected. If the cost of dispatching them individually is lower than the cost of dispatching them together, then the route of dispatching each target dispatching point individually is selected. In this way, the optimal vehicle dispatching route that coordinates the dispatching of idle vehicles by multiple target dispatching points and conforms to the actual traffic conditions is obtained.

[0060] 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.

[0061] In one embodiment, a shared electric bicycle dynamic scheduling system based on an intelligent scheduling model is provided. This shared electric bicycle dynamic scheduling system based on an intelligent scheduling model corresponds one-to-one with the shared electric bicycle dynamic scheduling method based on an intelligent scheduling model described in the above embodiments. For example... Figure 6 As shown, this shared electric bicycle dynamic dispatching system based on an intelligent dispatching model includes a vehicle positioning module, a road condition prediction module, a vehicle dispatching module, and a route optimization module. Detailed descriptions of each functional module are as follows: The vehicle positioning module is used to acquire the three-frequency positioning signals of the shared electric bicycles, perform ionospheric error elimination processing through a pre-built ionospheric error elimination model, and combine multipath interference compensation to locate the shared electric bicycles and obtain the electric bicycle positioning information.

[0062] The traffic prediction module is used to acquire real-time road traffic data and perform spatial dependency analysis of traffic flow, construct a three-dimensional traffic state network, and predict congestion trends in future periods through the three-dimensional traffic state network to obtain real-time traffic prediction data.

[0063] The vehicle dispatching module is used to predict vehicle demand for future periods based on real-time and historical vehicle demand using a pre-trained intelligent dispatching model, and to generate a vehicle dispatching plan by combining the location information of electric bicycles.

[0064] The route optimization module is used to plan and optimize the dispatch routes of electric bicycles based on real-time traffic prediction data and vehicle dispatching plans, and generate the optimal vehicle dispatching routes that conform to real-time traffic conditions.

[0065] Preferably, the route optimization module includes: The dispatch point filtering submodule is used to obtain idle vehicle data from several dispatch points closest to the target vehicle location according to the vehicle dispatch plan, filter target dispatch points based on the profit maximization objective, and plan the corresponding vehicle dispatch routes.

[0066] The route optimization submodule is used to combine real-time traffic prediction data to optimize the vehicle dispatching routes for each target dispatching point, and obtain the optimal vehicle dispatching route that meets the real-time traffic conditions and allows multiple target dispatching points to coordinate the use of idle vehicles.

[0067] Preferably, before the vehicle dispatching module, it also includes: The data training submodule is used to acquire users' historical vehicle usage data and historical regional vehicle usage data, and to train the data through a hybrid neural network to analyze users' vehicle usage trends and historical regional vehicle usage trends.

[0068] The model building submodule is used to comprehensively analyze the correlation between different time points and vehicle demand based on user vehicle usage trends and historical regional vehicle usage trends, and to build an intelligent scheduling model based on the correlation between time points and vehicle demand.

[0069] Preferably, the vehicle dispatching module specifically includes: The user demand prediction submodule is used to acquire user vehicle search requests, perform real-time user demand analysis, predict user demand for future periods through an intelligent scheduling model, and generate user-based vehicle demand prediction results.

[0070] The regional demand forecasting submodule is used to obtain historical vehicle demand within a defined region, predict user demand for future periods using an intelligent scheduling model, and generate regional vehicle demand forecasting results.

[0071] The prediction result verification submodule is used to comprehensively analyze the user-based vehicle demand prediction results and the region-based vehicle demand prediction results, verify the vehicle prediction results, and generate a vehicle dispatching plan by combining the electric bicycle location information.

[0072] Preferably, the traffic prediction module specifically includes: The traffic analysis submodule is used to acquire real-time road traffic data and perform spatial dependency analysis of traffic flow based on graph neural networks to construct a three-dimensional traffic state network. The real-time road traffic data includes road segment speed, lane occupancy rate, and queue length.

[0073] The traffic prediction submodule is used to acquire historical road traffic data and predict congestion trends in future periods based on current and historical road traffic data through a three-dimensional traffic state network, thus obtaining real-time traffic prediction data.

[0074] Preferably, before the vehicle positioning module, it includes: The ionospheric error elimination model construction submodule is used to acquire the Beidou three-frequency positioning signals of shared electric bicycles and perform data preprocessing. Based on the ionospheric delay equation, an ionospheric error elimination model is constructed to perform ionospheric error elimination processing on the preprocessed three-frequency positioning signals.

[0075] The model optimization submodule is used to obtain the BeiDou three-frequency observation values ​​of shared electric bicycles, calculate the ionospheric relative delay of the BeiDou three-frequency observation values, set up a multipath estimation delay-locked loop, and optimize the ionospheric error elimination model.

[0076] Preferably, the vehicle positioning module specifically includes: The positioning data acquisition submodule is used to acquire the three-frequency positioning signals of shared electric bicycles in real time, input them into the ionospheric error elimination model for ionospheric error elimination processing, and obtain the three-frequency positioning data of the shared electric bicycles with ionospheric error eliminated.

[0077] The vehicle positioning submodule is used to perform timing deviation compensation processing on the three-frequency positioning data through multipath estimation delay-locked loop, and to locate the shared electric bicycle based on the compensated three-frequency positioning data, so as to obtain the electric bicycle positioning information fused from the multi-frequency data.

[0078] Specific limitations regarding the shared electric bicycle dynamic scheduling system based on the intelligent scheduling model can be found in the limitations of the shared electric bicycle dynamic scheduling method based on the intelligent scheduling model mentioned above, and will not be repeated here. Each module in the aforementioned shared electric bicycle dynamic scheduling system based on the intelligent scheduling model can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0079] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores shared electric bicycle scheduling data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a dynamic scheduling method for shared electric bicycles based on an intelligent scheduling model.

[0080] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements a dynamic scheduling method for shared electric bicycles based on an intelligent scheduling model.

[0081] Those skilled in the art will recognize that the units of the various examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application of the technical solution and the constraints involved. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of the invention.

[0082] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical functional division. In actual implementation, there may be other division methods, such as multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored.

[0083] Furthermore, the functional units in the various embodiments of the present invention 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.

[0084] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them. Although the present invention 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 or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be covered within the scope of the claims and specification of the present invention.

Claims

1. A dynamic scheduling method for shared electric bicycles based on an intelligent scheduling model, characterized in that, The method includes: The three-frequency positioning signals of shared electric bicycles are obtained, and ionospheric error elimination processing is performed through a pre-constructed ionospheric error elimination model. Combined with multipath interference compensation, the shared electric bicycles are located to obtain electric bicycle positioning information. Real-time road traffic data is acquired and traffic flow spatial dependency analysis is performed to construct a three-dimensional traffic state network. The congestion trend in future time periods is predicted through the three-dimensional traffic state network to obtain real-time traffic prediction data. The pre-trained intelligent scheduling model predicts vehicle demand for future periods based on real-time and historical vehicle demand, and generates a vehicle scheduling plan by combining the electric bicycle location information. Based on the real-time traffic prediction data and the vehicle dispatching scheme, the dispatching routes of electric bicycles are planned and optimized to generate the optimal vehicle dispatching routes that conform to the real-time traffic conditions.

2. The shared electric bicycle dynamic scheduling method based on an intelligent scheduling model according to claim 1, characterized in that, The step of planning and optimizing the dispatch routes for electric bicycles based on the real-time traffic prediction data and the vehicle dispatch plan to generate the optimal vehicle dispatch routes that conform to the real-time traffic conditions includes: According to the vehicle dispatching plan, obtain the idle vehicle data of several dispatching points closest to the target vehicle location, select the target dispatching points based on the profit maximization objective, and plan the corresponding vehicle dispatching routes; By combining the real-time traffic prediction data, the vehicle dispatching routes for each target dispatching point are optimized to obtain the optimal vehicle dispatching routes that coordinate the use of idle vehicles by multiple target dispatching points and conform to the real-time traffic conditions.

3. The shared electric bicycle dynamic scheduling method based on an intelligent scheduling model according to claim 1, characterized in that, Before the pre-trained intelligent scheduling model predicts vehicle demand for future periods based on real-time and historical vehicle demand, and generates a vehicle scheduling plan by combining the electric bicycle location information, the following steps are also included: Acquire users' historical vehicle usage data and historical regional vehicle usage data, train the data through a hybrid neural network, and analyze user vehicle usage trends and historical regional vehicle usage trends; Based on the user vehicle usage trends and historical regional vehicle usage trends, the correlation between different time points and vehicle demand is comprehensively analyzed, and an intelligent scheduling model is constructed based on the correlation between time points and vehicle demand.

4. The shared electric bicycle dynamic scheduling method based on an intelligent scheduling model according to claim 3, characterized in that, The pre-trained intelligent scheduling model predicts vehicle demand for future periods based on real-time and historical vehicle demand, and generates a vehicle scheduling plan by combining the electric bicycle location information, specifically including: The system acquires user vehicle search requests and performs real-time user demand analysis. It then uses the intelligent scheduling model to predict user demand for future time periods and generates vehicle demand prediction results based on users. The system obtains historical vehicle demand within a defined area, uses the intelligent scheduling model to predict user demand for future periods, and generates a vehicle demand prediction result based on the region. The vehicle demand forecast results based on users and the vehicle demand forecast results based on regions are comprehensively analyzed to verify the vehicle forecast results, and a vehicle dispatching plan is generated by combining the electric bicycle location information.

5. The shared electric bicycle dynamic scheduling method based on an intelligent scheduling model according to claim 1, characterized in that, The process of acquiring real-time road traffic data and performing spatial dependency analysis of traffic flow to construct a three-dimensional traffic state network, and then using this three-dimensional traffic state network to predict congestion trends in future time periods, thereby obtaining real-time traffic condition prediction data, specifically includes: Real-time road traffic data is acquired and spatial dependency analysis of traffic flow is performed based on graph neural networks to construct a three-dimensional traffic state network. The real-time road traffic data includes road segment speed, lane occupancy rate, and queue length. Historical road traffic data is acquired, and based on the current road traffic data and the historical road traffic data, the congestion trend for future periods is predicted through the three-dimensional traffic state network to obtain real-time traffic prediction data.

6. The shared electric bicycle dynamic scheduling method based on an intelligent scheduling model according to claim 1, characterized in that, Before obtaining the tri-frequency positioning signal of the shared electric bicycle, performing ionospheric error elimination processing through a pre-constructed ionospheric error elimination model, and combining multipath interference compensation to locate the shared electric bicycle, the process includes: The Beidou tri-frequency positioning signals of shared electric bicycles are acquired and preprocessed. An ionospheric error elimination model is constructed based on the ionospheric delay equation, and the preprocessed tri-frequency positioning signals are subjected to ionospheric error elimination processing. Obtain the BeiDou three-frequency observation values ​​of shared electric bicycles, calculate the ionospheric relative delay of the BeiDou three-frequency observation values, set up a multipath estimation delay-locked loop, and optimize the ionospheric error elimination model.

7. The shared electric bicycle dynamic scheduling method based on an intelligent scheduling model according to claim 6, characterized in that, The process involves acquiring the three-frequency positioning signal of the shared electric bicycle, performing ionospheric error elimination processing through a pre-constructed ionospheric error elimination model, and combining this with multipath interference compensation to locate the shared electric bicycle, thereby obtaining the electric bicycle positioning information. Specifically, this includes: The three-frequency positioning signals of the shared electric bicycles are acquired in real time and input into the ionospheric error elimination model for ionospheric error elimination processing to obtain the three-frequency positioning data of the shared electric bicycles with ionospheric error elimination. The multipath estimation delay-locked loop is used to perform timing deviation compensation processing on the three-frequency positioning data. The shared electric bicycle is located based on the compensated three-frequency positioning data to obtain the electric bicycle positioning information fused from the multi-frequency data.

8. A shared electric bicycle dynamic scheduling system based on an intelligent scheduling model, characterized in that, The system is applied to the shared electric bicycle dynamic scheduling method based on the intelligent scheduling model according to any one of claims 1-7, and the system includes: The vehicle positioning module is used to acquire the three-frequency positioning signals of the shared electric bicycle, perform ionospheric error elimination processing through a pre-built ionospheric error elimination model, and combine multipath interference compensation to locate the shared electric bicycle and obtain the electric bicycle positioning information. The traffic prediction module is used to acquire real-time road traffic data and perform spatial dependency analysis of traffic flow, construct a three-dimensional traffic state network, and predict the congestion trend in future time periods through the three-dimensional traffic state network to obtain real-time traffic prediction data. The vehicle dispatching module is used to predict vehicle demand for future periods based on real-time and historical vehicle demand using a pre-trained intelligent dispatching model, and to generate a vehicle dispatching plan by combining the electric bicycle location information. The route optimization module is used to plan and optimize the dispatch routes of electric bicycles based on the real-time traffic prediction data and the vehicle dispatch plan, and generate the optimal vehicle dispatch route that conforms to the real-time traffic conditions.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the shared electric bicycle dynamic scheduling method based on the intelligent scheduling model as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the shared electric bicycle dynamic scheduling method based on the intelligent scheduling model as described in any one of claims 1 to 7.

Images