Track station shared bicycle classification scheduling method based on parking position perception

Abstract

The invention relates to a rail station shared bicycle classification scheduling method based on parking position perception, and the method comprises the steps: monitoring a shared bicycle parking region around a rail station, and obtaining the number, states and operator types of shared bicycles around the rail station in real time through a pre-trained parking position perception model; determining a corresponding operation strategy according to the number and the state of the shared bicycles and the types of operators to which the shared bicycles belong and in combination with the station types of the rail stations; according to the operation strategy, scheduling demands of shared bicycles around the rail station are predicted in real time, and scheduling suggestions are generated; and according to the generated scheduling suggestion, carrying out classified scheduling on the shared bicycles around the rail station. According to the method, efficient classified management and balanced distribution of the shared bicycles are realized through accurate perception and intelligent scheduling, the resource utilization efficiency and the user experience are remarkably improved, the operation cost is reduced, and the urban traffic resource allocation is optimized.

Description

Technical Field

[0001] This invention relates to the fields of intelligent transportation and computer vision technology. Specifically, this invention relates to a method for classifying and scheduling shared bicycles at rail stations based on parking location awareness. Background Technology

[0002] Existing technology 1: A shared bicycle scheduling method and system based on video data, comprising: collecting video data and environmental perception data of shared bicycle parking areas; using a target detection algorithm to detect the video data based on the parking areas to obtain bicycle status data of the parking areas; using a pre-trained Transformer model to perform feature fusion based on the bicycle status data to generate fused feature data; and using a hierarchical reinforcement learning algorithm to generate a scheduling strategy based on the fused feature data and the environmental perception data. This application uses a detection algorithm to monitor and detect the bicycle status of the parking areas in real time, which can quickly obtain information on bicycle status such as idle, locked, and faulty status, thereby adjusting the scheduling strategy in a timely manner and improving scheduling efficiency. By using a hierarchical reinforcement learning algorithm, the scheduling strategy can be dynamically adjusted to optimize bicycle distribution, reduce scheduling delays, and improve resource utilization.

[0003] Existing technology 2: A shared bicycle scheduling optimization method considering the fairness of bicycle allocation between regions, comprising: 1. setting a freely floating set of operating cycles and regions for the shared bicycle system, as well as parameters and variables related to the deterministic scheduling optimization model of shared bicycles; 2. establishing a deterministic scheduling model for shared bicycles; 3. establishing an uncertain scheduling model for shared bicycles considering the randomness of demand; 4. reconstructing the uncertain scheduling model for shared bicycles based on the strong duality principle of second-order cone programming; 5. solving the reconstructed uncertain scheduling model for shared bicycles using a binary search algorithm to obtain the scheduling optimization result. This invention can achieve fairness in bicycle allocation between regions, ensuring that the needs of users in each region are met relatively fairly. At the same time, it focuses on considering the uncertainty of demand, enhancing the adaptability and robustness of the scheduling scheme, thereby reducing the waste of shared bicycle resources and improving the service quality of the shared bicycle system.

[0004] The existing technical solution has the following technical problems: it lacks differentiated response strategies, and the vehicle usage characteristics around different functional locations are different.

[0005] The existing technical solution 2 has the following technical problems: it is not very targeted. In first-tier cities, the management of shared bicycles at rail stations has become a pain point. Summary of the Invention

[0006] The technical problem to be solved by the present invention is to provide a classification and scheduling method for shared bicycles at rail stations based on parking location awareness, which aims to solve at least one of the above-mentioned technical problems.

[0007] Firstly, the technical solution of the present invention to solve the above-mentioned technical problem is as follows: a method for classifying and scheduling shared bicycles at rail stations based on parking location awareness, the method comprising: The system monitors the parking areas of shared bicycles around rail stations and uses a pre-trained parking location awareness model to obtain the number, status, and operator type of shared bicycles around the rail stations in real time. Based on the number, status, and type of operator of shared bicycles, and in combination with the type of rail station, determine the corresponding operation strategy; Based on the operational strategy, the scheduling demand for shared bicycles around rail stations is predicted in real time, and scheduling suggestions are generated. Based on the generated scheduling suggestions, shared bicycles around rail stations are categorized and scheduled accordingly.

[0008] The beneficial effects of this invention are as follows: By using a pre-trained parking location awareness model to monitor the shared bicycle parking areas around rail stations in real time, key information such as the number, status, and operator type of shared bicycles can be accurately obtained, providing a detailed and accurate data foundation for subsequent scheduling decisions. Furthermore, by combining this real-time data with the station type of the rail station to determine the operational strategy, the scheduling scheme can fully meet the specific needs and operational characteristics of different stations, achieving precise and personalized scheduling. Based on the operational strategy, real-time prediction of scheduling needs and generation of scheduling suggestions, this process leverages the model's predictive capabilities to plan scheduling actions in advance, effectively improving the foresight and timeliness of scheduling and avoiding the problem of uneven bicycle distribution caused by scheduling delays. Finally, by classifying and scheduling shared bicycles according to the generated scheduling suggestions, not only is the bicycle distribution around rail stations optimized and resource utilization improved, but user experience is also enhanced, reducing the time and inconvenience for users searching for bicycles. Simultaneously, operating costs are reduced, and overall operational efficiency is improved, providing strong technical support for the efficient management and operation of shared bicycles.

[0009] Based on the above technical solution, the present invention can be further improved as follows.

[0010] Furthermore, the above methods also include: Based on historical operational data and environmental characteristics around rail stations of different station types, extract feature data related to shared bicycle scheduling, including changes in the number of bicycles, tidal characteristics, user demand patterns, and geographic information; Based on different site types and the operator types of shared bicycles in historical operation data, combined with extracted feature data, the demand matching degree and saturation of bicycles of different operator types in different site types in historical operation data are determined. Based on historical operational data on the demand matching and saturation of bicycles of different operator types at different station types, different types of operational strategies are formulated.

[0011] Furthermore, the station types of the aforementioned rail stations are determined based on the following method: Based on the environmental characteristics surrounding the rail station, the station type is determined, which can be any one of the following: office area, residential area, tourist area, commercial area, school area, or mixed area.

[0012] Furthermore, the types of shared bicycle operators around the aforementioned rail stations include at least one of the following: blue operators, yellow operators, green operators, and other non-shared bicycle operators.

[0013] Furthermore, based on the number, status, and operator type of shared bicycles, combined with the station type of the rail transit station, the corresponding operational strategies are determined, including: Based on the station type, analyze the single-vehicle demand patterns and tidal characteristics of the rail stations in different time periods; Based on the operator type of shared bicycles around the rail stations, assess the proportion and distribution of bicycles of each operator type around the rail stations. Based on the bicycle demand patterns and tidal characteristics of rail stations at different time periods, the proportion and distribution of bicycles from different operators, and combined with the number, status and operator type of shared bicycles, the demand matching degree and saturation of shared bicycles from different operators around rail stations are determined. Based on the demand matching degree and saturation of shared bicycles of different operators around the rail stations, the corresponding operation strategies are determined.

[0014] Furthermore, the method also includes: The pre-trained density recognition model is used to monitor the bicycle density in the shared bicycle parking area around the rail station in real time, and to assess the bicycle distribution saturation around the rail station based on the bicycle density. Based on the bicycle demand patterns and tidal characteristics of rail stations at different times, the proportion and distribution of bicycles from different operators, and considering the quantity, status, and operator type of shared bicycles, the demand matching degree and saturation of shared bicycles from different operator types around rail stations are determined, including: Based on the bicycle demand patterns and tidal characteristics of rail stations at different times, the proportion and distribution of bicycles from different operators, and combined with the number, status, operator type, and bicycle distribution saturation around rail stations, the demand matching degree and saturation of bicycles from different operators around rail stations are determined.

[0015] Furthermore, the method also includes: The density of shared bicycles in the parking area around the rail station is monitored in real time using a pre-trained density recognition model. Assess the saturation of bicycle distribution around rail stations based on bicycle density; The operation strategy is dynamically adjusted based on the saturation of bicycle distribution around the rail stations.

[0016] Secondly, to solve the above-mentioned technical problems, the present invention also provides a shared bicycle classification and scheduling device for rail stations based on parking location awareness, the device comprising: The real-time identification module is used to monitor the parking areas of shared bicycles around rail stations. Through a pre-trained parking location perception model, it can obtain the number, status and operator type of shared bicycles around rail stations in real time. The operation strategy determination module is used to determine the corresponding operation strategy based on the number and status of shared bicycles and the type of operator they belong to, combined with the station type of the rail station. The scheduling suggestion generation module is used to predict the scheduling demand of shared bicycles around rail stations in real time based on the operation strategy and generate scheduling suggestions. The classification and scheduling module is used to classify and schedule shared bicycles around rail stations based on the generated scheduling suggestions.

[0017] Thirdly, in order to solve the above-mentioned technical problems, the present invention also provides an electronic device, which 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 shared bicycle classification and scheduling method based on parking location awareness of the present application.

[0018] Fourthly, in order to solve the above-mentioned technical problems, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the shared bicycle classification and scheduling method based on parking location awareness of the present application.

[0019] Additional aspects and advantages of this application will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments of the present invention will be briefly introduced below.

[0021] Figure 1A flowchart illustrating a method for classifying and scheduling shared bicycles at rail stations based on parking location awareness, provided as an embodiment of the present invention; Figure 2 A schematic diagram of an identification frame provided in one embodiment of the present invention; Figure 3 This is a schematic diagram of another identification frame provided in one embodiment of the present invention; Figure 4 This is a schematic diagram of another identification frame provided in one embodiment of the present invention; Figure 5 This is a schematic diagram illustrating the application of an algorithm model according to an embodiment of the present invention; Figure 6 A schematic diagram of a shared bicycle classification and scheduling device at a rail station based on parking location awareness, provided in one embodiment of the present invention; Figure 7 This is a schematic diagram of the structure of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0022] The principles and features of the present invention are described below. The examples given are only for explaining the present invention and are not intended to limit the scope of the present invention.

[0023] The technical solution of the present invention and how the technical solution of the present invention solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0024] The solution provided in this invention can be applied to any application scenario that requires the classification and scheduling of shared bicycles at rail stations. The solution provided in this invention can be executed by any electronic device, such as a user's terminal device, including at least one of the following: smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, smart TV, or smart in-vehicle device.

[0025] This invention provides a possible implementation, such as... Figure 1 The diagram shows a flowchart of a shared bicycle classification and scheduling method based on parking location awareness at rail stations. This scheme can be executed by any electronic device, such as a terminal device, or jointly executed by a terminal device and a server. For ease of description, the method provided in this embodiment will be described below using a terminal device as the execution subject as an example. Figure 1 The flowchart shown indicates that the method may include the following steps: S10 monitors the parking areas of shared bicycles around rail stations. Through a pre-trained parking location perception model, it obtains the number, status, and operator type of shared bicycles around rail stations in real time. S20 determines the corresponding operation strategy based on the number, status, and operator type of shared bicycles, combined with the station type of the rail station; S30, based on the operation strategy, predicts the scheduling demand of shared bicycles around the rail stations in real time and generates scheduling suggestions; S40 classifies and schedules shared bicycles around rail stations based on the generated scheduling suggestions.

[0026] The method of this invention uses a pre-trained parking location awareness model to monitor shared bicycle parking areas around rail stations in real time. This allows for precise acquisition of key information such as the number, status, and operator type of shared bicycles, providing a detailed and accurate data foundation for subsequent scheduling decisions. Furthermore, based on this real-time data and the type of rail station, an operational strategy is determined, enabling the scheduling plan to fully meet the specific needs and operational characteristics of different stations, achieving precise and personalized scheduling. Real-time prediction of scheduling demand and generation of scheduling suggestions based on the operational strategy leverages the model's predictive capabilities to plan scheduling actions in advance, effectively improving the foresight and timeliness of scheduling and avoiding uneven bicycle distribution caused by scheduling delays. Finally, shared bicycles are categorized and scheduled according to the generated scheduling suggestions, optimizing bicycle distribution around rail stations, improving resource utilization, enhancing user experience, reducing time and inconvenience for users searching for bicycles, lowering operating costs, and improving overall operational efficiency. This provides strong technical support for the efficient management and operation of shared bicycles.

[0027] The following specific embodiments further illustrate the solution of the present invention. In this embodiment, the present invention proposes a classification and scheduling method for shared bicycles at rail transit stations based on parking location awareness. By establishing a perception model through video recognition of shared bicycle parking areas around rail transit stations, different types of operation strategies are defined based on historical operation data characteristics and station surrounding environment characteristics. The scheduling trend of shared bicycles is predicted, and scheduling suggestions are provided in real time to solve the problems of uneven distribution and untimely scheduling of shared bicycles.

[0028] Based on this, the shared bicycle classification and scheduling method based on parking location awareness provided in this embodiment may include the following steps: S10 monitors the parking areas of shared bicycles around rail stations. Through a pre-trained parking location perception model, it obtains the number, status, and operator type of shared bicycles around rail stations in real time. The pre-trained parking location awareness model refers to a model pre-trained using deep learning technology. This model can analyze video or image data of shared bicycle parking areas around rail stations to accurately identify the number, status (e.g., idle, in use, faulty), and operator type of shared bicycles in real time. This model is trained using a large amount of labeled data, enabling it to perceive shared bicycle parking conditions in different scenarios. This provides accurate data support for subsequent classification and scheduling, and is a key technological foundation for achieving efficient scheduling.

[0029] Optionally, the operator type of shared bicycles includes at least one of blue operators, yellow operators, green operators, and other non-shared bicycle operators.

[0030] Shared bikes of different operator types can be represented by different probability values. The parking location awareness model outputs multiple bounding boxes, each corresponding to multiple probability values, and each probability value corresponding to an operator type. The operator type corresponding to the highest probability value in each bounding box is determined as the operator type of the shared bike in that bounding box. When multiple different types of shared bikes exist in a single bounding box, the parking location awareness model can represent the mixed situation by outputting the probability value of each operator type. By setting thresholds and proportional allocations, the probability of each operator type of bike existing in the bounding box can be accurately determined, and a reasonable scheduling strategy can be formulated accordingly. This method not only improves the accuracy of identification but also effectively handles complex mixed scenarios, providing reliable data support for the classification and scheduling of shared bikes.

[0031] As an example, for a bounding box, among its various probability values, the probability of a blue operator is 0.60, the probability of a yellow operator is 0.35, the probability of a green operator is 0.03, and the probability of other operators is 0.02. In this case, the bounding box contains two main types of shared bikes: the probability of a blue operator's bike is 0.60, meaning there is a 60% chance that the bike in the box belongs to a blue operator. The probability of a yellow operator's bike is 0.35, meaning there is a 35% chance that the bike in the box belongs to a yellow operator. The probabilities of green operators and other operators are lower (0.03 and 0.02 respectively), suggesting that these two types of bikes are few or almost non-existent in the box. A threshold (e.g., 0.10) can be set, and only operator types with probabilities higher than this threshold are considered significantly present. In this example, both the probabilities of blue and yellow operators are higher than 0.10, so it can be assumed that both blue and yellow operator bikes exist in the box. Therefore, the bounding box can display a mixed probability value of blue and yellow (which could be the average of the probabilities of blue and yellow operators).

[0032] For the identification frames of shared bicycles from different operators, please refer to [link / reference]. Figures 2 to 4 .

[0033] S20 determines the corresponding operation strategy based on the number, status, and operator type of shared bicycles, combined with the station type of the rail station; The operational strategy refers to a set of rules and methods for guiding the dispatch of shared bicycles, comprehensively formulated based on multi-dimensional data such as the type of rail station, the number and status of shared bicycles, the type of operator they belong to, and the real-time monitored bicycle distribution saturation. It aims to optimize bicycle distribution, meet user needs, improve resource utilization, and reduce operating costs. Specifically, the operational strategy dynamically adjusts the dispatch direction, quantity, priority, and timing based on different station types (such as office areas, residential areas, tourist areas, etc.) and the actual distribution of bicycles from various operators, to achieve efficient management and balanced distribution of shared bicycles around rail stations.

[0034] Optionally, the station type of the aforementioned rail stations is determined based on the following method: Based on the environmental characteristics surrounding the rail station, the station type is determined, which can be any one of the following: office area, residential area, tourist area, commercial area, school area, or mixed area.

[0035] The environmental characteristics surrounding rail stations refer to various geographical, social, and usage-related features associated with these stations. These characteristics can influence the demand for shared bicycles, parking needs, and scheduling strategies. Specifically, these include the surrounding area's functions (e.g., office areas, residential areas, tourist areas, commercial areas, school areas), population density, traffic flow, frequency of commercial activities, distribution of public facilities (e.g., parks, hospitals, shopping centers), road network layout, weather conditions, and user behavior patterns. These characteristics collectively determine the demand patterns and parking capacity for shared bicycles at different stations at different times, providing a basis for developing precise operational strategies.

[0036] The stations are divided into five categories: office area, residential area, tourist area, commercial area, school area, and mixed area. On weekdays, the flow of shared bicycles between office and residential areas is distinct, but in opposite directions. During the morning rush hour, the number of shared bicycles at stations in residential areas increases dramatically while the number in office areas decreases sharply; conversely, during the evening rush hour, the number of shared bicycles in residential areas decreases sharply while the number in office areas increases dramatically. On weekends and holidays, the flow of shared bicycles is not distinct.

[0037] Data for tourist areas and commercial districts is inactive on weekdays but active on weekends and holidays.

[0038] The proportion of private bicycles in the school district is high, while the demand is low.

[0039] Prior to S20, it is necessary to establish different types of, i.e., differentiated, operational strategies: Based on historical operational data and environmental characteristics around rail stations of different station types, extract feature data related to shared bicycle scheduling, including changes in the number of bicycles, tidal characteristics, user demand patterns, and geographic information; Based on different site types and the operator types of shared bicycles in historical operation data, combined with extracted feature data, the demand matching degree and saturation of bicycles of different operator types in different site types in historical operation data are determined. Based on historical operational data on the demand matching and saturation of bicycles of different operator types at different station types, different types of operational strategies are formulated.

[0040] Historical operational data refers to various records of information related to bike usage, dispatch, and parking accumulated during the operation of shared bikes. This data covers changes in the number of bikes at each rail station and surrounding area over different time periods, user rental and return records, bike malfunctions, dispatch operation history, and the distribution and flow of bikes from different operators. Analyzing historical operational data can reveal key information such as patterns in user demand, tidal characteristics, bike flow patterns between stations, and the utilization efficiency of bikes from different operators. This provides data support for developing scientific and reasonable operational strategies, helping to optimize bike distribution, improve dispatch efficiency, and better meet user needs.

[0041] Based on different site types and historical operational data on shared bicycle operators, combined with extracted feature data (such as changes in bicycle quantity, tidal characteristics, user demand patterns, and geographical information), a comprehensive assessment of the demand matching degree and saturation of bicycles from different operator types across different site types can be achieved. Demand matching degree is quantified by the ratio of the actual number of bicycles to the number of bicycles requested by users, reflecting the degree of fit between bicycle supply and user demand. Saturation is assessed by the ratio of the actual number of bicycles to the maximum capacity of the parking area, reflecting the utilization of the bicycle parking area. These calculations provide data support for optimizing operational strategies, adjusting the number of bicycles deployed, and determining dispatch direction and timing, thereby improving bicycle utilization efficiency and user satisfaction, and avoiding uneven bicycle distribution.

[0042] Saturation refers to the degree of matching between the actual number of shared bicycles in a certain area or rail station and the user demand in that area. It considers not only the number of bicycles but also user demand patterns and time factors. Specifically, the saturation of bicycles from different operators at various station types can be assessed based on the maximum capacity of bicycle parking areas and the actual number of bicycles. Saturation reflects the usage of bicycle parking areas; a higher saturation indicates a more dense concentration of bicycles in the area, potentially requiring scheduling adjustments.

[0043] Demand matching degree refers to the degree of match between the actual number of shared bicycles around a rail station and the number of bicycles needed by users in that area within a specific time period. It reflects the degree of fit between current bicycle supply and user demand and is an important indicator for evaluating the rationality of operational strategies. Demand matching degree is usually quantified by calculating the ratio of the actual number of bicycles to the number of bicycles needed by users. The closer the ratio is to 1, the higher the demand matching degree, meaning that the bicycle supply and user demand are more matched.

[0044] While formulating different types of operation strategies, we can obtain the demand matching degree and saturation of bicycles of different operator types in different station types, and the correspondence between different types of operation strategies.

[0045] Optionally, S20 above determines the corresponding operation strategy based on the number, status, and operator type of the shared bicycles, combined with the station type of the rail transit station, including: S201, Based on the station type of the rail station, analyze the single-vehicle demand pattern and tidal characteristics of the rail station in different time periods; S202, Based on the operator type of shared bicycles around the rail station, assess the proportion and distribution of bicycles of each operator type around the rail station. S203. Based on the bicycle demand patterns and tidal characteristics of rail stations at different time periods, the proportion and distribution of bicycles of each operator, and combined with the number, status and operator type of shared bicycles, determine the demand matching degree and saturation of bicycles of different operator types among the shared bicycles around rail stations. S204. Based on the demand matching degree and saturation of shared bicycles of different operators around the rail stations, determine the corresponding operation strategy.

[0046] After determining the demand matching degree and saturation of shared bicycles of different operators around rail stations, the corresponding operational strategies for the demand matching degree and saturation of shared bicycles of different operators around rail stations can be determined based on the correspondence between the demand matching degree and saturation of shared bicycles of different operators in different station types and different types of operational strategies.

[0047] Bike demand patterns refer to the patterns and behavioral characteristics of user demand for shared bikes within a specific time period. It reflects user habits and demand intensity across different site types (e.g., office areas, residential areas, tourist areas), time periods (e.g., morning peak, evening peak, off-peak), and weather conditions. Specifically, it includes information such as the frequency of bike rentals and returns, usage duration, riding distance, and popular departure and destination points. By analyzing historical operational and user behavior data, these demand patterns can be identified, providing a basis for developing precise operational strategies, optimizing bike distribution, and improving user satisfaction.

[0048] Tidal characteristics refer to the significant patterns of change in the usage and parking volume of shared bicycles within a specific time period, which are usually closely related to people's daily activity patterns. For example, during the morning rush hour, bicycle usage in residential areas increases significantly as people need to cycle to work, leading to a decrease in the number of bicycles in residential areas and an increase in the number of bicycles in office areas. Conversely, during the evening rush hour, bicycle usage increases in office areas as people cycle back to their residences, resulting in a decrease in the number of bicycles in office areas and an increase in the number of bicycles in residential areas. This periodic change in the number and usage of bicycles within a specific time period is similar to the rise and fall of ocean tides, hence the name tidal characteristics. By analyzing tidal characteristics, user demand can be predicted and met more accurately, bicycle scheduling and distribution can be optimized, and operational efficiency can be improved.

[0049] S30, based on the operation strategy, predicts the scheduling demand of shared bicycles around the rail stations in real time and generates scheduling suggestions; Optionally, based on the operational strategy, the above-mentioned real-time prediction of the dispatch demand of shared bicycles around rail stations and generation of dispatch suggestions include: based on the type of rail station, the number and status of shared bicycles around the rail station, and the type of operator, using a preset prediction model or algorithm, comprehensively considering factors such as tidal characteristics, user demand patterns, and geographical information in historical operational data, dynamically calculating the changing trends of bicycle demand and supply at each station in the future, and then determining which stations need to dispatch bicycles to which stations, as well as the specific dispatch quantity and priority, and finally forming detailed dispatch suggestions to guide subsequent classified dispatch operations and ensure the reasonable distribution and efficient utilization of shared bicycles around rail stations.

[0050] The dynamic calculation of the changing trends in bicycle demand and supply at each station over a future period is achieved through comprehensive analysis of historical operational data, station type characteristics, user behavior patterns, and the current status and distribution of bicycles. Specifically, this process involves the following key steps: First, by leveraging the tidal characteristics and user demand patterns in historical operational data, and combining them with the specific demand patterns of station types (such as office areas, residential areas, and tourist areas), the demand for bicycles at each station during different time periods can be predicted. For example, for office area stations, there is usually a high demand for bicycles during the morning rush hour, while a large number of bicycles are returned during the evening rush hour. By analyzing these patterns in historical data, the trend of bicycle demand changes in similar time periods in the future can be predicted.

[0051] Secondly, considering the number, status, and operator type of shared bikes around the rail stations, and combining this with the parking capacity and real-time bike distribution of the rail stations, the bike supply at each rail station is assessed. Real-time data obtained through a pre-trained parking location awareness model accurately reveals the current number and status of bikes at each rail station, thus providing a basis for supply assessment.

[0052] Then, machine learning algorithms or deep learning models, such as time series forecasting models and Long Short-Term Memory (LSTM) networks, are used to model and predict the changing trends of demand and supply for bicycles. These models can learn complex patterns and regularities in historical data and dynamically output predictions for a future period based on current input data.

[0053] Finally, based on the prediction results and operational strategies, detailed scheduling recommendations are generated. These recommendations include determining which stations to dispatch bicycles to, as well as the specific dispatch quantities and priorities, to ensure the rational distribution and efficient utilization of bicycles. By updating the input data of the prediction model in real time, the scheduling recommendations can be dynamically adjusted to adapt to constantly changing realities, thereby improving the accuracy and timeliness of scheduling.

[0054] S40 classifies and schedules shared bicycles around rail stations based on the generated scheduling suggestions.

[0055] Optionally, based on the generated scheduling suggestions, the shared bicycles around the rail stations are categorized and scheduled accordingly. This includes: implementing differentiated scheduling operations for shared bicycles from different operators based on the scheduling direction, quantity, priority, and time arrangement specified in the scheduling suggestions, combined with the bicycle operator type. Specifically, bicycles are scheduled from stations with high supply or low demand to stations with high demand or insufficient supply, ensuring that the number of bicycles at each station matches user demand. During the scheduling process, high-priority scheduling tasks are prioritized, and scheduling time is rationally arranged to improve scheduling efficiency and reduce user waiting time. Simultaneously, bicycles in good condition are scheduled based on their status (e.g., idle, in use, faulty), avoiding faulty bicycles from affecting user experience. The intelligent scheduling system automatically executes scheduling instructions and monitors scheduling execution in real time, dynamically adjusting the scheduling plan based on actual execution results and feedback information to optimize bicycle distribution and improve overall operational efficiency and service quality.

[0056] Optionally, the method further includes: The pre-trained density recognition model is used to monitor the bicycle density in the shared bicycle parking area around the rail station in real time, and to assess the bicycle distribution saturation around the rail station based on the bicycle density. Based on the bicycle demand patterns and tidal characteristics of rail stations at different times, the proportion and distribution of bicycles from different operators, and combined with the quantity, status, and operator type of shared bicycles, the demand matching degree and saturation of shared bicycles from different operator types around rail stations are determined, including: Based on the bicycle demand patterns and tidal characteristics of rail stations at different times, the proportion and distribution of bicycles from different operators, and combined with the number, status, operator type, and bicycle distribution saturation around rail stations, the demand matching degree and saturation of bicycles from different operators around rail stations are determined.

[0057] Among them, bike distribution saturation refers to the ratio of the actual number of shared bikes in a certain area or station to the maximum number of bikes that the area or station can accommodate. It mainly reflects the density of bike parking in that area.

[0058] Optionally, the method further includes: The density of shared bicycles in the parking area around the rail station is monitored in real time using a pre-trained density recognition model. Assess the saturation of bicycle distribution around rail stations based on bicycle density; The operation strategy is dynamically adjusted based on the saturation of bicycle distribution around the rail stations.

[0059] As an example, see Figure 5The diagram illustrates how this solution identifies the location, density, and brand name (operator type) of shared bicycles around the rail station, specifically the leftmost shared bicycle parking area. Based on this identification, the shared bicycles in the parking area around the rail station can be categorized and dispatched accordingly.

[0060] The solution presented in this invention offers the following advantages: It enables precise classification and scheduling of shared bicycles around rail stations, effectively addressing the issues of uneven bicycle distribution and untimely scheduling. By using a pre-trained parking location awareness model to obtain real-time information on the number, status, and operator type of bicycles, and combining this with station type and historical operational data, differentiated operational strategies are formulated to optimize bicycle distribution and improve resource utilization. Simultaneously, this invention can dynamically predict bicycle scheduling needs and generate real-time scheduling suggestions, ensuring forward-looking and timely scheduling, reducing user waiting time, and improving user experience. Furthermore, the automated execution and real-time monitoring of the intelligent scheduling system further improves scheduling efficiency, reduces operating costs, and enhances the overall operational management level and service quality of the shared bicycle system.

[0061] Based on and Figure 1 Using the same principle as the method shown, this embodiment of the invention also provides a shared bicycle classification and scheduling device 20 based on parking location awareness at rail stations, such as... Figure 6 As shown, the shared bicycle classification and scheduling device 20 based on parking location awareness at rail stations may include a real-time identification module 210, an operation strategy determination module 220, a scheduling suggestion generation module 230, and a classification and scheduling module 240, wherein: The real-time identification module 210 is used to monitor the parking area of ​​shared bicycles around the rail station. Through a pre-trained parking location perception model, it can obtain the number, status and operator type of shared bicycles around the rail station in real time. The operation strategy determination module 220 is used to determine the corresponding operation strategy based on the number, status and operator type of shared bicycles, combined with the station type of the rail station. The scheduling suggestion generation module 230 is used to predict the scheduling demand of shared bicycles around the rail station in real time based on the operation strategy and generate scheduling suggestions. The classification and scheduling module 240 is used to classify and schedule shared bicycles around the rail stations according to the generated scheduling suggestions.

[0062] Optionally, the above-mentioned device further includes: The operation strategy formulation module is used to acquire and extract feature data related to shared bicycle scheduling based on historical operation data and environmental characteristics around rail stations of different station types. This includes changes in the number of bicycles, tidal characteristics, user demand patterns, and geographical information. Based on different station types and the operator types of shared bicycles in historical operation data, combined with the extracted feature data, the module determines the demand matching degree and saturation of bicycles of different operator types in different station types from the historical operation data. Based on the demand matching degree and saturation of bicycles of different operator types in different station types from the historical operation data, different types of operation strategies are formulated.

[0063] Optionally, the station type of the aforementioned rail stations is determined based on the following method: Based on the environmental characteristics surrounding the rail station, the station type is determined, which can be any one of the following: office area, residential area, tourist area, commercial area, school area, or mixed area.

[0064] Optionally, the types of shared bicycle operators around the aforementioned rail stations include at least one of the following: blue operators, yellow operators, green operators, and other non-shared bicycle operators.

[0065] Optionally, when determining the corresponding operation strategy based on the number, status, and operator type of shared bicycles, combined with the station type of the rail station, the aforementioned operation strategy determination module 220 is specifically used for: Based on the station type, analyze the single-vehicle demand patterns and tidal characteristics of the rail stations in different time periods; Based on the operator type of shared bicycles around the rail stations, assess the proportion and distribution of bicycles of each operator type around the rail stations. Based on the bicycle demand patterns and tidal characteristics of rail stations at different time periods, the proportion and distribution of bicycles from different operators, and combined with the number, status and operator type of shared bicycles, the demand matching degree and saturation of shared bicycles from different operators around rail stations are determined. Based on the demand matching degree and saturation of shared bicycles of different operators around the rail stations, the corresponding operation strategies are determined.

[0066] Optionally, the above-mentioned device further includes: The bicycle distribution saturation determination module is used to monitor the bicycle density in the shared bicycle parking area around the rail station in real time through a pre-trained density recognition model, and to evaluate the bicycle distribution saturation around the rail station based on the bicycle density. The operation strategy determination module 220, based on the bicycle demand patterns and tidal characteristics of rail stations at different time periods, the proportion and distribution of bicycles from different operators, and combined with the quantity, status, and operator type of shared bicycles, determines the demand matching degree and saturation of shared bicycles of different operator types around rail stations. Specifically, it is used for: Based on the bicycle demand patterns and tidal characteristics of rail stations at different times, the proportion and distribution of bicycles from different operators, and combined with the number, status, operator type, and bicycle distribution saturation around rail stations, the demand matching degree and saturation of bicycles from different operators around rail stations are determined.

[0067] Optionally, the above-mentioned device further includes: The bicycle distribution saturation determination module is used to monitor the bicycle density in the shared bicycle parking area around the rail station in real time through a pre-trained density recognition model; and to evaluate the bicycle distribution saturation around the rail station based on the bicycle density. The adjustment module is used to dynamically adjust the operation strategy based on the saturation of bicycle distribution around the rail station.

[0068] The shared bicycle classification and scheduling device based on parking location awareness at rail stations in this embodiment of the invention can execute the shared bicycle classification and scheduling method based on parking location awareness at rail stations provided in this embodiment of the invention. The implementation principle is similar. The actions performed by each module and unit in the shared bicycle classification and scheduling device based on parking location awareness at rail stations in each embodiment of the invention correspond to the steps in the shared bicycle classification and scheduling method based on parking location awareness at rail stations in each embodiment of the invention. For detailed functional descriptions of each module of the shared bicycle classification and scheduling device based on parking location awareness at rail stations, please refer to the descriptions in the corresponding shared bicycle classification and scheduling method based on parking location awareness at rail stations shown above, which will not be repeated here.

[0069] The aforementioned shared bicycle classification and scheduling device based on parking location awareness at rail stations can be a computer program (including program code) running on a computer device. For example, the shared bicycle classification and scheduling device based on parking location awareness at rail stations is an application software. The device can be used to execute the corresponding steps in the method provided in the embodiments of the present invention.

[0070] In some embodiments, the shared bicycle classification and scheduling device based on parking location awareness at rail stations provided in this invention can be implemented using a combination of hardware and software. As an example, the shared bicycle classification and scheduling device based on parking location awareness at rail stations provided in this invention can be a processor in the form of a hardware decoding processor, which is programmed to execute the shared bicycle classification and scheduling method based on parking location awareness at rail stations provided in this invention. For example, the processor in the form of a hardware decoding processor can be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0071] In other embodiments, the shared bicycle classification and scheduling device for rail stations based on parking location awareness provided in this invention can be implemented in software. Figure 6 A shared bicycle classification and scheduling device based on parking location awareness, stored in a memory, is shown. It can be software in the form of programs and plug-ins, and includes a series of modules, including a real-time identification module 210, an operation strategy determination module 220, a scheduling suggestion generation module 230, and a classification and scheduling module 240, for implementing the shared bicycle classification and scheduling method based on parking location awareness provided in the embodiments of the present invention.

[0072] The modules described in the embodiments of the present invention can be implemented in software or hardware. The names of the modules are not, in some cases, limiting the scope of the module itself.

[0073] Based on the same principles as the methods shown in the embodiments of the present invention, the embodiments of the present invention also provide an electronic device, which may include, but is not limited to: a processor and a memory; the memory for storing computer programs; and the processor for executing the methods shown in any embodiment of the present invention by invoking the computer programs.

[0074] In one alternative embodiment, an electronic device is provided, such as Figure 7 As shown, Figure 7The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of the present invention.

[0075] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this invention. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0076] Bus 4002 may include a pathway for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 7 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0077] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0078] The memory 4003 stores application code (computer program) for executing the present invention, and its execution is controlled by the processor 4001. The processor 4001 executes the application code stored in the memory 4003 to implement the content shown in the foregoing method embodiments.

[0079] Among these, electronic devices can also be terminal devices. Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0080] This invention provides a computer-readable storage medium storing a computer program that, when run on a computer, enables the computer to execute the corresponding content in the aforementioned method embodiments.

[0081] According to another aspect of the present invention, a computer program product or computer program is also provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various embodiments described above.

[0082] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0083] It should be understood that the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0084] The computer-readable storage medium provided in this invention can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0085] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the method shown in the above embodiments.

[0086] The above description is merely a preferred embodiment of the present invention and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this invention is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-disclosed concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this invention.

Claims

1. A method for classifying and scheduling shared bicycles at rail stations based on parking location awareness, characterized in that, Includes the following steps: The system monitors the parking areas of shared bicycles around rail stations and uses a pre-trained parking location awareness model to obtain the number, status, and operator type of shared bicycles around the rail stations in real time. Based on the number, status, and operator type of the shared bicycles, and in conjunction with the station type of the rail station, a corresponding operation strategy is determined. Based on the aforementioned operational strategy, the scheduling demand for shared bicycles around the rail stations is predicted in real time, and scheduling suggestions are generated. Based on the generated scheduling suggestions, the shared bicycles around the rail stations are classified and scheduled accordingly.

2. The method according to claim 1, characterized in that, The method further includes: Based on historical operational data and environmental characteristics around rail stations of different station types, extract feature data related to shared bicycle scheduling, including changes in the number of bicycles, tidal characteristics, user demand patterns, and geographic information; Based on different site types and the operator types of shared bicycles in the historical operation data, combined with the extracted feature data, the demand matching degree and saturation of bicycles of different operator types in different site types in the historical operation data are determined. Based on the demand matching degree and saturation of bicycles of different operator types in different station types in the historical operation data, different types of operation strategies are formulated.

3. The method according to claim 1, characterized in that, The station type of the rail station is determined based on the following method: Based on the environmental characteristics surrounding the rail station, the station type is determined, which can be any one of the following: office area, residential area, tourist area, commercial area, school area, and mixed area.

4. The method according to claim 1, characterized in that, The types of shared bicycle operators around the rail stations include at least one of the following: blue operators, yellow operators, green operators, and other non-shared bicycle operators.

5. The method according to any one of claims 1 to 4, characterized in that, The step of determining the corresponding operation strategy based on the number, status, and operator type of the shared bicycles, combined with the station type of the rail station, includes: Based on the station type of the rail station, analyze the single-vehicle demand pattern and tidal characteristics of the rail station in different time periods; Based on the operator type of the shared bicycles around the rail station, assess the proportion and distribution of bicycles of each operator type around the rail station. Based on the bicycle demand patterns and tidal characteristics of the rail stations at different time periods, the proportion and distribution of bicycles from each operator, and combined with the quantity, status, and operator type of the shared bicycles, the demand matching degree and saturation of bicycles from different operator types around the rail stations are determined. Based on the demand matching degree and saturation of shared bicycles of different operators around the rail stations, the corresponding operation strategies are determined.

6. The method according to claim 5, characterized in that, The method also includes The density of shared bicycles in the parking area around the rail station is monitored in real time using a pre-trained density recognition model, and the saturation of bicycle distribution around the rail station is assessed based on the bicycle density. The process involves determining the demand matching degree and saturation of shared bicycles from different operators around the rail station based on the bicycle demand patterns and tidal characteristics at different time periods, the proportion and distribution of bicycles from different operators, and the quantity, status, and operator type of the shared bicycles. Based on the bicycle demand patterns and tidal characteristics of the rail stations at different time periods, the proportion and distribution of bicycles from each operator, and combined with the number, status, operator type, and bicycle distribution saturation around the rail stations, the demand matching degree and saturation of bicycles from different operator types around the rail stations are determined.

7. The method according to any one of claims 1 to 5, characterized in that, The method further includes: The density of shared bicycles in the parking area around the rail station is monitored in real time using a pre-trained density recognition model. Based on the single-vehicle density, assess the single-vehicle distribution saturation around the rail station; The operation strategy is dynamically adjusted based on the saturation of bicycle distribution around the rail station.

8. A shared bicycle classification and scheduling device for rail stations based on parking location awareness, characterized in that, include: The real-time identification module is used to monitor the parking areas of shared bicycles around the rail stations. Through a pre-trained parking location perception model, it can obtain the number, status and operator type of shared bicycles around the rail stations in real time. The operation strategy determination module is used to determine the corresponding operation strategy based on the number, status, and operator type of the shared bicycles, combined with the station type of the rail station. The scheduling suggestion generation module is used to predict the scheduling demand of shared bicycles around the rail station in real time based on the operation strategy and generate scheduling suggestions. The classification and scheduling module is used to classify and schedule shared bicycles around the rail stations according to the generated scheduling suggestions.

9. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method of any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1-7.

Images