Intelligent bus shelter waiting optimization method and system

Abstract

The invention provides an intelligent bus shelter waiting optimization method and system, and relates to the technical field of bus management. The intelligent bus shelter waiting optimization method comprises the steps of obtaining preset bus operation information, and determining related buses, operation routes, stop stations and stop duration according to the bus operation information; according to the real-time monitoring data of the parking duration, the running route and the associated path of the parking station, predicting a target passenger quantity; optimizing the shifts of the related buses according to the target passenger quantity; and updating the bus information displayed by the intelligent bus kiosk according to the optimized shifts, the running routes, the stop stations, the stop duration, the target passenger quantity and the preset running association information. According to the method, the bus shift is optimized by dynamically predicting the target passenger quantity, and the accuracy of the bus information displayed on the intelligent bus kiosk is improved on the basis of updating the parking time, the running route and the like, so that the waiting experience feeling of passengers is improved.

Description

Technical Field

[0001] The present application relates to the field of public transportation management technology, for example, to a smart bus booth waiting optimization method and system. Background Art

[0002] With the advancement of science and technology, smart bus shelters have emerged to optimize urban management. These are intelligent upgrades to traditional bus shelters. Leveraging technologies such as the Internet of Things (IoT), big data, and artificial intelligence, they provide real-time bus information, environmental monitoring, and convenient services, enhancing the passenger waiting experience and improving urban management efficiency. Passengers can use smart bus shelters to access real-time bus information, optimize travel routes, and enjoy value-added services such as charging and Wi-Fi, either directly at the shelter or through smart devices (such as mobile apps).

[0003] In related technologies, the pre-set bus schedules and operating hours are generally displayed on smart bus kiosks. However, the bus operation status may be affected by external factors such as the environment, causing the preset operating status to change, thereby affecting the passengers' waiting experience. Summary of the Invention

[0004] This application aims to provide a smart bus booth waiting optimization method and system, which can optimize the bus information display of the smart bus booth and enhance the passengers' waiting experience.

[0005] According to one aspect of the present application, a smart bus booth waiting optimization method is proposed, comprising: Obtain preset bus operation information, and determine relevant buses, routes, stops and stop durations based on the bus operation information; Predict target passenger volume based on real-time monitoring data of stop duration, route and associated paths of stops; Optimize the frequency of relevant buses based on target passenger volume; The bus information displayed on the smart bus kiosk is updated according to the optimized schedule, route, stop points, stop duration, target passenger volume and preset operation-related information.

[0006] Through the above-described embodiments provided by this application, by correlating real-time route monitoring data with stop duration analysis, target passenger volume can be dynamically predicted, reducing the error rate in schedule optimization and avoiding empty or overloaded buses. Schedules are automatically adjusted based on target passenger volume, improving vehicle turnover during peak hours and reducing ineffective departures during off-peak hours. Stop durations and routes are updated based on the optimized schedules, improving the accuracy of bus information displayed on smart bus kiosks.

[0007] According to some embodiments, predicting target passenger volume based on real-time monitoring data of stop duration, route, and associated paths of stop sites includes: Determine the basic stop time relationship of relevant buses at stop sites based on stop duration and route; Predict target passenger volume based on basic stop schedule relationships and real-time monitoring data.

[0008] The above-described embodiments of this application, combined with real-time monitoring data of associated paths for stop durations, routes, and stops, enable dynamic adjustment of basic stop time relationships, eliminating discrepancies between historical data and real-time scenarios. This significantly improves the accuracy of target passenger volume forecasts and reduces the error rate. Dynamically modifying the forecast model based on real-time monitoring data allows for rapid adaptation to emergencies (such as traffic congestion and temporary road closures), achieving a response within seconds, ensuring a close match between passenger volume forecasts and actual operational scenarios, and enhancing the flexibility of bus scheduling.

[0009] According to some embodiments, predicting a target passenger volume based on basic stop schedule relationships and real-time monitoring data includes: Based on real-time monitoring data, predict the passenger change corresponding to the basic stop time relationship; Correct the passenger volume change based on the mobile traffic and operation-related information to determine the correction trend; The target passenger volume is determined based on the revised trend and passenger monitoring data of relevant buses.

[0010] The above-mentioned embodiments provided by this application can quickly respond to traffic status changes through a real-time correction mechanism, improve the accuracy of passenger volume prediction, and integrate multi-dimensional data such as mobile traffic and operation-related information to overcome the limitations of a single data source.

[0011] According to some embodiments, predicting the passenger change corresponding to the basic stop time relationship based on real-time monitoring data includes: Determine the mobile flow under the dwelling duration based on real-time monitoring data; Predict passenger changes based on mobile traffic.

[0012] Through the above-mentioned embodiments provided by this application, by cross-analyzing mobile traffic and stop duration, the recognition response time and prediction sensitivity of sudden passenger flow increases are improved. After integrating multi-source data, the impact of single data source failures on prediction results is reduced, and the robustness of the system is significantly enhanced. The passenger change calculated based on this is more accurate.

[0013] According to some embodiments, the operation-related information includes weather data; wherein, based on the mobile traffic and the operation-related information, the passenger change is corrected to determine the correction trend, including: Based on weather data, predict the traffic conditions of the route and associated paths; Adjust mobile traffic based on weather data; The passenger change is corrected according to the adjusted movement flow to determine the correction trend.

[0014] The above-mentioned embodiments provided by this application improve the accuracy of road condition predictions in abnormal weather conditions, reduce the error rate of passenger volume predictions, and avoid over-allocation of transport capacity due to road flooding. Through the collaborative analysis of weather, road conditions, and passenger flow, an environmentally adaptable prediction system has been constructed, significantly improving the operational resilience of the public transportation system in complex weather conditions.

[0015] According to some embodiments, the operation-related information further includes road condition information; wherein, updating the bus information displayed on the smart bus kiosk according to the optimized schedule, operation route, stop location, stop duration, target passenger volume and preset operation-related information includes: Update the stop duration and optimized schedule based on traffic information and target passenger volume; The operating route, stop sites, updated stop duration and updated frequency are used as information to be displayed, so that the information to be displayed replaces the public transportation information.

[0016] Through the above-mentioned embodiments provided by this application, under unexpected road conditions, the recalculation of bus schedules and stop times can be completed quickly, improving dispatch response speed. By optimizing bus schedules, the phenomenon of buses becoming train-like can be avoided, and the average travel speed of road sections can be improved. Through the closed-loop linkage of road conditions, passenger flow, and schedules, an adaptive bus operation system has been established, significantly improving the service quality and environmental friendliness of urban public transportation.

[0017] According to some embodiments, when the operation-related information is weather data, the bus information displayed on the smart bus kiosk is updated according to the optimized schedule, operation route, stop location, stop duration, target passenger volume and preset operation-related information, including: Based on weather data, predict the traffic conditions of the route and associated paths; Based on traffic data and optimized schedules, routes, stops, and durations are updated to generate new bus operation information. Update the bus information displayed on the smart bus kiosk according to the new bus operation information.

[0018] Through the above-mentioned embodiments provided by this application, real-time road condition predictions based on weather data can trigger route adjustment strategies in advance, improving the responsiveness of bus operations to sudden weather events and avoiding the inefficient vehicle delays or detours caused by information lags in traditional dispatching. Smart bus kiosks display real-time "estimated arrival times" and "route adjustment reminders" based on weather and road condition updates, improving passenger satisfaction with bus service.

[0019] According to some embodiments, the method further comprises: Detect operational correlation information to identify abnormal environmental data and abnormal moments; Analyze abnormal environmental data to determine abnormal characteristics; Obtain the devices corresponding to abnormal characteristics on the smart bus booth to control the devices to start within the preset time fluctuation range corresponding to the abnormal moment.

[0020] Through the above-mentioned embodiments provided in this application, the invalid startup rate of the equipment is reduced through time fluctuation range management, thereby saving energy consumption of the bus shelter, reducing frequent starts and stops, and extending the life of the equipment.

[0021] According to some embodiments, the method further comprises: Obtaining interactive information input by waiting passengers at the stop; Based on the interactive information, the detailed large picture corresponding to the updated bus information is called for display.

[0022] Through the above-mentioned embodiments provided in this application, by accurately responding to passenger inquiries, reducing the display of invalid information, and improving the utilization rate of bus booth screens, energy consumption is reduced by reducing unnecessary screen brightness and refresh frequency.

[0023] According to one aspect of the present application, a smart bus shelter waiting optimization system is proposed, comprising: An information determination module is used to obtain preset bus operation information and determine the relevant buses, operation routes, stop sites and stop durations based on the bus operation information; A prediction module is used to predict the target passenger volume based on real-time monitoring data of the associated paths of the stop duration, the route and the stop sites; The schedule optimization module is used to optimize the schedule of relevant buses according to the target passenger volume; The display update module is used to update the bus information displayed on the smart bus kiosk based on the optimized schedule, route, stop points, stop duration, target passenger volume and preset operation-related information.

[0024] Optionally, the prediction module is specifically used to: Determine the basic stop time relationship of relevant buses at stop sites based on stop duration and route; Predict target passenger volume based on basic stop schedule relationships and real-time monitoring data.

[0025] Optionally, when predicting the target passenger volume based on the basic stop schedule relationship and the real-time monitoring data, the prediction module is specifically configured to: Based on real-time monitoring data, predict the passenger change corresponding to the basic stop time relationship; Correct the passenger volume change based on the mobile traffic and operation-related information to determine the correction trend; The target passenger volume is determined based on the revised trend and passenger monitoring data of relevant buses.

[0026] Optionally, when the prediction module predicts the passenger change corresponding to the basic stop time relationship based on the real-time monitoring data, it is specifically used to: Determine the mobile flow under the dwelling duration based on real-time monitoring data; Predict passenger changes based on mobile traffic.

[0027] Optionally, the operation-related information includes weather data; when the prediction module corrects the passenger change amount based on the mobile traffic and the operation-related information to determine the correction trend, the prediction module is specifically configured to: Based on weather data, predict the traffic conditions of the route and associated paths; Adjust mobile traffic based on weather data; The passenger change is corrected according to the adjusted movement flow to determine the correction trend.

[0028] Optionally, the operation-related information also includes road condition information; the display update module is specifically configured to: Update the stop duration and optimized schedule based on traffic information and target passenger volume; The operating route, stop sites, updated stop duration and updated frequency are used as information to be displayed, so that the information to be displayed replaces the public transportation information.

[0029] Optionally, when the operation-related information is weather data, the display update module is specifically configured to: Based on weather data, predict the traffic conditions of the route and associated paths; Based on traffic data and optimized schedules, routes, stops, and durations are updated to generate new bus operation information. Update the bus information displayed on the smart bus kiosk according to the new bus operation information.

[0030] Optionally, the smart bus shelter waiting optimization system further includes a device control module for: Detect operational correlation information to identify abnormal environmental data and abnormal moments; Analyze abnormal environmental data to determine abnormal characteristics; Obtain the devices corresponding to abnormal characteristics on the smart bus booth to control the devices to start within the preset time fluctuation range corresponding to the abnormal moment.

[0031] Optionally, the smart bus shelter waiting optimization system further includes a detail display module for: Obtaining interactive information input by waiting passengers at the stop; Based on the interactive information, the detailed large picture corresponding to the updated bus information is called for display.

[0032] According to one aspect of the present application, an electronic device is provided, comprising: a processor; and a memory storing a computer program, wherein when the computer program is executed by the processor, the processor executes the method as described above.

[0033] According to one aspect of the present application, a non-transitory computer-readable medium is provided, on which readable instructions are stored. When the instructions are executed by a processor, the processor is caused to execute the method described above.

[0034] It should be understood that the foregoing general description and the following detailed description are merely illustrative and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without exceeding the scope of protection required by this application.

[0036] Figure 1 A flowchart of the smart bus shelter waiting optimization method provided in an embodiment of the present application; Figure 2 A block diagram of the smart bus shelter waiting optimization device provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0037] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be embodied in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art. Like reference numerals in the drawings represent like or similar parts, and thus repetitive description thereof will be omitted.

[0038] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner.In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps etc. can be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0039] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0040] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0041] It should be understood that although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Thus, the first component discussed below could be referred to as the second component without departing from the teachings of the present invention. As used herein, the term "and / or" includes any one and all combinations of one or more of the associated listed items.

[0042] For specific implementation methods, please refer to the following embodiments.

[0043] Figure 1 This is a flow chart of the smart bus booth waiting optimization method provided in the embodiment of this application. The method of this embodiment can be applied to the waiting optimization server. Figure 1 As shown, the method includes: step S10, step S11, step S12 and step S13.

[0044] In step S10, preset bus operation information is obtained, and the relevant buses, operation routes, stop sites and stop durations are determined according to the bus operation information.

[0045] Before a bus runs, bus operation information may be pre-set to guide the normal operation of the bus. The bus operation information may include the vehicle ID of the bus performing the work, the route of the bus, the stop points and the stop duration.

[0046] In step S11 , the target passenger volume is predicted based on the real-time monitoring data of the associated paths of the stop duration, the running route and the stop sites.

[0047] In this application, the associated path can be used to represent the road directly connected to the stop and the path to which the stop belongs. The real-time monitoring data can be the monitoring data collected by the monitoring equipment installed on the associated path. The associated path can be the road within a radius of one kilometer with the stop as the origin.

[0048] In some implementations, real-time location, speed, and stop duration (time stamp from when the vehicle came to rest to when it started) can be obtained through the vehicle's onboard optical boresight (OBD) or GPS device. This can be integrated with the bus dispatch system to extract deviations between planned and actual stop times. Real-time video streams from roadside cameras (such as electronic police cameras and checkpoint cameras) can be accessed. Edge computing devices can be used to analyze the video streams in real time to extract information about pedestrian traffic (using object detection algorithms such as YOLOv7), non-motorized vehicle traffic (bicycles, electric vehicles), and motor vehicle traffic (differentiating between private cars and taxis).

[0049] All data is standardized to UTC timestamps (Coordinated Universal Time Timestamps) and sliced into 1-minute granularity. Camera coordinates are mapped to associated routes (e.g., specific road segment IDs) through a GIS system, and a passenger volume prediction model is built based on this.

[0050] Analyze real-time monitoring data to determine the characteristics of pedestrian, non-motorized vehicle, and motor vehicle flows. Input these characteristics, along with stop durations and routes, into a passenger volume prediction model to output target passenger volume.

[0051] In step S12, the frequency of relevant public buses is optimized according to the target passenger volume.

[0052] In this application, the target passenger volume can be divided into time windows (e.g., 15-minute windows) to eliminate invalid operating time data due to accidents / failures. The schedule can be optimized according to the preset optimization conditions.

[0053] In some implementations, when the passenger volume is overloaded (>110% capacity), the scheduling API (Application Programming Interface) is triggered to optimize execution: one additional trip is added during the current period and the interval between subsequent trips is shortened.

[0054] In the case of insufficient passenger volume (<60% capacity), K-means cluster analysis is used to analyze the data of three consecutive flights. If the number of passengers is less than the threshold, a merge is triggered and optimized execution is performed: merge adjacent flights (such as merging two flights into one) and extend the interval. In the event of sudden large passenger flows (such as large-scale events), temporary routes are generated through path planning algorithms and optimized execution: temporary shuttle buses are inserted, stopping only at high-demand stations.

[0055] In step S13, the bus information displayed on the smart bus kiosk is updated according to the optimized schedule, route, stop points, stop duration, target passenger volume and preset operation-related information.

[0056] In this application, operation-related information can be used to represent external information that affects normal operation, such as weather data. An operation information update model can be pre-set, and the operation-related information, optimized schedules, routes, stops, stop durations, and target passenger volume can be input into the model. The model then outputs actual information, which is then displayed in the corresponding smart bus kiosk. This information can include the vehicles stopping at the stop, the time, the number of passengers on the vehicle, and the required waiting time.

[0057] This application dynamically predicts target passenger volume by linking real-time route monitoring data with stop duration analysis, reducing the error rate in schedule optimization and avoiding empty or overloaded buses. Schedules are automatically adjusted based on target passenger volume, improving vehicle turnover during peak hours and reducing ineffective departures during off-peak hours. Stop durations and operating routes are updated based on the optimized schedule, improving the accuracy of bus information displayed on smart bus kiosks.

[0058] According to some embodiments, the basic stop time relationship of the relevant buses at the stop sites can be determined based on the stop duration and the running route; and the target passenger volume can be predicted based on the basic stop time relationship and real-time monitoring data.

[0059] In this application, the basic stop time relationship can be used to represent the correspondence between bus-stop site-stop time.

[0060] In some implementations, historical operational data can be used to calculate the average dwell time (e.g., boarding and alighting times, door opening and closing times) at each stop for each bus route, and to establish an initial correlation model between dwell time and passenger flow at the stop. Combined with the route (e.g., route length, stop sequence, departure intervals), a basic stop schedule can be generated, recording the planned arrival and departure time windows for each bus at each stop.

[0061] Using onboard GPS, smart bus stop signs, or passenger card swipe data, the system obtains real-time bus arrival and departure times and current locations. If a bus is delayed or early, the predicted stop durations at subsequent stops are adjusted using a sliding window algorithm (e.g., data from the last N trips). Based on real-time stop durations (e.g., if boarding and alighting times at a particular stop are 20% longer than the historical average) and the number of waiting passengers estimated using platform cameras or mobile location data, a Kalman filter or LSTM model is used to predict boarding and alighting volumes for the next one or two stops. By integrating multiple data sources (e.g., holidays and surrounding events), the system uses time series analysis or regression models to predict the time-of-day passenger flow distribution for the entire route, outputting the predicted target passenger volume for each stop over the next 15 minutes.

[0062] In some implementations, a population threshold can be set (e.g., triggering an early warning when the number exceeds 80% of the station capacity), and the prediction model parameters can be calibrated in real time based on actual passenger card swiping data to form a closed-loop optimization.

[0063] By combining real-time monitoring data of stop durations, routes, and associated paths at stops, this application can dynamically adjust the relationship between basic stop times, eliminating deviations between historical data and real-time scenarios, significantly improving the accuracy of target passenger volume forecasts and reducing the error rate. Dynamically modifying the forecast model based on real-time monitoring data can quickly adapt to emergencies (such as traffic congestion and temporary road closures), achieving a response within seconds, ensuring a close match between passenger volume forecasts and actual operating scenarios, and enhancing the flexibility of bus scheduling.

[0064] According to some embodiments, the passenger change corresponding to the basic stop time relationship can be predicted based on real-time monitoring data; the passenger change can be corrected based on mobile traffic and operation-related information to determine a correction trend; and the target passenger volume can be determined based on the correction trend and passenger monitoring data of relevant buses.

[0065] This application extracts basic stop timing relationships (such as planned arrival times and stop durations) from historical data and aligns them with real-time monitoring data (such as GPS trajectories and onboard sensor data) to generate a time series dataset. Using a sliding time window algorithm (e.g., data from the last 15 minutes), the deviation between the real-time stop duration and the basic timing is calculated as the initial input for passenger change.

[0066] Key features are extracted from real-time monitoring data, including the deviation of actual vehicle arrival / departure times, mobile traffic around the station (such as mobile phone signaling data and shared bike usage), and external factors such as holidays (encoded as dummy variables). A lightweight machine learning model (such as online gradient boosting trees (OGBs) or gated recurrent units (GRUs)) is used as input, taking real-time features and outputting the change in passenger volume (ΔP).

[0067] Combined with bus operation related information (such as the actual passenger volume of the previous bus and the line congestion index), the weights of key factors affecting passenger volume are identified through causal inference models (such as Bayesian networks). Dynamic weighted corrections are made to the passenger volume changes, for example: The corrected ΔP=the above-output ΔP×(1+α×congestion index), where α is the preset dynamic adjustment coefficient.

[0068] The corrected passenger change is added to the basic passenger volume (such as the historical average for the same period), and the result is smoothed through Kalman filtering to output the final predicted value: Target passenger volume = basic passenger volume + corrected ΔP ± confidence interval, which can be set in advance.

[0069] This application uses a real-time correction mechanism to quickly respond to changes in traffic conditions and improve the accuracy of passenger volume predictions. It also integrates multi-dimensional data such as mobile traffic and operational correlation information to overcome the limitations of a single data source.

[0070] According to some embodiments, the mobile flow rate under the stop duration can be determined based on real-time monitoring data; and the passenger change amount can be predicted based on the mobile flow rate.

[0071] This application uses onboard GPS, smart bus stops, passenger card swiping systems, and third-party data (such as mobile phone signaling and shared bike APIs) to obtain real-time monitoring data, including: vehicle location and speed, number of people waiting at stops (via cameras or infrared sensors), and surrounding mobile traffic (such as mobile phone signaling activity within a 500-meter radius). Missing values (such as GPS signal loss) are interpolated, and outliers (such as instantaneous passenger surges) are smoothed using a sliding window mean filter.

[0072] Based on real-time trajectory data, calculate the deviation ΔT = T_actual - T_base between the actual stop duration (T_actual) and the baseline planned stop duration (T_base). Define mobile traffic (F) as the number of mobile devices per unit time around a station (e.g., the number of mobile phone signals per minute). Use cluster analysis (e.g., DBSCAN) to identify traffic hotspots and associate them with specific stations. Construct composite features. In some implementations, construct the traffic-duration ratio: F / ΔT (reflecting passenger pressure per unit stop time); and the spatiotemporal weighted traffic: F × e^(-b × d) (where d is the distance from the station and b is the attenuation coefficient).

[0073] A lightweight regression model (such as extreme gradient boosting tree or wide-deep learning model) is used to input real-time features and output the passenger change ΔP.

[0074] This application improves the recognition response time and prediction sensitivity of sudden passenger surges (such as the end of a large event) by cross-analyzing mobile traffic and stop duration. By integrating multi-source data, the impact of single data source failures (such as GPS offline) on prediction results is reduced, significantly enhancing system robustness. The resulting passenger change calculation is more accurate.

[0075] According to some embodiments, the operation-related information includes weather data. Traffic condition data for the operation route and associated paths can be predicted based on the weather data; mobile traffic volume can be adjusted based on the weather data; and passenger volume changes can be corrected based on the adjusted mobile traffic volume to determine a correction trend.

[0076] This application obtains real-time weather data from the Meteorological Bureau, vehicle-mounted weather sensors, or third-party weather services (including: precipitation probability, wind speed, temperature, visibility). The weather data is normalized to eliminate dimensional differences. A weather-road condition mapping table is constructed, for example: Heavy rain (precipitation > 80%) → Traffic delay index increases by 30%; Heavy fog (visibility <500m) → accident risk level increases to high.

[0077] Use a time series model or graph neural network to input weather data and output the traffic delay index for the next 15 minutes.

[0078] Based on historical data regression analysis, determine the flow adjustment coefficient under different weather conditions, such as: Light rain (rainfall = 30%) → Traffic adjustment factor = 1.2 (passenger flow increases by 20%) Heavy snow (snowfall = 90%) → Traffic adjustment factor = 0.8 (passenger flow reduced by 20%) Flow correction formula: Adjusted mobile flow = original mobile flow × flow adjustment coefficient (rainfall, temperature).

[0079] The adjusted mobile traffic and traffic delay index are input into the correction model to obtain the correction trend.

[0080] This application improves the accuracy of road condition predictions in abnormal weather conditions, reduces the error rate in passenger volume predictions, and avoids over-allocation of transport capacity due to road flooding. Through collaborative analysis of weather, road conditions, and passenger flow, an environmentally adaptable prediction system has been constructed, significantly improving the operational resilience of the public transportation system in complex weather conditions.

[0081] According to some embodiments, the operation-related information also includes road condition information. The stop duration and optimized schedule can be updated based on the road condition information and target passenger volume; the operation route, stop sites, updated stop duration, and updated schedule are used as the information to be displayed, so that the information to be displayed replaces the public transportation information.

[0082] In some implementations, the following data can be obtained through traffic management departments, floating vehicle data (such as Didi and AutoNavi), or sensors installed on the road side (such as geomagnetic detectors): average vehicle speed, congestion mileage, and accident location.

[0083] Constructing the comprehensive road condition index RCI: RCI=e×(1-average vehicle speed / free flow speed)+f×congestion mileage+γ×accident impact.

[0084] Where e, f, and γ are weight coefficients.

[0085] Based on the RCI and target passenger volume, fuzzy logic control rules are used to dynamically adjust stop durations. Combined with the updated stop durations, departure intervals are recalculated using a genetic algorithm or reinforcement learning model. This data is integrated into a real-time bus information package: updated stop durations, optimized schedules, original routes, and stop locations. This information package is pushed to the smart bus kiosk via MQTT or WebSocket, triggering a display update.

[0086] This application allows for rapid recalculation of bus schedules and stop times in the event of unexpected road conditions (such as traffic accidents), improving dispatch response speed. By optimizing schedules, bus trains can be avoided (e.g., three buses arriving simultaneously), increasing average travel speeds along the route. By integrating traffic conditions, passenger flow, and schedules in a closed loop, an adaptive bus operation system has been established, significantly enhancing the service quality and environmental friendliness of urban public transportation.

[0087] According to some embodiments, the road condition data of the operating route and the associated paths can be predicted based on weather data; based on the road condition data and the optimized schedule, the operating route, stop sites and stop durations are updated to generate new bus operation information; and based on the new bus operation information, the bus information displayed on the smart bus kiosk is updated.

[0088] Real-time weather data can be obtained through the meteorological bureau, vehicle-mounted sensors and environmental monitoring modules of smart bus stops, including: precipitation type (rain / snow / hail) and intensity (mm / h), visibility (unit: meter), wind speed (unit: m / s), and extreme weather warning levels (such as yellow / orange / red warnings).

[0089] Using a spatiotemporal graph neural network or Transformer model, the system takes weather data and historical traffic conditions as input and outputs a traffic delay index for the next 15 minutes. Predefined thresholds for the traffic delay index can be used: for example, an RCI > 0.8 indicates severe congestion, triggering route adjustments.

[0090] When the traffic delay index exceeds a threshold and a weather warning is in effect, a pre-configured backup route library is used. If visibility falls below a threshold, such as 200 meters, non-essential stops (such as those in commercial areas) can be skipped, and stops at key stations like hospitals and schools can be extended. Based on the traffic delay index and target passenger volume, deep reinforcement learning (the model dynamically adjusts departure intervals) is used.

[0091] Integrate the updated routes, stops, stop durations and frequencies, generate structured information packages, and update bus information.

[0092] This application uses weather data to predict road conditions in real time (e.g., heavy rain causing waterlogging, snow accumulation causing low adhesion), triggering route adjustment strategies in advance, improving bus operations' responsiveness to weather emergencies and avoiding the inefficient detours and delays caused by information lags in traditional dispatching. Smart bus kiosks display "estimated arrival times" and "route adjustment reminders" based on weather and road condition updates in real time, improving passenger satisfaction with bus service.

[0093] According to some embodiments, operation-related information can be detected to determine abnormal environmental data and abnormal moments; abnormal environmental data can be analyzed to determine abnormal characteristics; and devices corresponding to abnormal characteristics on smart bus booths can be obtained to control the devices to start within a preset time fluctuation range corresponding to the abnormal moments.

[0094] In some implementations, real-time data (such as temperature, humidity, wind speed, PM2.5 concentration, and visibility) from weather stations, on-board sensors, and smart bus shelter environmental monitoring modules can be integrated to create a multi-dimensional environmental data stream. Based on historical data and expert experience, abnormal thresholds for each environmental parameter can be set (e.g., temperature threshold: ≥40°C or ≤-10°C; visibility threshold: ≤50 meters). Machine learning algorithms can also be used to dynamically adjust thresholds (e.g., to account for seasonal and time-of-day factors).

[0095] A sliding window algorithm (e.g., a 10-minute window length) can be used to monitor environmental data in real time. When data exceeds a threshold within three consecutive time windows, it is marked as an anomaly, and the start time and duration of the anomaly are recorded. Feature engineering is performed on abnormal environmental data to extract the following key features: anomaly type (e.g., high temperature, heavy rain, dense fog), anomaly intensity (e.g., rainstorm intensity ≥ 50 mm / h), and anomaly diffusion trend (e.g., visibility decrease rate ≥ 5 meters / minute).

[0096] According to the preset association method, a rule library is built to associate devices with abnormal features, for example: Abnormally high temperature (temperature ≥ 40°C) → Activate bus shelter cooling fans and spray cooling devices; Abnormal heavy rain (precipitation intensity ≥ 30mm / h) → Activate the bus shelter rainproof roof and ground drainage pump; Abnormal visibility (visibility ≤ 50 meters) → Turn on the bus shelter’s high-brightness warning lights and voice broadcast system.

[0097] Set a time fluctuation range for device startup for each abnormality type (for example, in the case of a high temperature abnormality, fans can start within ±5 minutes of the abnormal time) to avoid energy waste and equipment damage caused by frequent device startups and shutdowns. Based on the abnormality characteristics and the current time, determine whether the time fluctuation range is within the range. If so, the corresponding device will be started.

[0098] This application reduces the invalid startup rate of equipment through time fluctuation range management, thereby saving energy consumption of bus shelters, reducing frequent starts and stops, and extending the life of equipment.

[0099] According to some embodiments, interactive information input by waiting passengers at a bus stop may be obtained; based on the interactive information, a detailed large image corresponding to the updated bus information may be called for display.

[0100] In this application, a smart bus kiosk can be equipped with a touch screen, voice recognition module, or gesture sensing device to support passengers entering interactive information through clicks, voice commands (such as "check the next bus"), and gesture sliding. The kiosk can also parse passenger input of station names, route numbers, or keywords such as "next bus." Passenger feedback on the current information display (such as "display is unclear" or "font size needs to be enlarged") is recorded. Voice commands are subjected to noise reduction and semantic recognition, and gesture commands are subjected to coordinate mapping and motion analysis to generate structured interaction data.

[0101] In some implementations, a mapping table between interaction instructions and bus information details may be constructed, for example: Command "Next bus" → call up the updated bus schedule and estimated arrival time details.

[0102] Command "Show route" → Call up the updated HD map of the route and stops.

[0103] Based on WebGL (Web Graphics Library) or Canvas (HTML CanvasElement) technology, a detailed large image containing the following elements is generated in real time: the vehicle's real-time position (via GPS positioning), the distance to the next stop (such as "500 meters, estimated 3 minutes"), and dynamic reminders of the interval between shifts (such as "Current interval: 8 minutes, the next shift is expected to arrive at 12:05").

[0104] The detailed picture obtained above is displayed.

[0105] This application improves the utilization rate of bus booth screens by accurately responding to passenger inquiries, reducing the display of invalid information (such as schedule information for non-target routes), and reducing energy consumption by reducing unnecessary screen brightness and refresh rate.

[0106] The following describes an apparatus embodiment of the present application, which can be used to perform the method embodiment of the present application. For details not disclosed in the apparatus embodiment of the present application, reference can be made to the method embodiment of the present application.

[0107] Figure 2 This is a block diagram of the smart bus shelter waiting optimization system provided in the embodiment of this application. Figure 2 As shown, the smart bus stop waiting optimization system 200 includes an information determination module 201, a prediction module 202, a schedule optimization module 203 and a display update module 204.

[0108] The information determination module 201 is used to obtain preset bus operation information and determine the relevant buses, operation routes, stop sites and stop durations based on the bus operation information; Prediction module 202, for predicting target passenger volume based on real-time monitoring data of associated paths of stop duration, operation routes, and stop sites; A schedule optimization module 203 is used to optimize the schedule of relevant buses according to the target passenger volume; The display update module 204 is used to update the bus information displayed on the smart bus kiosk according to the optimized schedule, route, stop points, stop duration, target passenger volume and preset operation-related information.

[0109] Optionally, the prediction module 202 is specifically configured to: Determine the basic stop time relationship of relevant buses at stop sites based on stop duration and route; Predict target passenger volume based on basic stop schedule relationships and real-time monitoring data.

[0110] Optionally, when predicting the target passenger volume based on the basic stop schedule relationship and the real-time monitoring data, the prediction module 202 is specifically configured to: Based on real-time monitoring data, predict the passenger change corresponding to the basic stop time relationship; Correct the passenger volume change based on the mobile traffic and operation-related information to determine the correction trend; The target passenger volume is determined based on the revised trend and passenger monitoring data of relevant buses.

[0111] Optionally, when predicting the passenger change corresponding to the basic stop time relationship based on the real-time monitoring data, the prediction module 202 is specifically configured to: Determine the mobile flow under the dwelling duration based on real-time monitoring data; Predict passenger changes based on mobile traffic.

[0112] Optionally, the operation-related information includes weather data; when the prediction module 202 corrects the passenger change amount based on the mobile traffic and the operation-related information to determine the correction trend, it is specifically configured to: Based on weather data, predict the traffic conditions of the route and associated paths; Adjust mobile traffic based on weather data; The passenger change is corrected according to the adjusted movement flow to determine the correction trend.

[0113] Optionally, the operation-related information also includes road condition information; the display update module 204 is specifically configured to: Update the stop duration and optimized schedule based on traffic information and target passenger volume; The operating route, stop sites, updated stop duration and updated frequency are used as information to be displayed, so that the information to be displayed replaces the public transportation information.

[0114] Optionally, when the operation-related information is weather data, the display update module 204 is specifically configured to: Based on weather data, predict the traffic conditions of the route and associated paths; Based on traffic data and optimized schedules, routes, stops, and durations are updated to generate new bus operation information. Update the bus information displayed on the smart bus kiosk according to the new bus operation information.

[0115] Optionally, the smart bus shelter waiting optimization system 200 further includes a device control module 205 for: Detect operational correlation information to identify abnormal environmental data and abnormal moments; Analyze abnormal environmental data to determine abnormal characteristics; Obtain the devices corresponding to abnormal characteristics on the smart bus booth to control the devices to start within the preset time fluctuation range corresponding to the abnormal moment.

[0116] Optionally, the smart bus shelter waiting optimization system 200 further includes a detail display module 206 for: Obtaining interactive information input by waiting passengers at the stop; Based on the interactive information, the detailed large picture corresponding to the updated bus information is called for display.

[0117] The device performs functions similar to the method provided above. For other functions, please refer to the previous description and will not be repeated here.

[0118] Figure 3A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, such as Figure 3 As shown, the electronic device 300 of this embodiment may include: a memory 301 and a processor 302.

[0119] The memory 301 stores a computer program. When the computer program is executed by the processor 302 , the processor 302 executes the method in the above embodiment.

[0120] The processor 302 and the memory 301 are connected, for example, via a bus.

[0121] Optionally, the electronic device 300 may further include a transceiver. It should be noted that in actual applications, the number of transceivers is not limited to one, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0122] Processor 302 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 may implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the present disclosure. Processor 302 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, or a combination of a DSP and a microprocessor.

[0123] A bus includes a path that transmits information between the components mentioned above. Examples include a PCI (Peripheral Component Interconnect) bus and an EISA (Extended Industry Standard Architecture) bus. Buses can be categorized as address buses, data buses, and control buses. For ease of illustration, the diagram uses a single thick line, but this does not imply a single bus or type of bus.

[0124] The memory 301 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0125] The memory 301 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 302. The processor 302 is used to execute the application code stored in the memory 301 to implement the content shown in the above method embodiment.

[0126] Electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. They may also include servers, etc. Figure 3 The electronic device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0127] The electronic device of this embodiment can be used to execute the method of any of the above embodiments. Its implementation principles and technical effects are similar and will not be described in detail here.

[0128] The present application also provides a non-transitory computer-readable storage medium having computer-readable instructions stored thereon. When the aforementioned instructions are executed by a processor, the processor executes the method in the above embodiment.

[0129] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a non-transitory computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0130] The embodiments of the present application are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only intended to help understand the method and core ideas of the present application. At the same time, changes or modifications made by those skilled in the art based on the ideas of the present application, the specific implementation methods, and the scope of application of the present application, all fall within the scope of protection of the present application. In summary, the contents of this specification should not be construed as limiting the present application.

Claims

1. A smart bus shelter waiting optimization method, characterized in that: include: Obtaining preset bus operation information, and determining relevant buses, operation routes, stop sites, and stop durations based on the bus operation information; predicting a target passenger volume based on real-time monitoring data of the stop duration, the operation route, and associated paths of the stop sites; Optimizing the frequency of the relevant public transportation according to the target passenger volume; The bus information displayed on the smart bus kiosk is updated according to the optimized schedule, the operating route, the stop sites, the stop duration, the target passenger volume and the preset operation-related information.

2. The method according to claim 1, characterized in that The method of predicting a target passenger volume based on the real-time monitoring data of the stop duration, the operation route, and the associated paths of the stop sites includes: Determine the basic stop time relationship of the relevant bus at the stop site according to the stop duration and the running route; The target passenger volume is predicted based on the basic stop time relationship and the real-time monitoring data.

3. The method according to claim 2, characterized in that The step of predicting the target passenger volume based on the basic stop time relationship and the real-time monitoring data includes: Predicting a passenger change corresponding to the basic stop time relationship based on the real-time monitoring data; Correcting the passenger change amount according to the mobile flow and operation-related information to determine a correction trend; The target passenger volume is determined according to the revised trend and the passenger monitoring data of the relevant public transport.

4. The method according to claim 3, characterized in that The step of predicting the passenger change corresponding to the basic stop time relationship based on the real-time monitoring data includes: Determining the mobile flow rate under the stop duration according to the real-time monitoring data; The passenger change amount is predicted according to the mobile flow.

5. The method according to claim 3, characterized in that The operation-related information includes weather data; The step of correcting the passenger change amount based on the mobile flow and operation-related information to determine a correction trend includes: predicting traffic condition data of the running route and the associated path based on the weather data; adjusting the mobile traffic based on the weather data; The passenger change amount is corrected according to the adjusted movement flow to determine the correction trend.

6. The method according to claim 3, characterized in that The operation-related information also includes road condition information; The updating of the bus information displayed on the smart bus kiosk according to the optimized schedule, the operation route, the stop sites, the stop duration, the target passenger volume and the preset operation-related information includes: updating the stop duration and the optimized schedule according to the traffic information and the target passenger volume; The running route, the stop sites, the updated stop duration and the updated schedule are used as information to be displayed, so that the information to be displayed replaces the public transportation information.

7. The method according to claim 1, characterized in that In the case where the operation-related information is weather data, updating the bus information displayed on the smart bus kiosk according to the optimized schedule, the operation route, the stop site, the stop duration, the target passenger volume and the preset operation-related information includes: predicting traffic condition data of the running route and the associated path based on the weather data; Based on the traffic data and the optimized schedule, the operation route, the stop sites and the stop duration are updated to generate new bus operation information; According to the new bus operation information, the bus information displayed on the smart bus kiosk is updated.

8. The method according to any one of claims 1 to 7, characterized in that Also includes: Detecting the operation-related information to determine abnormal environmental data and abnormal time; Analyzing the abnormal environmental data to determine abnormal characteristics; Obtain the device corresponding to the abnormal feature on the smart bus booth to control the device to start within a preset time fluctuation range corresponding to the abnormal moment.

9. The method according to any one of claims 1 to 7, characterized in that Also includes: Obtaining interactive information input by waiting passengers at the stop; According to the interactive information, the detailed large picture corresponding to the updated bus information is called for display.

10. A smart bus shelter waiting optimization system, characterized in that: include: An information determination module is used to obtain preset bus operation information and determine the relevant buses, operation routes, stop sites and stop durations based on the bus operation information; a prediction module, configured to predict a target passenger volume based on real-time monitoring data of the stop duration, the operation route, and associated paths of the stop sites; A schedule optimization module, configured to optimize the schedule of the relevant public transportation according to the target passenger volume; The display update module is used to update the bus information displayed on the smart bus kiosk according to the optimized schedule, the operating route, the stop sites, the stop duration, the target passenger volume and the preset operation-related information.

Images