Electronic bulletin board intelligent data interaction method and system

Abstract

The application provides an electronic station board intelligent data interaction method and system. Through data fusion and neural network prediction, the application realizes accurate bus arrival time prediction, and through bidirectional data transmission optimization scheduling, solves the technical problems of the data interaction system in the prior art in terms of data processing accuracy, data transmission stability and safety.

Description

Technical Field

[0001] This invention relates to the field of data interaction technology for electronic bus stop signs in intelligent transportation, and particularly to an intelligent data interaction method and system for electronic bus stop signs. Background Technology

[0002] With the rapid development of intelligent transportation systems, LED electronic bus stop signs are increasingly widely used in urban public transportation. To improve the quality of public transportation services and passenger waiting experience, efficient and accurate intelligent data interaction has become a key requirement. This invention focuses on solving the data interaction problem between LED electronic bus stop signs and public transportation operating systems, as well as surrounding intelligent devices, to achieve real-time data updates and sharing. Summary of the Invention

[0003] This invention proposes an intelligent data interaction method and system for electronic bus stop signs, and the technical solution adopted is as follows:

[0004] A method for intelligent data interaction of electronic bus stop signs, the method comprising:

[0005] S1: Collect bus location data, bus operation scheduling data, and road condition data through a data acquisition system, and then fuse the bus location data, bus operation scheduling data, and road condition data through a multi-data fusion method to obtain fused data;

[0006] S2: Establish a bus vehicle prediction model, and through the bus vehicle prediction model, predict the arrival time of the bus at each station based on the fused data to obtain several estimated arrival times corresponding to each station.

[0007] S3: A two-way data transmission channel is constructed through a wireless communication network. The estimated arrival time is transmitted to the electronic signboard at the station through the two-way data transmission channel and displayed on the screen of the electronic signboard. At the same time, passenger flow information and environmental information within the station are acquired through a video acquisition system and transmitted back to the bus operation and dispatch system through the two-way data transmission channel.

[0008] S4: The bus operation dispatching system dynamically dispatches buses that are operating normally and buses waiting in passenger stations based on passenger flow information and environmental information.

[0009] Preferably, S1 includes:

[0010] S11: Obtain the bus's location data through the positioning device on the bus, the location data including the bus's latitude and longitude, speed and direction of travel;

[0011] S12: Obtain permission to enter the bus operation and dispatch system, and collect bus operation and dispatch data after entering the bus operation and dispatch system. The bus operation and dispatch data includes: bus schedule information and route information.

[0012] S13: Obtain road condition data through the city's traffic monitoring system. The road condition data includes: traffic flow data, bus speed data, and traffic control data.

[0013] S14: Input the location data of buses, bus operation scheduling data and road condition data into the neural network system. The neural network system fuses multiple features to obtain fused data.

[0014] Preferably, S2 includes:

[0015] S21: The neural network system extracts historical features from the historical fusion data. The historical features include: the distance of the bus from the next station in history and the corresponding speed, and the historical traffic flow. The neural network system is trained and improved using the historical features.

[0016] S22: The neural network system extracts features from the fused data. The features include the current speed of the bus at the same historical moment, the distance to the next station, and the traffic flow. The neural network system then predicts the arrival time of the bus at each station based on the obtained features, resulting in several estimated arrival times that correspond one-to-one with each station.

[0017] Preferably, S3 includes:

[0018] S31: A two-way data transmission channel is established through a wireless communication network. The estimated arrival time of buses obtained from the neural network system is sent to the electronic signs at each station through the two-way data transmission channel, and then displayed on the screen of the electronic signs to passengers.

[0019] S32: Obtain passenger flow information and environmental information within the station through a video acquisition system. The passenger flow information includes the number of passengers, and the environmental information represents the ambient temperature and humidity. Transmit the passenger flow information and environmental information back to the bus operation and dispatch system through a two-way data transmission channel.

[0020] Preferably, S4 includes:

[0021] S41: Analyze the passenger flow information and environmental information, and based on the analysis results, formulate and implement a dynamic scheduling strategy. The dynamic adjustment strategy includes, but is not limited to: adjusting the departure time and route of buses, the speed of buses, and increasing or decreasing the number of buses to cope with changing passenger demand and traffic conditions.

[0022] S42: The command and dispatch system implements dynamic dispatching of buses that are operating normally and buses waiting in passenger stations according to the dynamic adjustment strategy.

[0023] An intelligent data interaction system for electronic bus stop signs, the system comprising:

[0024] Data Acquisition and Fusion System: The system collects bus location data, bus operation scheduling data, and road condition data, and then uses a multi-data fusion method to fuse the bus location data, bus operation scheduling data, and road condition data to obtain fused data.

[0025] Vehicle arrival time prediction system: Establish a bus prediction model, and through the bus prediction model, predict the arrival time of buses at each station based on fused data to obtain several estimated arrival times corresponding to each station.

[0026] Information interaction and feedback system: A two-way data transmission channel is built through a wireless communication network. The estimated arrival time is transmitted to the electronic signboard at the station through the two-way data transmission channel and displayed on the screen of the electronic signboard. At the same time, passenger flow information and environmental information within the station are acquired through a video acquisition system and transmitted back to the bus operation and dispatch system through the two-way data transmission channel.

[0027] Dynamic Dispatch Management System: The bus operation dispatch system dynamically dispatches buses that are operating normally and buses waiting in passenger stations based on passenger flow information and environmental information.

[0028] Preferably, the data acquisition and fusion system includes:

[0029] Location data acquisition system: The system acquires the location data of the bus through the positioning device on the bus. The location data includes the latitude and longitude of the bus, its speed and direction of travel.

[0030] Dispatch data access and collection system: Obtains permission to enter the bus operation dispatch system, and collects bus operation dispatch data after entering the bus operation dispatch system. The bus operation dispatch data includes: bus schedule information and route information.

[0031] Road condition data acquisition system: acquires road condition data through the city's traffic monitoring system, including traffic flow data, bus speed data, and traffic control data;

[0032] Data fusion and analysis system: The system inputs the location data of buses, bus operation scheduling data, and road condition data into the neural network system. The neural network system fuses multiple features to obtain fused data.

[0033] Preferably, the vehicle arrival time prediction system includes:

[0034] Historical Feature Extraction and Model Training System: The neural network system extracts historical features from the historical fusion data. The historical features include: the historical distance of buses from the next station and the corresponding speed, and historical traffic flow. The neural network system is trained and improved using the historical features.

[0035] Real-time feature extraction and prediction system: The neural network system extracts features from the fused data. The features include the current speed of the bus at the same historical moment, the distance to the next station, and the traffic flow. The neural network system then predicts the arrival time of the bus at each station based on the obtained features, resulting in several estimated arrival times corresponding to each station.

[0036] Preferably, the information interaction and feedback system includes:

[0037] Information display and transmission system: A two-way data transmission channel is built through a wireless communication network. The estimated arrival time of buses obtained from the neural network system is sent to the electronic signs at each station through the two-way data transmission channel, and then displayed to passengers on the screens of the electronic signs.

[0038] Passenger Flow and Environmental Information Collection System: This system acquires passenger flow and environmental information within the station through a video acquisition system. The passenger flow information includes the number of passengers, and the environmental information includes the ambient temperature and humidity. The passenger flow and environmental information are then transmitted back to the bus operation and dispatch system via a two-way data transmission channel.

[0039] Preferably, the dynamic scheduling management system includes:

[0040] Dispatch strategy analysis and formulation system: Analyzes the passenger flow information and environmental information, formulates and implements dynamic dispatch strategies based on the analysis results, and the dynamic adjustment strategies include but are not limited to: adjusting the departure time and route of buses, the speed of buses, and increasing or decreasing the number of buses to cope with changing passenger demand and traffic conditions.

[0041] Command and dispatch system: The command and dispatch system implements dynamic dispatching of buses that are running normally and buses waiting in passenger stations according to the dynamic adjustment strategy.

[0042] The beneficial effects of this invention are as follows: This invention achieves accurate prediction of bus arrival times through data fusion and neural network prediction, and optimizes scheduling through two-way data transmission. Electronic bus stop signs display information in real time and provide feedback on passenger flow and environmental data, improving bus operation efficiency and passenger satisfaction, and enhancing the system's convenience and reliability. Attached Figure Description

[0043] Figure 1 This invention relates to an intelligent data interaction method for electronic bus stop signs. Detailed Implementation

[0044] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0045] One embodiment of the present invention provides an intelligent data interaction method for electronic bus stop signs, the method comprising:

[0046] S1: Collect bus location data, bus operation scheduling data, and road condition data through a data acquisition system, and then fuse the bus location data, bus operation scheduling data, and road condition data through a multi-data fusion method to obtain fused data;

[0047] S2: Establish a bus vehicle prediction model, and through the bus vehicle prediction model, predict the arrival time of the bus at each station based on the fused data to obtain several estimated arrival times corresponding to each station.

[0048] S3: A two-way data transmission channel is constructed through a wireless communication network. The estimated arrival time is transmitted to the electronic signboard at the station through the two-way data transmission channel and displayed on the screen of the electronic signboard. At the same time, passenger flow information and environmental information within the station are acquired through a video acquisition system and transmitted back to the bus operation and dispatch system through the two-way data transmission channel.

[0049] S4: The bus operation dispatching system dynamically dispatches buses that are operating normally and buses waiting in passenger stations based on passenger flow information and environmental information.

[0050] The working principle and effects of the above technical solution are as follows: The intelligent data interaction method for electronic bus stop signs achieves precise management and scheduling of public transportation by integrating multiple information systems. First, a data acquisition system collects data on bus location, operational scheduling, and road conditions, and performs multi-data fusion to obtain comprehensive traffic information. Next, based on this fused data, a predictive model calculates the estimated arrival time of vehicles at each station. Subsequently, the calculation results are transmitted to the electronic screens at the stations via a wireless communication network for display, while passenger flow and environmental information within the stations are collected and fed back to the scheduling system. Finally, the scheduling system dynamically schedules vehicles based on this real-time feedback information, optimizing vehicle configuration and operational strategies. This method improves responsiveness to traffic changes by integrating multi-source data and predicting bus arrival times in real time, making information transmission more timely and accurate. Simultaneously, real-time passenger flow and environmental feedback is achieved through two-way data transmission, further optimizing the decision-making capabilities of the scheduling system and ensuring the rational allocation and flexible scheduling of buses. The overall system not only improves the passenger waiting experience and public transportation operational efficiency but also enhances the intelligence and service quality of public transportation, adapting to the changes and needs of modern urban transportation.

[0051] In one embodiment of the present invention, S1 includes:

[0052] S11: Obtain the bus's location data through the positioning device on the bus, the location data including the bus's latitude and longitude, speed and direction of travel;

[0053] S12: Obtain permission to enter the bus operation and dispatch system, and collect bus operation and dispatch data after entering the bus operation and dispatch system. The bus operation and dispatch data includes: bus schedule information and route information.

[0054] S13: Obtain road condition data through the city's traffic monitoring system. The road condition data includes: traffic flow data, bus speed data, and traffic control data.

[0055] S14: Input the location data of buses, bus operation scheduling data and road condition data into the neural network system. The neural network system fuses multiple features to obtain fused data.

[0056] The working principle and effects of the above technical solution are as follows: This method accurately analyzes public transportation operation status through multi-step data collection and fusion. Initially, real-time data such as vehicle latitude, longitude, speed, and direction are collected using vehicle positioning equipment. Next, access to the dispatch system is obtained to acquire detailed information about bus schedules and routes. Simultaneously, the urban traffic monitoring system provides traffic flow, vehicle speed, and traffic control information. By integrating multi-dimensional data from vehicle positioning, the dispatch system, and urban traffic monitoring, this method comprehensively reflects real-time traffic and operational status. Utilizing neural networks for feature fusion improves the accuracy and timeliness of data analysis, providing high-quality information support for prediction and decision-making. This integrated approach not only enhances the understanding of complex traffic conditions but also lays the foundation for optimizing the efficiency of the public transportation system, reducing delays, and improving passenger service quality, thus achieving the goal of intelligent and refined management of the public transportation system.

[0057] In one embodiment of the present invention, S2 includes:

[0058] S21: The neural network system extracts historical features from the historical fusion data. The historical features include: the distance of the bus from the next station in history and the corresponding speed, and the historical traffic flow. The neural network system is trained and improved using the historical features.

[0059] S22: The neural network system extracts features from the fused data. The features include the current speed of the bus at the same historical moment, the distance to the next station, and the traffic flow. The neural network system then predicts the arrival time of the bus at each station based on the obtained features, resulting in several estimated arrival times that correspond one-to-one with each station.

[0060] Furthermore, the neural network system predicts the arrival time based on the following formula:

[0061]

[0062] Where D represents the distance of the bus from the next stop, V represents the real-time speed of the bus, Δt1 represents the time adjustment based on historical characteristics, and Δt2 represents the time adjustment based on real-time traffic conditions.

[0063] Furthermore, Δt1 is obtained using the following formula:

[0064]

[0065] Where N represents the number of historical samples, D i V represents the distance from the i-th record in the historical samples to the next station. iVi represents the speed recorded in the i-th historical sample, and V0 represents the average speed of the bus from startup to the present.

[0066] Furthermore, Δt2 is obtained using the following formula:

[0067] Δt2=t s ×n s +t a ×n a

[0068] Among them, t s n represents the average time the bus has stayed at each traffic light since it departed. s t represents the number of traffic lights. a n represents the average delay caused by each accident affecting the bus from its departure to the present. a This indicates the number of accidents that caused delays to public transportation.

[0069] The working principle and effects of the above technical solution are as follows: This method uses a neural network system to extract and analyze features from historical and current bus operation data. First, the neural network extracts features from historical fused data, such as the distance of vehicles to the next stop, speed, and traffic flow in history. These features are used to train and improve the neural network model. Next, the neural network extracts real-time features from the current fused data, analyzing the current vehicle speed, distance to the next stop, and current traffic flow. By combining these historical and real-time features, the neural network predicts the arrival time of vehicles at each stop, thereby generating effective estimated arrival times and providing accurate support for bus scheduling. This method improves the neural network's adaptability and predictive ability to complex traffic patterns by using historical features to train the model, while the extraction of real-time features ensures an accurate reflection of the current traffic situation. This approach, combining historical experience with real-time data, makes the prediction of bus arrival times more accurate and reliable, thus providing strong support for efficient scheduling and optimization decisions in the bus system, improving overall operational efficiency and passenger satisfaction.

[0070] In the formula for calculating arrival time prediction, the average historical travel time is calculated by using distances and speeds at similar times in the past when calculating Δt1. This reflects the actual situation of travel under similar conditions in the past. By calculating a baseline historical average travel time and comparing it with the current expected travel time, deviations in the current prediction process can be identified. This helps to apply trends or anomalies observed in historical data to current travel predictions. The formula as a whole comprehensively considers current traffic distances and speeds, historical travel data, and real-time traffic conditions to accurately predict the estimated arrival time of public transport vehicles. By introducing effective speed and historical and real-time adjustments, it not only calculates the travel time under ideal conditions but also corrects for deviations that may be caused by historical trends and delays caused by immediate traffic. This method, through a multi-level prediction model, enhances the adaptability to complex traffic environments and improves the accuracy and reliability of public transport systems.

[0071] In one embodiment of the present invention, S3 includes:

[0072] S31: A two-way data transmission channel is established through a wireless communication network. The estimated arrival time of buses obtained from the neural network system is sent to the electronic signs at each station through the two-way data transmission channel, and then displayed on the screen of the electronic signs to passengers.

[0073] S32: Obtain passenger flow information and environmental information within the station through a video acquisition system. The passenger flow information includes the number of passengers, and the environmental information represents the ambient temperature and humidity. Transmit the passenger flow information and environmental information back to the bus operation and dispatch system through a two-way data transmission channel.

[0074] The working principle and effects of the above technical solution are as follows: This method achieves real-time transmission and feedback of public transportation information by establishing a two-way data transmission channel. First, using a wireless communication network, the estimated arrival times of buses are transmitted to electronic display boards at each station and promptly provided to passengers via screens. In addition, video capture systems within stations collect passenger flow information and environmental data, such as passenger numbers, ambient temperature, and humidity. This information is fed back through the same transmission channel to the public transportation operation and dispatch system, providing timely and accurate data support for dispatch decisions. By transmitting estimated arrival times in real time, passengers can obtain arrival information promptly, improving their travel experience. Simultaneously, the real-time feedback of passenger flow and environmental information allows the dispatch system to dynamically adjust its operational strategies, better respond to changes in passenger flow and environmental factors at stations, and optimize the allocation of public transportation resources. This two-way information flow not only improves service quality but also enhances the coordination and responsiveness of the public transportation system, making it more intelligent and passenger-centric.

[0075] In one embodiment of the present invention, S4 includes:

[0076] S41: Analyze the passenger flow information and environmental information, and based on the analysis results, formulate and implement a dynamic scheduling strategy. The dynamic adjustment strategy includes, but is not limited to: adjusting the departure time and route of buses, the speed of buses, and increasing or decreasing the number of buses to cope with changing passenger demand and traffic conditions.

[0077] S42: The command and dispatch system implements dynamic dispatching of buses that are operating normally and buses waiting in passenger stations according to the dynamic adjustment strategy.

[0078] The working principle and effects of the above technical solution are as follows: This method supports dynamic scheduling decisions for public transportation by analyzing passenger flow information and environmental data. First, the system conducts in-depth analysis of this information to obtain a comprehensive view of current operating conditions and passenger demand. Based on these analysis results, dynamic scheduling strategies are formulated, adjusting vehicle departure times, routes, speeds, and frequencies to flexibly respond to changes in passenger numbers and traffic conditions. Then, the command and dispatch system applies these strategies to buses in operation and those on standby, implementing refined dynamic scheduling. Through the analysis of passenger flow and environmental information, this method significantly improves the public transportation system's ability to respond to dynamic demands. By flexibly adjusting vehicle departure times, routes, speeds, and frequencies, it achieves rapid response to changes in passenger demand and traffic conditions. This dynamic scheduling strategy not only improves the operational efficiency and service quality of the public transportation system but also optimizes resource allocation, reduces passenger waiting time and overall travel costs, thereby providing passengers with more reliable and efficient public transportation services.

[0079] One embodiment of the present invention provides an intelligent data interaction system for electronic bus stop signs, the system comprising:

[0080] Data Acquisition and Fusion System: The system collects bus location data, bus operation scheduling data, and road condition data, and then uses a multi-data fusion method to fuse the bus location data, bus operation scheduling data, and road condition data to obtain fused data.

[0081] Vehicle arrival time prediction system: Establish a bus prediction model, and through the bus prediction model, predict the arrival time of buses at each station based on fused data to obtain several estimated arrival times corresponding to each station.

[0082] Information interaction and feedback system: A two-way data transmission channel is built through a wireless communication network. The estimated arrival time is transmitted to the electronic signboard at the station through the two-way data transmission channel and displayed on the screen of the electronic signboard. At the same time, passenger flow information and environmental information within the station are acquired through a video acquisition system and transmitted back to the bus operation and dispatch system through the two-way data transmission channel.

[0083] Dynamic Dispatch Management System: The bus operation dispatch system dynamically dispatches buses that are operating normally and buses waiting in passenger stations based on passenger flow information and environmental information.

[0084] The working principle and effects of the above technical solution are as follows: The intelligent data interaction method for electronic bus stop signs achieves precise management and scheduling of public transportation by integrating multiple information systems. First, a data acquisition system collects data on bus location, operational scheduling, and road conditions, and performs multi-data fusion to obtain comprehensive traffic information. Next, based on this fused data, a predictive model calculates the estimated arrival time of vehicles at each station. Subsequently, the calculation results are transmitted to the electronic screens at the stations via a wireless communication network for display, while passenger flow and environmental information within the stations are collected and fed back to the scheduling system. Finally, the scheduling system dynamically schedules vehicles based on this real-time feedback information, optimizing vehicle configuration and operational strategies. This method improves responsiveness to traffic changes by integrating multi-source data and predicting bus arrival times in real time, making information transmission more timely and accurate. Simultaneously, real-time passenger flow and environmental feedback is achieved through two-way data transmission, further optimizing the decision-making capabilities of the scheduling system and ensuring the rational allocation and flexible scheduling of buses. The overall system not only improves the passenger waiting experience and public transportation operational efficiency but also enhances the intelligence and service quality of public transportation, adapting to the changes and needs of modern urban transportation.

[0085] According to one embodiment of the present invention, the data acquisition and fusion system includes:

[0086] Location data acquisition system: The system acquires the location data of the bus through the positioning device on the bus. The location data includes the latitude and longitude of the bus, its speed and direction of travel.

[0087] Dispatch data access and collection system: Obtains permission to enter the bus operation dispatch system, and collects bus operation dispatch data after entering the bus operation dispatch system. The bus operation dispatch data includes: bus schedule information and route information.

[0088] Road condition data acquisition system: acquires road condition data through the city's traffic monitoring system, including traffic flow data, bus speed data, and traffic control data;

[0089] Data fusion and analysis system: The system inputs the location data of buses, bus operation scheduling data, and road condition data into the neural network system. The neural network system fuses multiple features to obtain fused data.

[0090] The working principle and effects of the above technical solution are as follows: This system accurately analyzes public transportation operation status through multi-step data collection and fusion. Initially, real-time data such as vehicle latitude, longitude, speed, and direction are collected through vehicle positioning equipment. Next, access to the dispatch system is obtained to acquire detailed information on bus schedules and routes. Simultaneously, the urban traffic monitoring system provides traffic flow, vehicle speed, and traffic control information. This method, by integrating multi-dimensional data from vehicle positioning, the dispatch system, and urban traffic monitoring, comprehensively reflects real-time traffic and operational status. Utilizing neural networks for feature fusion improves the accuracy and timeliness of data analysis, providing high-quality information support for prediction and decision-making. This integrated approach not only enhances the understanding of complex traffic conditions but also lays the foundation for optimizing the efficiency of the public transportation system, reducing delays, and improving passenger service quality, thus achieving the goal of intelligent and refined management of the public transportation system.

[0091] In one embodiment of the present invention, the vehicle arrival time prediction system includes:

[0092] Historical Feature Extraction and Model Training System: The neural network system extracts historical features from the historical fusion data. The historical features include: the historical distance of buses from the next station and the corresponding speed, and historical traffic flow. The neural network system is trained and improved using the historical features.

[0093] Real-time feature extraction and prediction system: The neural network system extracts features from the fused data. The features include the current speed of the bus at the same historical moment, the distance to the next station, and the traffic flow. The neural network system then predicts the arrival time of the bus at each station based on the obtained features, resulting in several estimated arrival times corresponding to each station.

[0094] The working principle and effects of the above technical solution are as follows: This system uses a neural network system to extract and analyze features from historical and current bus operation data. First, the neural network extracts features from historical fusion data, such as the distance of vehicles to the next stop, speed, and traffic flow in history. These features are used to train and improve the neural network model. Next, the neural network extracts features from the current fusion data in real time, analyzing the current vehicle speed, distance to the next stop, and current traffic flow. By combining these historical and real-time features, the neural network predicts the arrival time of vehicles at each stop, thereby generating effective estimated arrival times and providing accurate support for bus scheduling. This method improves the neural network's adaptability and predictive ability to complex traffic patterns by using historical features to train the model, while the extraction of real-time features ensures an accurate reflection of the current traffic situation. This approach, combining historical experience with real-time data, makes the prediction of bus arrival times more accurate and reliable, thus providing strong support for efficient scheduling and optimization decisions in the bus system, improving overall operational efficiency and passenger satisfaction.

[0095] In one embodiment of the present invention, the information interaction and feedback system includes:

[0096] Information display and transmission system: A two-way data transmission channel is built through a wireless communication network. The estimated arrival time of buses obtained from the neural network system is sent to the electronic signs at each station through the two-way data transmission channel, and then displayed to passengers on the screens of the electronic signs.

[0097] Passenger Flow and Environmental Information Collection System: This system acquires passenger flow and environmental information within the station through a video acquisition system. The passenger flow information includes the number of passengers, and the environmental information includes the ambient temperature and humidity. The passenger flow and environmental information are then transmitted back to the bus operation and dispatch system via a two-way data transmission channel.

[0098] The working principle and effects of the above technical solution are as follows: This system achieves real-time transmission and feedback of public transportation information by establishing a two-way data transmission channel. First, using a wireless communication network, the estimated arrival times of buses are transmitted to electronic display boards at each station and promptly provided to passengers via screens. In addition, video capture systems within stations collect passenger flow information and environmental data, such as passenger numbers, ambient temperature, and humidity. This information is fed back to the public transportation operation and dispatch system through the same transmission channel, providing timely and accurate data support for dispatch decisions. By transmitting estimated arrival times in real time, passengers can obtain arrival information promptly, improving their travel experience. Simultaneously, the real-time feedback of passenger flow and environmental information allows the dispatch system to dynamically adjust its operational strategies, better respond to changes in passenger flow and environmental factors at stations, and optimize the allocation of public transportation resources. This two-way information flow not only improves service quality but also enhances the coordination and responsiveness of the public transportation system, making it more intelligent and passenger-centric.

[0099] In one embodiment of the present invention, the dynamic scheduling management system includes:

[0100] Dispatch strategy analysis and formulation system: Analyzes the passenger flow information and environmental information, formulates and implements dynamic dispatch strategies based on the analysis results, and the dynamic adjustment strategies include but are not limited to: adjusting the departure time and route of buses, the speed of buses, and increasing or decreasing the number of buses to cope with changing passenger demand and traffic conditions.

[0101] Command and dispatch system: The command and dispatch system implements dynamic dispatching of buses that are running normally and buses waiting in passenger stations according to the dynamic adjustment strategy.

[0102] The working principle and effects of the above technical solution are as follows: This system supports dynamic scheduling decisions for public transportation by analyzing passenger flow information and environmental data. First, the system conducts in-depth analysis of this information to obtain a comprehensive view of current operating conditions and passenger demand. Based on these analysis results, dynamic scheduling strategies are formulated, adjusting vehicle departure times, routes, speeds, and frequencies to flexibly respond to changes in passenger numbers and traffic conditions. Then, the command and dispatch system applies these strategies to buses already in operation and those on standby, implementing refined dynamic scheduling. Through the analysis of passenger flow and environmental information, this method significantly improves the public transportation system's ability to respond to dynamic demands. By flexibly adjusting vehicle departure times, routes, speeds, and frequencies, it achieves rapid response to changes in passenger demand and traffic conditions. This dynamic scheduling strategy not only improves the operational efficiency and service quality of the public transportation system but also optimizes resource allocation, reduces passenger waiting time and overall travel costs, thereby providing passengers with more reliable and efficient public transportation services.

[0103] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. An electronic bulletin board intelligent data interaction method, characterized in that, The method comprises: S1: collecting positioning data of a bus, bus operation scheduling data and road condition data through a data acquisition system, and fusing the positioning data of the bus, the bus operation scheduling data and the road condition data through a multi-data fusion method to obtain fused data; S2: establishing a bus prediction model, and predicting the time of the bus arriving at each station according to the fused data through the bus prediction model to obtain a plurality of predicted arrival times corresponding to each station; S3: constructing a bidirectional data transmission channel through a wireless communication network, transmitting the predicted arrival time to an electronic watch card on the station through the bidirectional data transmission channel, and displaying the predicted arrival time on the display screen of the electronic watch card, and acquiring passenger flow information and environmental information in the station through a video acquisition system, and transmitting the passenger flow information and the environmental information back to the bus operation scheduling system through the bidirectional data transmission channel; S4: the bus operation scheduling system dynamically schedules the normally running bus and the bus on standby in the passenger station according to the passenger flow information and the environmental information; The S2 comprises: S21: a neural network system extracts historical features from historical fused data, the historical features include the distance of the bus from the next station and the corresponding speed in history, and historical traffic flow, and the neural network system is trained using the historical features to improve the neural network; S22: the neural network system extracts features from the fused data, the features include the current speed of the bus at the same time in history, the distance from the next station and the traffic flow, and the neural network system predicts the time of the bus arriving at each station according to the obtained features to obtain a plurality of predicted arrival times corresponding to each station; And the neural network system predicts the arrival time based on the following formula: wherein D represents the distance of the bus vehicle from the next stop, V represents the real-time speed of the bus vehicle, represents the time adjustment amount based on the historical characteristics, represents the time adjustment amount based on the real-time traffic conditions; Also, the is obtained by the following equation: where N represents the number of historical samples, represents the distance from the i-th record in the historical sample to the next site, represents the speed recorded in the i-th record in the historical sample, represents the average speed of the bus from start to present; Also, the is obtained by the following equation: wherein, represents the average time the bus vehicle is stopped at each red light from departure until now, represents the number of red lights, represents the average delay time caused by each accident for the bus vehicle from departure until now, represents the number of accidents causing delay for the bus vehicle.

2. The intelligent data interaction method of electronic station board according to claim 1, characterized in that, The S1 comprises: S11: obtaining positioning data of a bus through a positioning device on the bus, the positioning data including latitude and longitude, speed and direction of the bus; S12: obtaining the permission to enter the bus operation scheduling system, collecting bus operation scheduling data after entering the bus operation scheduling system, the bus operation scheduling data including shift information and route information of the bus; S13: obtaining road condition data through a city traffic monitoring system, the road condition data including traffic flow data, bus speed data and traffic control data; S14: inputting the positioning data of the bus, the bus operation scheduling data and the road condition data into the neural network system, and the neural network system fusing a plurality of features to obtain fused data.

3. The intelligent data interaction method of electronic station board according to claim 1, characterized in that, The S3 comprises: S31: constructing a bidirectional data transmission channel through a wireless communication network, sending the predicted arrival time of the bus obtained from the neural network system to the electronic watch card of each station through the bidirectional data transmission channel, and displaying the predicted arrival time to passengers on the display screen of the electronic watch card. S32: Obtain passenger flow information and environment information in the station through the video acquisition system, the passenger flow information includes the number of passengers, and the environment information indicates an environment temperature and an environment humidity, and the passenger flow information and the environment information are transmitted back to the bus operation scheduling system through a bidirectional data transmission channel.

4. The intelligent data interaction method of electronic station board according to claim 1, characterized in that, The S4 includes: S41: Analyze the passenger flow information and the environment information, and formulate and implement a dynamic scheduling strategy based on an analysis result, the dynamic adjustment strategy including but not limited to: adjusting a bus vehicle departure time and a route, a bus vehicle driving speed, increasing or decreasing a number of shifts to cope with changing passenger demand and traffic conditions; S42: The instruction scheduling system implements dynamic scheduling on the bus normally running and the bus on standby in the passenger station according to the dynamic adjustment strategy.

5. An electronic-stationboard intelligent data interaction system, characterized in that, The system includes: A data acquisition and fusion system: acquiring positioning data of a bus vehicle, bus operation scheduling data and road condition data through a data acquisition system, and fusing the positioning data of the bus vehicle, the bus operation scheduling data and the road condition data through a multi-data fusion method to obtain fused data; A vehicle arrival time prediction system: establishing a bus vehicle prediction model, and predicting, through the bus vehicle prediction model, a time for the bus vehicle to arrive at each station according to the fused data to obtain a plurality of predicted arrival times corresponding to each station one by one; An information interaction and feedback system: constructing a bidirectional data transmission channel through a wireless communication network, transmitting the predicted arrival time to an electronic watch on the station through the bidirectional data transmission channel, and displaying the predicted arrival time on a display screen of the electronic watch, and obtaining passenger flow information and environment information in the station through a video acquisition system, and transmitting the passenger flow information and the environment information back to the bus operation scheduling system through the bidirectional data transmission channel; A dynamic scheduling management system: the bus operation scheduling system implements dynamic scheduling on the bus normally running and the bus on standby in the passenger station according to the passenger flow information and the environment information; The vehicle arrival time prediction system includes: A historical feature extraction and model training system: a neural network system extracts historical features from historical fused data, the historical features including a distance of a bus vehicle from a next station and a corresponding speed in history, and historical traffic flow, and the neural network system is trained using the historical features to improve the neural network; A real-time feature extraction and prediction system: the neural network system extracts features from the fused data, the features including a current speed of the bus vehicle, a distance from the next station and the traffic flow at the same time in history, and the neural network system predicts a time for the bus vehicle to arrive at each station according to the obtained features to obtain a plurality of predicted arrival times corresponding to each station one by one; And the neural network system predicts the arrival time based on the following formula: wherein D represents the distance of the bus vehicle from the next stop, V represents the real-time speed of the bus vehicle, represents the time adjustment amount based on the historical characteristics, represents the time adjustment amount based on the real-time traffic conditions; Also, the is obtained by the following equation: where N represents the number of historical samples, represents the distance from the i-th record in the historical sample to the next station, represents the speed recorded in the i-th record in the historical sample, represents the average speed of the bus from start to present; Also, the is obtained by the following equation: wherein, represents the average time the bus vehicle is stopped at each red light from departure until now, represents the number of red lights, represents the average delay time caused by each accident for the bus vehicle from departure until now, represents the number of accidents that caused the bus vehicle to be delayed.

6. The electronic stopboard intelligent data interaction system according to claim 5, characterized in that, The data acquisition and fusion system includes: A positioning data acquisition system: acquiring positioning data of a bus vehicle through a positioning device on the bus vehicle, the positioning data including latitude and longitude, a driving speed and a driving direction of the bus vehicle; The scheduling data access and collection system: obtains the right to enter the bus operation scheduling system, collects bus operation scheduling data after entering the bus operation scheduling system, and the bus operation scheduling data includes: shift information and route information of the bus; The road condition data collection system: obtains road condition data through the city traffic monitoring system, and the road condition data includes: traffic flow data, bus speed data and traffic control data; The data fusion and analysis system: inputs the positioning data of the bus, the bus operation scheduling data and the road condition data into the neural network system, the neural network system fuses multiple features to obtain fused data.

7. The intelligent data interaction system of electronic bulletin board according to claim 5, characterized in that, The information interaction and feedback system includes: The information display and transmission system: constructs a bidirectional data transmission channel through a wireless communication network, sends the estimated arrival time of the bus obtained from the neural network system to the electronic display of each station through the bidirectional data transmission channel, and displays the estimated arrival time of the bus on the display screen of the electronic display for passengers; The passenger flow and environmental information collection system: obtains passenger flow information and environmental information in the station through a video collection system, the passenger flow information includes the number of passengers, the environmental information represents the environmental temperature and the environmental humidity, and the passenger flow information and the environmental information are transmitted back to the bus operation scheduling system through the bidirectional data transmission channel.

8. The intelligent data interaction system of electronic bulletin board according to claim 5, characterized in that, The dynamic scheduling management system includes: The scheduling strategy analysis and formulation system: analyzes the passenger flow information and the environmental information, formulates and implements a dynamic scheduling strategy based on the analysis result, and the dynamic adjustment strategy includes but is not limited to: adjusting the departure time and route of the bus, the driving speed of the bus, and increasing or decreasing the number of shifts to cope with the changing passenger demand and traffic conditions; The instruction scheduling system: the instruction scheduling system implements dynamic scheduling on the bus normally running and the bus on standby in the passenger station according to the dynamic adjustment strategy.

Images