Information management method, system, device and medium for bus electronic stop sign

Abstract

The present invention relates to the field of intelligent transportation technology and discloses an information management method, system, device, and medium for electronic bus stops. The method comprises: obtaining bus travel data, historical traffic data, and urban transportation system data; preprocessing the bus travel data and the urban transportation system data to obtain a feature vector of the bus; inputting the feature vector of the bus into a preset prediction model to calculate the estimated waiting time and the degree of congestion in the carriage; and sending the estimated waiting time and the degree of congestion in the carriage to the corresponding electronic bus stop and displaying them. The present invention accurately predicts bus waiting times by establishing a random forest model that combines traffic congestion and weather conditions, and calculates the degree of congestion in the carriage based on historical data, thereby improving the passenger experience.

Description

Technical Field

[0001] The present invention relates to the field of smart transportation technology, and in particular to an information management method, system, equipment and medium for an electronic bus stop sign. Background Art

[0002] In recent years, with the development of public transportation and the continuous growth of society, economy, and urban population, people's demand for public transportation has become increasingly greater and more demanding. Urban public transportation has become the main mode of transportation for the public. Currently, most cities have installed electronic bus stop systems on their buses. These systems use LCD screens installed in the bus stops to provide real-time bus information such as the bus's real-time location, arrival time, and distance to the station.

[0003] Existing methods for managing bus stop information primarily rely on wireless communication systems to transmit bus location information to LCD screens. The displayed content and style are then set to a static template that changes periodically according to a specific pattern. In practice, this method suffers from inaccurate information, which can easily prevent passengers from obtaining accurate location information. These issues primarily manifest in the following ways: Bus companies fail to update vehicle location information promptly, resulting in vehicles not arriving at stops within the waiting time indicated on the sign, delaying passengers' travel; Vehicles may operate slowly due to weather, road conditions, and other factors, but passengers may not receive updated waiting time information during the waiting time, delaying their boarding; The route information displayed on electronic stop signs can only be preset in advance. When buses temporarily change their routes based on road conditions, they may not be displayed immediately at the stops, causing inconvenience to passengers.

[0004] In addition, in the existing method for real-time display of bus electronic bus stop information, the principle of calculating the real-time arrival time of buses is generally as follows: the electronic bus stop information shows that the estimated time from a certain station to this station is T minutes, then the time from this station to the next station = the time from the previous station to this station - the time elapsed, that is, (the time to this station - the time to the previous station). When a vehicle travels from station A to the next station, station B, the travel time from station A to station B is obtained through the positioning system installed in the vehicle, and the time taken from station A to station B is obtained on the electronic screen of station B. Since the arrival time is only an estimate of the running time, when the vehicle's operation between platforms is affected by weather, road conditions, temporary stops, etc., the time between stations increases, and the electronic bus stop often cannot accurately display the estimated arrival time at the station.

[0005] In summary, the electronic bus stop signs in the prior art cannot accurately display the estimated time of arrival at the station, causing inconvenience to passengers. Summary of the Invention

[0006] The present invention provides an information management method, system, device and medium for a bus electronic bus stop sign, so as to solve the technical problem in the prior art that the electronic bus stop sign cannot accurately display the estimated arrival time at the station, causing inconvenience to passengers.

[0007] In a first aspect, in order to solve the above technical problems, the present invention provides an information management method for an electronic bus stop sign, comprising:

[0008] Obtain bus driving data, historical traffic data and urban transportation system data;

[0009] Preprocessing the bus travel data and the urban transportation system data to obtain a feature vector of the bus;

[0010] Inputting the characteristic vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the carriage;

[0011] The estimated waiting time and the carriage congestion level are sent to a corresponding electronic bus stop and displayed.

[0012] As an optional implementation, the bus driving data includes date, driving route data, vehicle location data, bus capacity, number of passengers in the car and driving speed data; the historical traffic data includes the historical stop time of each station, the average number of passengers getting on and off at each station on weekdays and the average number of passengers getting on and off at each station on holidays; the urban transportation system data includes traffic flow data of bus operating sections, electronic bus stop location data, traffic signal data, maximum traffic capacity of each section and weather conditions data.

[0013] As an optional implementation manner, the preprocessing of the bus travel data and the urban transportation system data to obtain the bus feature vector includes:

[0014] Filtering and averaging the driving speed data included in the driving data of the bus to obtain an average vehicle speed;

[0015] The weather condition data contained in the urban traffic system data is classified according to the degree of influence on vehicle speed. Assume that the weather condition data of a certain day is w, w = {0, 1, 2, 3, 4, 5, 6}, where 0 represents sunny, cloudy and overcast, 1 represents light rain, 2 represents heavy rain, 3 represents light haze, 4 represents heavy haze, 5 represents light snow, and 6 represents heavy snow, and the weather influence coefficient is obtained;

[0016] Calculating a congestion coefficient based on traffic flow data of bus operation sections and the maximum traffic capacity of each section included in the urban transportation system data;

[0017] Calculating the distance between the bus and the electronic bus stop and the number of traffic lights passed by the bus based on the driving route data and vehicle position data included in the driving data of the bus and the electronic bus stop position data and traffic signal data included in the urban transportation system data;

[0018] The average speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, number of traffic lights passed, historical stop time and date of each station, number of passengers on the bus, number of passengers in the car, average number of passengers getting on and off at each station on weekdays, and average number of passengers getting on and off at each station on holidays are vectorized and used as the feature vector of the bus.

[0019] As an optional implementation, the preset prediction model includes a random forest model for predicting waiting time and a carriage congestion calculation model, wherein the training process of the random forest model includes:

[0020] Generate a waiting time training set based on the average vehicle speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, number of traffic lights passed, historical stop time and historical waiting time of each station in the historical database;

[0021] Using the bootstrap sampling method on the waiting time training set to generate a sub-training set, using the sub-training set to train the initial random forest model, and constructing a random forest model including k CART decision trees;

[0022] The random forest model composed of a set of k CART decision trees is expressed as:

[0023] F={h1(T),h2(T),…,h k (T)}

[0024] Where T is the input data of the random forest model, h i In (T), i=1, 2,…, k represents the CART decision tree.

[0025] As an optional implementation, inputting the characteristic vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the bus compartment includes:

[0026] The average speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop sign, and number of traffic lights passed in the feature vector of the bus are input into the random forest model included in the prediction model for prediction. The k CART decision trees configured in the random forest model vote on the prediction results to obtain the estimated waiting time;

[0027] The date, the rated passenger capacity of the bus, the number of passengers in the bus, the average number of passengers getting on and off at each station on weekdays, and the average number of passengers getting on and off at each station on holidays in the feature vector of the bus are input into the carriage congestion calculation model included in the prediction model for calculation to obtain the carriage congestion level.

[0028] As an optional implementation, the date, vehicle location data, electronic bus stop location data, bus capacity, number of passengers in the bus, average number of passengers getting on and off at each station on weekdays, and average number of passengers getting on and off at each station on holidays in the bus feature vector are input into the carriage congestion calculation model included in the prediction model to calculate the carriage congestion level, specifically:

[0029] The date is determined. If the date is a weekday, the number of passengers in the carriage is added to the average number of passengers getting on and off on weekdays at all stations between the vehicle location data and the electronic bus stop location data to obtain the expected number of passengers. 预计 / n 核载 As the degree of crowdedness in the carriage, where n 预计 is the expected number of passengers, and n 核载 is the number of passengers on the bus; if the date is a holiday, the number of passengers in the car is added to the average number of passengers getting on and off on holidays at all stations between the vehicle location data and the electronic bus stop location data to obtain the expected number of passengers, and n is used as the 预计 / n 核载 As the degree of congestion in the carriage.

[0030] As an optional implementation, the sending and displaying of the estimated waiting time and the carriage congestion level to a corresponding electronic station sign includes:

[0031] Dividing the estimated waiting time by the historical average waiting time in the database to obtain a division result, if the division result is greater than or equal to a preset first multiple, determining that the road is congested, and sending the estimated waiting time to the corresponding electronic bus stop; if the division result is less than the preset first multiple and greater than a preset second multiple, determining that the road is relatively unobstructed as a result, and sending the estimated waiting time to the corresponding electronic bus stop; if the division result is less than the preset second multiple, determining that the road is unobstructed as a result, and sending the estimated waiting time to the corresponding electronic bus stop;

[0032] Sending the carriage congestion level to the corresponding electronic bus stop;

[0033] After receiving the estimated waiting time and the degree of congestion in the carriage, the electronic station board displays the information in a scrolling manner on a display screen configured for the electronic station board.

[0034] In a second aspect, the present invention provides an information management system for electronic bus stop signs, comprising:

[0035] Data acquisition module, used to obtain bus driving data, historical traffic data and urban transportation system data;

[0036] A preprocessing module, configured to preprocess the bus travel data and the urban traffic system data to obtain a feature vector of the bus;

[0037] A prediction module, configured to input the characteristic vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the carriage;

[0038] The display module is used to send the estimated waiting time and the carriage congestion level to a corresponding electronic bus stop and display them.

[0039] In a third aspect, the present invention also provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for managing the information of the electronic bus stop as described above is implemented.

[0040] In a fourth aspect, the present invention also provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned bus electronic stop information management methods.

[0041] Compared with the prior art, the present invention has the following beneficial effects:

[0042] The method involves obtaining bus travel data, historical traffic data, and urban transportation system data; preprocessing the bus travel data and urban transportation system data to obtain a bus feature vector; inputting the bus feature vector into a preset prediction model to calculate an estimated waiting time and carriage congestion level; and transmitting the estimated waiting time and carriage congestion level to the corresponding electronic bus stop sign for display. This method improves the passenger experience by establishing a random forest model that combines traffic congestion and weather conditions to accurately predict bus waiting times and calculate carriage congestion levels based on historical data. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of a method for managing information of an electronic bus stop sign provided by the first embodiment of the present invention;

[0044] Figure 2It is a structural diagram of an information management system for an electronic bus stop sign provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0046] Reference Figure 1 The first embodiment of the present invention provides a method for managing information of a bus electronic stop sign, comprising the following steps:

[0047] S11, obtaining bus travel data, historical traffic data and urban transportation system data;

[0048] S12, preprocessing the bus travel data and the urban transportation system data to obtain a feature vector of the bus;

[0049] S13, inputting the characteristic vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the bus compartment;

[0050] S14, sending the estimated waiting time and the carriage congestion level to a corresponding electronic bus stop and displaying them.

[0051] To facilitate understanding of the present invention, some preferred embodiments of the present invention are further described below.

[0052] In step S11, it should be noted that bus driving data, historical traffic data, and urban transportation system data are obtained. Bus driving data includes date, route data, vehicle location data, bus capacity, number of passengers in the bus cabin, and driving speed data. Furthermore, the date is used to distinguish between weekdays and holidays. The route data and vehicle location data are used to calculate the distance between the bus's location and each electronic bus stop sign and the number of traffic lights passed. The route data is obtained from the bus operation system, and the vehicle location data is obtained from the bus's GPS positioning system. The bus capacity and number of passengers in the bus cabin are used to calculate the level of passenger congestion. The bus capacity is obtained from the bus operation system and can be found by looking up the bus model. The number of passengers in the bus cabin is obtained from a thermal imaging camera installed on the bus, which processes images captured by the thermal imaging camera to calculate the number of passengers in the bus cabin. The driving speed data is obtained from the bus's speed measurement system and represents the bus's speed change curve during the measurement period, which is used to calculate the estimated waiting time.

[0053] Historical traffic data includes the historical stop times at each station, the average number of boarding and alighting passengers at each station on weekdays, and the average number of boarding and alighting passengers at each station on holidays. Furthermore, the historical stop times at each station are the average time buses on that route spend at each station along the route, and are used to calculate the estimated wait time. Because the number of passengers at some stations differs significantly between weekdays and holidays, separate calculations should be performed for weekdays and holidays when calculating carriage congestion. The average number of boarding and alighting passengers at each station on weekdays is the average number of boarding and alighting passengers at each station along the route on weekdays. This average number is calculated by averaging the number of boarding and alighting passengers at each station during the bus's operating period. If the number of boarding passengers exceeds the number of alighting passengers, the average number is positive; if the number of boarding passengers equals the number of alighting passengers, the average number is zero; and if the number of boarding passengers is less than the number of alighting passengers, the average number is negative. Similarly, the average number of passengers getting on and off at each station on holidays is the average number of passengers getting on and off at each station along the route of the bus on statutory holidays, including weekends, and is obtained by averaging the number of passengers getting on and off at each station on holidays during the bus operation period of the route. In another embodiment, the average number of passengers getting on and off at each station on weekdays can be further subdivided into the average number of passengers getting on and off at each station on Mondays, the average number of passengers getting on and off at each station on Tuesdays, the average number of passengers getting on and off at each station on Wednesdays, the average number of passengers getting on and off at each station on Thursdays, and the average number of passengers getting on and off at each station on Fridays. The average number of passengers getting on and off at each station on holidays can be further subdivided into the average number of passengers getting on and off at each station on Saturdays, the average number of passengers getting on and off at each station on Sundays, and the average number of passengers getting on and off at each station on holidays.

[0054] Urban transportation system data includes traffic flow data for bus routes, electronic bus stop location data, traffic signal data, maximum capacity of each route, and weather data. Furthermore, the traffic flow data for bus routes and the maximum capacity of each route are used to calculate the congestion coefficient for each route. The congestion coefficient describes the degree of congestion on the bus route. The traffic flow data for bus routes and the maximum capacity of each route are obtained through the urban transportation system. The traffic flow data for bus routes represents the actual traffic volume for each route during a measurement period, and the maximum capacity for each route represents the maximum capacity of each route, which is related to the number of lanes on the road. The electronic bus stop location data and traffic signal data are used to calculate the distance between the bus location and each electronic bus stop and the number of traffic lights passed by the bus. The weather condition data is the weather condition data of the area where the bus route is located on that date. On the premise of fully considering the local climate characteristics, the possible weather conditions are defined, including sunny, cloudy, overcast, light rain, heavy rain, light haze, heavy haze, light snow and heavy snow.

[0055] In step S12, it should be noted that the bus travel data and the urban transportation system data are preprocessed to obtain a bus feature vector. Furthermore, the speed data included in the bus travel data is filtered and averaged to obtain an average vehicle speed. Specifically, the travel speed data is first smoothed using a moving average filter, and then filtered using a Kalman filter to effectively remove noise from the speed data. The filtered speed data is then averaged to obtain the average vehicle speed.

[0056] Furthermore, the weather condition data contained in the urban traffic system data is classified according to the degree of influence on vehicle speed. Assume that the weather condition data for a certain day is w, w = {0, 1, 2, 3, 4, 5, 6}, where 0 represents sunny, cloudy, and overcast, 1 represents light rain, 2 represents heavy rain, 3 represents light haze, 4 represents heavy haze, 5 represents light snow, and 6 represents heavy snow. Then, based on the different impacts of different weather conditions on bus speed, different weather conditions are converted into numerical values of different sizes as weather impact coefficients. The weather impact coefficient takes a value between 0 and 1. For example, the weather impact coefficients corresponding to sunny, cloudy, and overcast days are defined as 1, the weather impact coefficient corresponding to light rain is defined as 0.95, and the weather impact coefficient corresponding to heavy rain is defined as 0.85.

[0057] Furthermore, the congestion coefficient is calculated based on the traffic data of the bus operating sections and the maximum traffic capacity of each section contained in the urban traffic system data. Specifically, the traffic data of the bus operating section on a certain section is divided by the maximum traffic capacity of the section to obtain the congestion coefficient, which takes a value between 0 and 1, for example 0.6.

[0058] Furthermore, the distance between the bus and the electronic bus stop and the number of traffic lights passed by the bus are calculated based on the route data and vehicle position data included in the bus's travel data and the electronic bus stop position data and traffic signal data included in the urban transportation system data. Specifically, the route data included in the bus's travel data is divided into multiple sections, and the sections that the bus needs to pass through to reach each electronic bus stop are calculated based on the vehicle position data and the electronic bus stop position data included in the urban transportation system data. The lengths of these sections are then summed to obtain the distance between the bus and the electronic bus stop. Preferably, the number of traffic lights included in the sections that the bus needs to pass through to reach each electronic bus stop is calculated in combination with the traffic signal data to obtain the number of traffic lights passed by the bus.

[0059] Furthermore, the average vehicle speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, number of traffic lights passed, historical stop time and date of each station, number of passengers allowed to ride on the bus, number of passengers in the car, average number of passengers getting on and off at each station on weekdays, and average number of passengers getting on and off at each station on holidays are vectorized as the feature vector of the bus.

[0060] In step S13, it should be noted that the bus's feature vector is input into a preset prediction model to calculate the estimated waiting time and the level of passenger compartment crowding. Furthermore, the preset prediction model includes a random forest model for predicting waiting time and a model for calculating passenger compartment crowding. The random forest model is a supervised machine learning algorithm for classification and regression. It boasts high classification accuracy, fast training, strong model generalization, and good interpretability, and is widely used in classification problems. Its basic concept is to randomly select and train multiple base classifiers with weaker classification capabilities, resulting in an ensemble classifier with stronger classification capabilities. Each CART decision tree is trained by randomly selecting a subset from the original dataset, and each CART decision tree is trained on a random subset. The prediction result of the random forest model is the majority vote or average of the prediction results of all CART decision trees. Each CART decision tree in the random forest is generated using samples from the dataset with replacement. Each CART decision tree is partitioned according to a specific feature of the sample. During this process, a generated random vector is used to control the generation of each CART decision tree. The CART decision tree is a base classifier that follows a tree-like model for feature splitting. Starting from the root node, the tree selects the feature with the best splitting effect for each split. This splitting process is repeated for the resulting child nodes, growing branches layer by layer until the child nodes can no longer split. The CART decision tree uses the Gini coefficient as the basis for node splitting. A smaller Gini coefficient indicates lower impurity and better classification performance. The expression of the Gini coefficient is a relatively simple quadratic operation. Therefore, using the CART decision tree as a base classifier can reduce the computational complexity of the random forest model to a certain extent. Multiple CART decision trees are organically linked to form a random forest. The original training sample is first randomly sampled multiple times to obtain multiple sub-training samples. The original feature geometry is then randomly sampled multiple times to obtain multiple sub-feature sets. Then, a CART decision tree model is constructed on each sub-training sample based on the random sub-feature set. Finally, the classification results of multiple CART decision tree models are combined using a voting method to obtain the random forest model and results.

[0061] Furthermore, the training process of the random forest model includes:

[0062] A waiting time training set is generated based on the average vehicle speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, number of traffic lights passed, historical stop time and historical waiting time of each station in the historical database. The bootstrap sampling method is used for the waiting time training set to generate a sub-training set. One sample is randomly and with replacement drawn from the waiting time training set containing n training samples each time, and repeated n times to obtain a sub-sample set containing n. There may be repeated samples in the sub-sample set, but since this repetition is random, it will not affect the model effect. Repeat the above sampling process k times to obtain k sub-sample sets, where k is the number of base classifiers in the random forest model, for example, k = 100.

[0063] The initial random forest model is trained using the sub-training set to construct a random forest model containing k CART decision trees. The bootstra sampling method allows multiple sample sets to be constructed under the condition that the data size of each sub-sample set is not less than that of the complete sample set. The CART algorithm is used to construct a decision tree model on each bootstrap sub-sample set. The decision tree based on the CART algorithm uses the Gini coefficient as a measure of feature selection and splitting. The Gini coefficient represents the classification impurity of the feature. The smaller the Gini coefficient, the higher the classification purity and the better the classification effect of the feature. Therefore, all features of the decision tree feature subset are traversed, and the feature with the smallest Gini coefficient is selected as the splitting feature of the current node. The k CART decision trees are combined into a random forest model.

[0064] The random forest model composed of a set of k CART decision trees is expressed as:

[0065] F={h1(T),h2(T),…,h k (T)}

[0066] Where T is the input data of the random forest model, h i In (T), i=1, 2,…, k represents the CART decision tree.

[0067] Furthermore, the feature vector of the bus is input into a preset prediction model to calculate the expected waiting time and the degree of congestion in the carriage, including: inputting the average speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, and number of traffic lights passed in the feature vector of the bus into a random forest model contained in the prediction model for prediction, and the k CART decision trees configured in the random forest model vote on the prediction results, and the prediction result with the highest number of votes is used as the expected waiting time.

[0068] Furthermore, the date, the rated passenger capacity of the bus, the number of passengers in the car, the average number of passengers getting on and off at each station on weekdays, and the average number of passengers getting on and off at each station on holidays in the characteristic vector of the bus are input into the car crowding calculation model contained in the prediction model to calculate the car crowding degree. Specifically, the date is first determined to determine whether the current date is a weekday or a holiday. Since the number of passengers at some stations is quite different on weekdays and holidays, the calculations should be made separately for weekdays and holidays when calculating the car crowding degree. If the date is a weekday, the number of passengers in the car and the average number of passengers getting on and off at all stations corresponding to the vehicle position data and the electronic bus stop position data on weekdays are added to obtain the expected number of passengers, and n is calculated. 预计 / n 核载 As the degree of crowdedness in the carriage, where n 预计 is the expected number of passengers, and n 核载 is the number of passengers on the bus; if the date is a holiday, the number of passengers in the car is added to the average number of passengers getting on and off on holidays at all stations between the vehicle location data and the electronic bus stop location data to obtain the expected number of passengers, and n is used as the 预计 / n 核载 As the degree of congestion in the carriage.

[0069] In step S14, it should be noted that the estimated waiting time and the degree of congestion in the carriage are sent to the corresponding electronic bus stop and displayed. Furthermore, the estimated waiting time is divided by the historical average waiting time in the database to obtain a division result. If the division result is greater than or equal to a preset first multiple, the road congestion is determined as a result, and the estimated waiting time is sent to the corresponding electronic bus stop, wherein the preset first multiple is preset based on past experience and has a value greater than 1, such as 1.5. If the division result is less than the preset first multiple and greater than a preset second multiple, the road is relatively unobstructed as a result, and the estimated waiting time is sent to the corresponding electronic bus stop, wherein the preset second multiple is preset based on past experience and has a value greater than 1 and less than the preset first multiple, such as 1.1. If the division result is less than the preset second multiple, the road is unobstructed as a result, and the estimated waiting time is sent to the corresponding electronic bus stop.

[0070] Furthermore, the data terminal sends the carriage congestion level to the corresponding electronic bus stop sign.

[0071] Furthermore, after receiving the estimated waiting time and the degree of congestion in the carriage, the electronic bus stop board scrolls and displays the information on a display screen configured for the electronic bus stop board.

[0072] Existing methods for managing bus stop information primarily rely on wireless communication systems to transmit bus location information to LCD screens. The displayed content and style are then set to a static template that changes periodically according to a specific pattern. In practice, this method suffers from inaccurate information, which can easily prevent passengers from obtaining accurate location information. These issues primarily manifest in the following ways: Bus companies fail to update vehicle location information promptly, resulting in vehicles not arriving at stops within the waiting time indicated on the sign, delaying passengers' travel; Vehicles may operate slowly due to weather, road conditions, and other factors, but passengers may not receive updated waiting time information during the waiting time, delaying their boarding; The route information displayed on electronic stop signs can only be preset in advance. When buses temporarily change their routes based on road conditions, they may not be displayed immediately at the stops, causing inconvenience to passengers.

[0073] In addition, in the existing method for real-time display of bus electronic bus stop information, the principle of calculating the real-time arrival time of buses is generally as follows: the electronic bus stop information shows that the estimated time from a certain station to this station is T minutes, then the time from this station to the next station = the time from the previous station to this station - the time elapsed, that is, (the time to this station - the time to the previous station). When a vehicle travels from station A to the next station, station B, the travel time from station A to station B is obtained through the positioning system installed in the vehicle, and the time taken from station A to station B is obtained on the electronic screen of station B. Since the arrival time is only an estimate of the running time, when the vehicle's operation between platforms is affected by weather, road conditions, temporary stops, etc., the time between stations increases, and the electronic bus stop often cannot accurately display the estimated arrival time at the station.

[0074] In response to the above-mentioned problems, the present invention provides an information management method for bus electronic bus stops, which obtains bus driving data, historical traffic data and urban traffic system data; pre-processes the bus driving data and the urban traffic system data to obtain a feature vector of the bus; inputs the feature vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the carriage; and sends the expected waiting time and the degree of congestion in the carriage to the corresponding electronic bus stop and displays them.

[0075] The method provided by the present invention accurately predicts the waiting time for buses by establishing a random forest model that combines traffic congestion and weather conditions, and calculates the degree of congestion in the carriage based on historical data, thereby improving the passenger riding experience.

[0076] Reference Figure 2 , is a system structure diagram of an information management system for bus electronic stop signs provided by the present invention.

[0077] A second embodiment of the present invention provides an information management system for electronic bus stop signs, including:

[0078] Data acquisition module 210, used to obtain bus driving data, historical traffic data and urban transportation system data;

[0079] A preprocessing module 220 is used to preprocess the bus travel data and the urban transportation system data to obtain a feature vector of the bus;

[0080] Prediction module 230, configured to input the feature vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the bus compartment;

[0081] The display module 240 is used to send the estimated waiting time and the carriage congestion level to a corresponding electronic bus stop sign and display them.

[0082] Preferably, the data acquisition module 210 is configured to acquire bus travel data, historical traffic data, and urban transportation system data. Bus travel data includes date, route, vehicle location, approved passenger capacity, number of passengers in the bus, and travel speed. Historical traffic data includes historical stop times at each station, the average number of passengers boarding and alighting at each station on weekdays, and the average number of passengers boarding and alighting at each station on holidays. Urban transportation system data includes traffic flow data for bus routes, electronic bus stop location data, traffic signal data, maximum capacity of each route, and weather data.

[0083] Preferably, the preprocessing module 220 is used to preprocess the bus driving data and the urban traffic system data to obtain the bus feature vector. The preprocessing module 220 includes a vehicle speed processing unit, a weather processing unit, a congestion coefficient calculation unit, a traffic route unit and a vectorization unit.

[0084] Furthermore, the vehicle speed processing unit is used to filter and average the driving speed data contained in the driving data of the bus to obtain an average vehicle speed.

[0085] Furthermore, the weather processing unit is used to classify the weather condition data contained in the urban traffic system data according to the degree of influence on the vehicle speed. Suppose the weather condition data of a certain day is w, w = {0, 1, 2, 3, 4, 5, 6}, where 0 represents sunny, cloudy and overcast, 1 represents light rain, 2 represents heavy rain, 3 represents light haze, 4 represents heavy haze, 5 represents light snow, and 6 represents heavy snow, and the weather impact coefficient is obtained.

[0086] Furthermore, the congestion coefficient calculation unit is used to calculate the congestion coefficient based on the traffic flow data of the bus operation section contained in the urban traffic system data and the maximum traffic capacity of each section.

[0087] Furthermore, the traffic route unit is used to calculate the distance between the bus and the electronic bus stop and the number of traffic lights passed by based on the driving route data and vehicle position data contained in the bus driving data and the electronic bus stop position data and traffic signal data contained in the urban traffic system data.

[0088] Furthermore, the vectorization unit is used to vectorize the average vehicle speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, number of traffic lights passed, historical stop time of each station, date, bus capacity, number of passengers in the car, average number of passengers getting on and off at each station on weekdays, and average number of passengers getting on and off at each station on holidays as the feature vector of the bus.

[0089] Preferably, the prediction module 230 is used to input the feature vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the carriage. The prediction module 230 includes a training unit, a waiting time prediction unit, and a degree of congestion in the carriage calculation unit.

[0090] Furthermore, the training unit is used to generate a waiting time training set based on the average vehicle speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, number of traffic lights passed, historical stop time and historical waiting time of each station in the historical database;

[0091] Using the bootstrap sampling method on the waiting time training set to generate a sub-training set, using the sub-training set to train the initial random forest model, and constructing a random forest model including k CART decision trees;

[0092] The random forest model composed of a set of k CART decision trees is expressed as:

[0093] F={h1(T),h2(T),…,h k (T)}

[0094] Where T is the input data of the random forest model, h i In (T), i=1, 2,…, k represents the CART decision tree.

[0095] Furthermore, the waiting time prediction unit is used to input the average speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, and number of traffic lights passed in the feature vector of the bus into the random forest model contained in the prediction model for prediction. The k CART decision trees configured in the random forest model vote on the prediction results to obtain the estimated waiting time.

[0096] Furthermore, the carriage congestion calculation unit is used to input the date, the bus's rated passenger capacity, the number of passengers in the carriage, the average number of passengers getting on and off at each station on weekdays, and the average number of passengers getting on and off at each station on holidays in the feature vector of the bus into the carriage congestion calculation model included in the prediction model for calculation. The carriage congestion calculation model determines the date. If the date is a weekday, the number of passengers in the carriage is added to the average number of passengers getting on and off at all stations corresponding to weekdays between the vehicle location data and the electronic bus stop location data to obtain the expected number of passengers, and n is used as the number of passengers in the carriage. 预计 / n 核载 As the degree of crowdedness in the carriage, where n 预计 is the expected number of passengers, and n 核载 is the number of passengers on the bus; if the date is a holiday, the number of passengers in the car is added to the average number of passengers getting on and off on holidays at all stations between the vehicle location data and the electronic bus stop location data to obtain the expected number of passengers, and n is used as the 预计 / n 核载 As the degree of congestion in the carriage.

[0097] Preferably, the display module 240 is used to send the estimated waiting time and the carriage congestion level to the corresponding electronic bus stop and display them. The display module 240 includes a determination unit, a sending unit, and a display unit.

[0098] Furthermore, the determination unit is used to determine the road congestion condition, divide the expected waiting time and the historical average waiting time in the database to obtain a division result. If the division result is greater than or equal to a preset first multiple, the road congestion is taken as the determination result; if the division result is less than the preset first multiple and greater than a preset second multiple, the road is relatively smooth as the determination result; if the division result is less than the preset second multiple, the road is smooth as the determination result.

[0099] Furthermore, the sending unit is used to send the determination result in combination with the estimated waiting time to the corresponding electronic bus stop, and send the carriage congestion level to the corresponding electronic bus stop.

[0100] Furthermore, the display unit is used to scroll and display the received estimated waiting time and the degree of congestion in the carriage on a display screen configured for the electronic bus stop.

[0101] An embodiment of the present invention further provides an electronic device. The electronic device includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above-mentioned embodiments of the method for managing information of the electronic bus stop are implemented, such as Figure 1 Alternatively, when the processor executes the computer program, the functions of the modules / units in the above-mentioned device embodiments are realized, such as the data acquisition module.

[0102] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0103] The electronic device may be a computing device such as a desktop computer, notebook, PDA, or smart tablet. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will appreciate that the aforementioned components are merely examples of electronic devices and do not constitute a limitation of the electronic device. The electronic device may include more or fewer components than those described above, or a combination of certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, and the like.

[0104] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the electronic device, connecting various parts of the entire electronic device using various interfaces and lines.

[0105] The memory can be used to store the computer programs and / or modules, and the processor realizes various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created based on the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0106] Wherein, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0107] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed across multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment. In addition, in the drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art can understand and implement the present invention without inventive effort.

[0108] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for managing information of a bus electronic stop sign, characterized in that: Executed by the data terminal include: Obtain bus driving data, historical traffic data and urban transportation system data; Preprocessing the bus travel data and the urban transportation system data to obtain a feature vector of the bus; Inputting the characteristic vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the carriage; Sending the estimated waiting time and the degree of congestion in the carriage to a corresponding electronic station sign and displaying them; The preset prediction model includes a random forest model for predicting waiting time and a carriage congestion calculation model, wherein the training process of the random forest model includes: Generate a waiting time training set based on the average vehicle speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, number of traffic lights passed, historical stop time and historical waiting time of each station in the historical database; Using the bootstrap sampling method on the waiting time training set to generate a sub-training set, using the sub-training set to train the initial random forest model, and constructing a random forest model including k CART decision trees; The random forest model composed of a set of k CART decision trees is expressed as: ； Where T is the input data of the random forest model, middle , represents the CART decision tree; The method of inputting the characteristic vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the bus carriage includes: The average speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop sign, and number of traffic lights passed in the feature vector of the bus are input into the random forest model included in the prediction model for prediction. The k CART decision trees configured in the random forest model vote on the prediction results to obtain the estimated waiting time; The date, the rated passenger capacity of the bus, the number of passengers in the bus, the average number of passengers getting on and off at each station on weekdays, and the average number of passengers getting on and off at each station on holidays in the feature vector of the bus are input into the carriage congestion calculation model included in the prediction model for calculation to obtain the carriage congestion level.

2. The method for managing information of an electronic bus stop sign according to claim 1, characterized in that: The bus driving data includes date, driving route data, vehicle location data, bus capacity, number of passengers in the car and driving speed data; the historical traffic data includes the historical stop time of each station, the average number of passengers getting on and off at each station on weekdays and the average number of passengers getting on and off at each station on holidays; the urban transportation system data includes traffic flow data of bus operating sections, electronic bus stop location data, traffic signal data, maximum traffic capacity of each section and weather conditions data.

3. The method for managing information of an electronic bus stop sign according to claim 1, characterized in that: The preprocessing of the bus travel data and the urban traffic system data to obtain a feature vector of the bus includes: Filtering and averaging the driving speed data included in the driving data of the bus to obtain an average vehicle speed; The weather condition data contained in the urban traffic system data is classified according to the degree of influence on vehicle speed. Assume that the weather condition data of a certain day is w, w = {0, 1, 2, 3, 4, 5, 6}, where 0 represents sunny, cloudy and overcast, 1 represents light rain, 2 represents heavy rain, 3 represents light haze, 4 represents heavy haze, 5 represents light snow, and 6 represents heavy snow, and the weather influence coefficient is obtained; Calculating a congestion coefficient based on traffic flow data of bus operation sections and the maximum traffic capacity of each section included in the urban transportation system data; Calculating the distance between the bus and the electronic bus stop and the number of traffic lights passed by the bus based on the driving route data and vehicle position data included in the driving data of the bus and the electronic bus stop position data and traffic signal data included in the urban transportation system data; The average speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, number of traffic lights passed, historical stop time and date of each station, number of passengers on the bus, number of passengers in the car, average number of passengers getting on and off at each station on weekdays, and average number of passengers getting on and off at each station on holidays are vectorized and used as the feature vector of the bus.

4. The method for managing information of an electronic bus stop sign according to claim 1, characterized in that: The date, vehicle location data, electronic bus stop location data, bus capacity, number of passengers in the bus, average number of passengers getting on and off at each station on weekdays, and average number of passengers getting on and off at each station on holidays in the bus feature vector are input into the carriage congestion calculation model included in the prediction model to calculate the carriage congestion level, specifically: The date is determined. If the date is a weekday, the number of passengers in the carriage is added to the average number of passengers getting on and off on weekdays at all stations between the vehicle location data and the electronic bus stop location data to obtain the expected number of passengers. As the degree of crowdedness in the carriage, the is the expected number of passengers, is the number of passengers on the bus; if the date is a holiday, the number of passengers in the car is added to the average number of passengers getting on and off on holidays at all stations between the vehicle location data and the electronic bus stop location data to obtain the expected number of passengers. As the degree of congestion in the carriage.

5. The method for managing information of an electronic bus stop sign according to claim 1, characterized in that: The sending and displaying of the estimated waiting time and the carriage congestion level to a corresponding electronic station sign includes: Dividing the estimated waiting time by the historical average waiting time in the database to obtain a division result, if the division result is greater than or equal to a preset first multiple, determining that the road is congested, and sending the estimated waiting time to the corresponding electronic bus stop; if the division result is less than the preset first multiple and greater than a preset second multiple, determining that the road is relatively unobstructed as a result, and sending the estimated waiting time to the corresponding electronic bus stop; if the division result is less than the preset second multiple, determining that the road is unobstructed as a result, and sending the estimated waiting time to the corresponding electronic bus stop; Sending the carriage congestion level to the corresponding electronic bus stop; After receiving the estimated waiting time and the degree of congestion in the carriage, the electronic station board displays the information in a scrolling manner on a display screen configured for the electronic station board.

6. An information management system for bus electronic stop signs, characterized in that: include: Data acquisition module, used to obtain bus driving data, historical traffic data and urban transportation system data; A preprocessing module, configured to preprocess the bus travel data and the urban traffic system data to obtain a feature vector of the bus; A prediction module, configured to input the characteristic vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the carriage; A display module is used to send the estimated waiting time and the degree of congestion in the carriage to a corresponding electronic station sign and display them; The preset prediction model includes a random forest model for predicting waiting time and a carriage congestion calculation model, wherein the training process of the random forest model includes: Generate a waiting time training set based on the average vehicle speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop, number of traffic lights passed, historical stop time and historical waiting time of each station in the historical database; Using the bootstrap sampling method on the waiting time training set to generate a sub-training set, using the sub-training set to train the initial random forest model, and constructing a random forest model including k CART decision trees; The random forest model composed of a set of k CART decision trees is expressed as: ； Where T is the input data of the random forest model, middle , represents the CART decision tree; The method of inputting the characteristic vector of the bus into a preset prediction model to calculate the expected waiting time and the degree of congestion in the bus carriage includes: The average speed, weather impact coefficient, congestion coefficient, distance between the bus and the electronic bus stop sign, and number of traffic lights passed in the feature vector of the bus are input into the random forest model included in the prediction model for prediction. The k CART decision trees configured in the random forest model vote on the prediction results to obtain the estimated waiting time; The date, the rated passenger capacity of the bus, the number of passengers in the bus, the average number of passengers getting on and off at each station on weekdays, and the average number of passengers getting on and off at each station on holidays in the feature vector of the bus are input into the carriage congestion calculation model included in the prediction model for calculation to obtain the carriage congestion level.

7. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for managing the information of the electronic bus stop sign according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for managing the information of the electronic bus stop according to any one of claims 1 to 5.

Images