TWI745086B - System and method for estimating carriage crowdedness of train - Google Patents

Abstract

A system and a method for estimating a carriage crowdedness of a train. The method includes: obtaining a total number of people and a total number of carriages, obtaining a plurality of environmental parameters, and obtaining a plurality of air-conditioning power values; calculating an average number of people per carriage according to the total number of people and the total number of carriages, and calculating an average actual crowdedness according to the average number of people per carriage, a recommend number of people per carriage, and an upper limit of people per carriage; calculating an average measured crowdedness according to the plurality of environmental parameters and the plurality of air-conditioning power values; calculating a calibration value according to the average actual crowdedness and the average measured crowdedness, and calculating the carriage crowdedness corresponding to the first carriage according to the first measured crowdedness, the calibration value, and the weight value.

Description

System and method for estimating congestion degree of train compartment

The present invention relates to a system and method for estimating the degree of congestion in a train compartment, in particular to a system and method for calculating the degree of congestion in each compartment by using the carbon dioxide concentration, ambient temperature, air conditioning power value and the total number of people in the train .

In terms of the number of passengers or the degree of congestion in the carriage, the previous method involves spreading infrared transmitters and receivers in the carriage vertically and horizontally to sense and count the number of people passing by. The second is to install cameras and use video image crowd detection and identification methods to determine the degree of congestion. In addition, passengers carry identification elements to achieve the purpose of counting the number of people by means of sensing. However, these methods do not take into account that the environmental conditions inside the compartment may also affect the passenger's perception of the degree of congestion in the compartment.

The present invention can calculate the congestion degree of each car of the train. The acquisition of the congestion degree of the carriages facilitates the management and scheduling of future trains and carriages by the management center, and the degree of congestion of carriages can also be used as reference information for the people to choose trains and carriages when planning a traffic journey.

A system for estimating the degree of congestion of train cars according to the present invention, wherein the train includes a plurality of cars, wherein the system includes a processor, a storage medium, a plurality of environmental sensors, and a transceiver. The storage medium stores multiple modules. The processor is coupled to storage media, transceivers, and multiple environmental sensors, and accesses and executes multiple modules, including data collection modules, average actual congestion calculation modules, and average measurement congestion Degree calculation module, calibration module and output module. The data collection module obtains the total number of people and the total number of cars corresponding to the train through the transceiver, obtains the environmental parameters corresponding to the multiple cars through the multiple environmental sensors, and obtains the environmental parameters corresponding to the multiple cars through the transceiver. Of multiple air-conditioning power values. The average actual congestion degree calculation module calculates the average number of passengers in a compartment based on the total number of people and the total number of cars, and calculates the average actual congestion degree according to the average number of people in the car, the recommended number of people in the car, and the upper limit of the number of people in the car. The average measured congestion degree calculation module calculates multiple measured congestion degrees corresponding to multiple cars according to multiple environmental parameters and multiple air-conditioning power values, and calculates the average measured congestion degree according to the multiple measured congestion degrees, where The plurality of cars includes a first car, and the plurality of measured congestion degrees includes the first measured congestion degree corresponding to the first car. The correction module calculates the correction value according to the average actual congestion degree and the average measured congestion degree, and calculates the car congestion degree corresponding to the first car according to the first measured congestion degree, the correction value and the weight value, wherein the weight value is between 0 and 1. The output module outputs the congestion degree of the carriage through the transceiver.

In an embodiment of the present invention, the aforementioned average measurement congestion degree calculation module calculates a plurality of measurement congestion degrees according to a machine learning model.

In an embodiment of the present invention, the aforementioned correction value is the ratio of the average actual crowdedness degree to the average measured crowdedness degree.

In an embodiment of the present invention, the above-mentioned plurality of cars includes a second car, and the plurality of measured congestion degrees includes a second measured congestion degree corresponding to the second car, wherein the correction module is based on the second measured congestion The degree, the correction value, and the weight value are calculated corresponding to the second-car congestion degree of the second car.

In an embodiment of the present invention, the aforementioned system further includes an output device. The output device is coupled to the processor, wherein the output device is arranged in the first compartment, and the output module generates a message according to the degree of congestion in the compartment and the degree of congestion in the second compartment, and outputs the message through the output device, wherein the message instructs people to move into or out of the first compartment .

In an embodiment of the present invention, each of the aforementioned multiple environmental parameters includes carbon dioxide concentration and environmental temperature.

A method for estimating the degree of congestion of a train compartment of the present invention, wherein the train includes a plurality of compartments, wherein the method includes: obtaining the total number of people and the total number of compartments corresponding to the train, and obtaining a plurality of environmental parameters corresponding to the multiple compartments respectively , And obtain multiple air-conditioning power values corresponding to multiple cars; calculate the average number of people in the car according to the total number of people and the total number of cars, and calculate the average actual congestion degree according to the average number of people in the car, the recommended number of people in the car, and the upper limit of the number of people in the car; The calculation of environmental parameters and multiple air-conditioning power values respectively correspond to multiple measured congestion degrees of multiple cars, and the average measured congestion degree is calculated according to the multiple measured congestion degrees, where the multiple cars include the first compartment, and the multiple cars include the first car. The measured congestion degree includes the first measured congestion degree corresponding to the first car; the correction value is calculated according to the average actual congestion degree and the average measured congestion degree, and the calculation corresponding to the first measured congestion degree, the correction value, and the weight value The degree of congestion of the first car, where the weight value is between 0 and 1, and the degree of congestion of the car is output.

The present invention is a system and method for estimating the congestion degree of each car in a train. The present invention can use the carbon dioxide concentration, temperature, air-conditioning power value and the total number of people actually boarding the train to calculate the congestion degree of each car. The acquisition of information on the degree of congestion of carriages helps the management center to manage and dispatch trains and carriages, and it is also convenient for people to use this information to plan their journeys.

The system of the present invention can be composed of existing environmental sensors, air conditioning systems and computing devices on the vehicle. In terms of sensing equipment, the source of environmental parameters can be from the original carbon dioxide concentration sensor and temperature sensor of the car, and the source of the air conditioning power value can be from the original air conditioning system of the car. The present invention does not need to additionally arrange and install equipment such as infrared, ultrasonic radar or camera in the vehicle compartment. Therefore, the present invention has great advantages in consideration of cost and construction complexity. For other non-sensing data, it is necessary to use relevant information such as the total number of people on the train, and these data can be obtained from the existing ticketing system.

The present invention uses the carbon dioxide concentration, temperature, air-conditioning power value and the total number of people actually boarded in each section of the train to calculate the degree of congestion in each compartment. The more people in the car, the higher the carbon dioxide concentration and temperature. When the carbon dioxide concentration or temperature in the cabin is higher, the output intensity of the air conditioning system is also greater. After a period of time, the carbon dioxide concentration, temperature, and air conditioning power value will stabilize and maintain a balance. When the number of people in the cabin decreases, the carbon dioxide concentration and temperature will decrease, and the output intensity of the air conditioning system will also decrease. Therefore, the above characteristics can be used to estimate the number of people in the compartment.

Fig. 1 illustrates a schematic diagram of a system 100 for estimating the degree of congestion of a train car according to an embodiment of the present invention. The system 100 can be used to estimate the degree of congestion in a train including multiple cars. The system 100 may include a processor 110, a storage medium 120, a transceiver 130, and multiple environment sensors 140, wherein the plurality of environment sensors may include an environment sensor 141 and an environment sensor 14N. In one embodiment, the system 100 further includes an output device 150.

The processor 110 is, for example, a central processing unit (CPU), or other programmable general-purpose or special-purpose micro control unit (MCU), microprocessor, or digital signal processing DSP (digital signal processor, DSP), programmable controller, application specific integrated circuit (ASIC), graphics processing unit (GPU), image signal processor (ISP) ), image processing unit (IPU), arithmetic logic unit (ALU), complex programmable logic device (CPLD), field programmable gate array (field programmable gate array) , FPGA) or other similar components or a combination of the above components. The processor 110 may be coupled to the storage medium 120, the transceiver 130, a plurality of environmental sensors (for example, the environmental sensor 141 or the environmental sensor 14N), and the output device 150, and access and execute storage in the storage medium Multiple modules and various applications in 120.

The storage medium 120 is, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), or flash memory. , Hard disk drive (HDD), solid state drive (SSD) or similar components or a combination of the above components, which are used to store multiple modules or various application programs that can be executed by the processor 110. In this embodiment, the storage medium 120 can store multiple modules including a data collection module 121, an average actual congestion degree calculation module 122, an average measured congestion degree calculation module 123, a correction module 124, and an output module 125. Group, its function will be explained later.

The transceiver 130 transmits and receives signals in a wireless or wired manner. The transceiver 130 may also perform operations such as low noise amplification, impedance matching, frequency mixing, up or down frequency conversion, filtering, amplification, and the like.

A plurality of environment sensors 140 may be respectively provided in a plurality of cars of the train. For example, the environment sensor 140 may be installed in the first car of the train, and the environment sensor 14N may be installed in the second car of the train. The functions of each of the plurality of environmental sensors 140 are similar. Taking the environment sensor 141 as an example, the environment sensor 141 may include a carbon dioxide detector and a temperature detector.

The output device 150 can output messages to the people in the train. The output device 150 may include a display or a speaker, but the invention is not limited thereto.

The data collection module 121 can obtain information such as the total number of trains and the total number of cars through the transceiver 130. For example, the data collection module 121 can access the ticketing system through the transceiver 130 to obtain information such as the total number of people and the total number of cars from the ticketing system. The data collection module 121 can obtain a plurality of environmental parameters corresponding to a plurality of cars through a plurality of environmental sensors 140. Environmental parameters may include information such as carbon dioxide concentration or ambient temperature. For example, the data collection module 121 can obtain the carbon dioxide concentration in the first compartment through the carbon dioxide detector in the environment sensor 141, and obtain the ambient temperature in the first compartment through the temperature detector in the environment sensor 141. . The data collection module 121 can obtain multiple air-conditioning power values corresponding to multiple cars through the transceiver 130. For example, the data collection module 121 can access the air-conditioning system of the train through the transceiver 130, so as to obtain multiple air-conditioning power values corresponding to multiple cars from the air-conditioning system.

The data collection module 121 can obtain the suggested number of passengers in the train and the upper limit of the number of passengers through the transceiver 130. The recommended number of people in a carriage is the upper limit that can ensure that all people in a single carriage are in a comfortable state. The maximum number of passengers in a carriage is the number of people in a single carriage when it is full.

The average actual congestion degree calculation module 122 can calculate the average number of passengers in a carriage according to the total number of people and the total number of cars, as shown in equation (1). The average actual congestion degree calculation module 122 can calculate the average actual congestion degree according to the average number of passengers in the car, the recommended number of people in the car, and the upper limit of the number of people in the car, as shown in equation (2). Average number of carriages = total number of passengers / total number of carriages …(1) Average actual crowdedness = (Average number of passengers in a compartment-Recommended number of people in a compartment) / (Maximum number of people in a compartment-Recommended number of people in a compartment) …(2)

The average measured congestion degree calculation module 123 can calculate a plurality of measured congestion degrees corresponding to a plurality of compartments according to a plurality of environmental parameters and a plurality of air-conditioning power values. Taking the first compartment as an example, the average measured congestion degree calculation module 123 can calculate the first measured congestion degree corresponding to the first compartment based on the carbon dioxide concentration C1, the ambient temperature T1 and the air-conditioning power value P1 corresponding to the first compartment , As shown in equation (3), where NN is, for example, a function related to a machine learning model, where the machine learning model may include a deep learning model or a neural network model, but the present invention does not Limited to this. The above-mentioned machine learning model is, for example, obtained by training based on data in a database related to environmental parameters and air-conditioning power values. The first measurement of crowdedness = NN (carbon dioxide concentration C1, ambient temperature T1, air conditioning power value P1) …(3)

Taking the second compartment as an example, the average measured congestion degree calculation module 123 can calculate the second measured congestion degree corresponding to the second compartment based on the carbon dioxide concentration C2, the ambient temperature T2 and the air-conditioning power value P2 corresponding to the second compartment , As shown in equation (4). The second measurement of congestion degree = NN (carbon dioxide concentration C2, ambient temperature T2, air conditioning power value P2) …(4)

After the average measured congestion degree calculation module 123 calculates the multiple measured congestion degrees corresponding to the multiple cars (the multiple measured congestion degrees include the first measured congestion degree), the average measured congestion degree is calculated The module 123 can calculate the average measured congestion degree based on the multiple measured congestion degrees and the total number of cars, as shown in equation (5). Average measured congestion degree = the sum of multiple measured congestion degrees / total number of cars …(5)

After obtaining the average actual congestion degree and the average measured congestion degree, the correction module 123 can calculate the correction value according to the average actual congestion degree and the average measured congestion degree, as shown in equation (6). Correction value = average actual crowdedness / average measured crowdedness …(6)

Then, the correction module 124 can calculate the congestion degree of the compartment according to the measured congestion degree, the correction value, and the weight value, where the weight value is between 0 and 1. Taking the first compartment as an example, the correction module 124 can calculate the first compartment congestion degree corresponding to the first compartment according to the first measured congestion degree, the correction value and the weight value α corresponding to the first compartment, as shown in equation (7 ) As shown. Taking the second car as an example, the correction module 124 can calculate the second car congestion degree corresponding to the second car according to the second measured congestion degree, the correction value and the weight value α corresponding to the second car, as shown in equation (8 ) As shown. The first car congestion degree = α*(the first measurement congestion degree*correction value) + (1-α)*the first measurement congestion degree …(7) Congestion degree of the second car = α*(congestion degree of the second measurement*correction value) + (1-α)*congestion degree of the second measurement …(8)

The output module 125 can output the first degree of congestion of the carriage through the transceiver 130. For example, the output module 125 can output the first compartment congestion degree to the ticketing system through the transceiver 130. When passengers access the ticketing system to purchase seats in the first car of the train through the ticketing application of a terminal device (for example, a smart phone), the ticketing system can display the congestion degree of the first car corresponding to the first car to the passengers Watching is used as a reference for assisting passengers to determine whether to take the first car.

In an embodiment, the output module 125 may instruct the people in the train to move to a car with a smaller number of people according to the degree of congestion of the car to disperse the crowd. The output module 125 can generate messages based on the congestion degree of the first compartment corresponding to the first compartment and the congestion degree of the second compartment corresponding to the second compartment. Move out of the first carriage or the second carriage. For example, suppose that the first compartment congestion degree indicates that the first compartment is in a congested state, and the second compartment congestion degree indicates that the second compartment is in a comfortable state. In this way, the output module 125 can output a message through the output device 150 provided in the first compartment, so as to instruct the people in the first compartment to move to the second compartment.

FIG. 2 shows a flowchart of a method for estimating the degree of congestion of a train car according to an embodiment of the present invention, wherein the method may be implemented by the system 100 as shown in FIG. 1. In step S201, the total number of people and the total number of cars corresponding to the train are obtained, a plurality of environmental parameters respectively corresponding to a plurality of cars are obtained, and a plurality of air-conditioning power values respectively corresponding to the plurality of cars are obtained. In step S202, calculate the average number of passengers in a vehicle based on the total number of passengers and the total number of vehicles, and calculate the average actual congestion degree based on the average number of passengers in the vehicle, the recommended number of passengers in the vehicle, and the upper limit of the number of passengers in the vehicle. In step S203, multiple measured congestion degrees corresponding to multiple cars are calculated according to multiple environmental parameters and multiple air-conditioning power values, and the average measured congestion degree is calculated based on the multiple measured congestion degrees, where multiple cars A first compartment is included, wherein the plurality of measured congestion degrees includes a first measured congestion degree corresponding to the first compartment. In step S204, a correction value is calculated according to the average actual congestion degree and the average measured congestion degree, and the car congestion degree corresponding to the first car is calculated according to the first measured congestion degree, the correction value and the weight value, wherein the weight value is between 0 and 1. In step S205, the degree of vehicle congestion is output. Features and effects

When compared with other conventional technologies, the system and method for calculating the congestion degree of each train compartment provided by the present invention has advantages including no need to spread infrared transmitters and receivers vertically and horizontally, and no problems of complicated wiring construction; no need to install cameras and The high-efficiency computing and identification unit does not have the problem of high price and cost; passengers do not need to carry identification components for the sensor to sense to achieve the purpose of counting the number of people. The acquisition of information on the congestion degree of each carriage of the train helps the management center to manage and dispatch the trains and carriages, and it is also convenient for the public to use the relevant historical information to plan their journeys.

100: system 110: processor 120: storage media 121: Data Collection Module 122: Average actual congestion calculation module 123: Calculation module for average measurement of congestion 124: Calibration module 125: output module 130: Transceiver 140: Multiple environmental sensors 141, 14N: Environmental sensor 150: output device S201, S202, S203, S204, S205: steps

Please refer to the detailed description of the present invention and its accompanying drawings to further understand the technical content of the present invention and its objectives and effects; the relevant drawings are: Fig. 1 illustrates a schematic diagram of a system for estimating the congestion degree of a train car according to an embodiment of the present invention. Fig. 2 illustrates a flow chart of a method for estimating the degree of congestion of a train car according to an embodiment of the present invention.

S201, S202, S203, S204, S205: steps

Claims (7)

A system for estimating the degree of congestion of train cars, wherein the train includes a plurality of cars, wherein the system includes: transceiver; Multiple environmental sensors; Storage media, storing multiple modules; and The processor is coupled to the storage medium, the transceiver, and the plurality of environmental sensors, and accesses and executes the plurality of modules, wherein the plurality of modules include: The data collection module obtains the total number of people and the total number of cars corresponding to the train through the transceiver, obtains a plurality of environmental parameters corresponding to the plurality of cars through the plurality of environmental sensors, and passes The transceiver obtains a plurality of air-conditioning power values respectively corresponding to the plurality of compartments; The average actual congestion degree calculation module calculates the average number of passengers in the carriage according to the total number of people and the total number of cars, and calculates the average actual congestion degree according to the average number of cars, the recommended number of people in the car, and the upper limit of the number of cars; The average measurement congestion degree calculation module calculates a plurality of measurement congestion degrees corresponding to the plurality of cars respectively according to the plurality of environmental parameters and the plurality of air-conditioning power values, and according to the plurality of measurement congestion Calculating an average measured congestion degree, wherein the plurality of cars includes a first car, and wherein the plurality of measured congestion degrees includes a first measured congestion degree corresponding to the first car; The correction module calculates a correction value according to the average actual congestion degree and the average measured congestion degree, and calculates a correction value corresponding to the first compartment according to the first measured congestion degree, the correction value, and the weight value. The degree of congestion of the carriage, wherein the weight value is between 0 and 1; and The output module outputs the congestion degree of the carriage through the transceiver. The system according to claim 1, wherein the average measurement congestion degree calculation module calculates the plurality of measurement congestion degrees according to a machine learning model. The system according to claim 1, wherein the correction value is a ratio of the average actual congestion degree and the average measured congestion degree. The system according to claim 1, wherein the plurality of cars includes a second car, and the plurality of measured congestion degrees includes a second measured congestion degree corresponding to the second car, wherein The correction module calculates a second compartment congestion degree corresponding to the second compartment according to the second measured congestion degree, the correction value, and the weight value. The system described in claim 4 further includes: An output device coupled to the processor, wherein the output device is arranged in the first compartment, wherein The output module generates a message according to the degree of congestion of the carriage and the degree of congestion of the second carriage, and outputs the message through the output device, wherein the message instructs a person to move into or out of the first carriage. The system according to claim 1, wherein each of the plurality of environmental parameters includes carbon dioxide concentration and environmental temperature. A method for estimating the degree of congestion of train cars, wherein the train includes a plurality of cars, wherein the method includes: Obtaining a total number of people and a total number of cars corresponding to the train, obtaining a plurality of environmental parameters corresponding to the plurality of cars, and obtaining a plurality of air conditioning power values corresponding to the plurality of cars; Calculate the average number of passengers in the carriages according to the total number of people and the total number of cars, and calculate the average actual congestion degree according to the average number of people in the cars, the recommended number of people in the cars, and the upper limit of the number of people in the cars; Calculate multiple measured congestion degrees corresponding to the multiple cars according to the multiple environmental parameters and the multiple air-conditioning power values, and calculate an average measured congestion degree based on the multiple measured congestion degrees, wherein The plurality of cars includes a first car, wherein the plurality of measured congestion degrees includes a first measured congestion degree corresponding to the first car; A correction value is calculated according to the average actual congestion degree and the average measured congestion degree, and the compartment congestion corresponding to the first compartment is calculated according to the first measured congestion degree, the correction value, and the weight value Degree, wherein the weight value is between 0 and 1; and Output the degree of congestion in the compartment.

Images