Rail transit transportation capacity risk prediction method and device, electronic equipment and storage medium

Abstract

The invention relates to a rail transit transport capacity risk prediction method and device, electronic equipment and a storage medium, a rail transit road network comprising at least one line is determined, and each line comprises at least two stations. And periodically determining a risk attribute set comprising at least one risk attribute value of each station and the operation interval at a moment corresponding to the period, and predicting a station transport capacity risk of each station and an interval transport capacity risk of each operation interval according to the corresponding risk attribute value based on a Bayesian network obtained by training. And predicting a corresponding line transport capacity risk according to the station transport capacity risk of the station included in each line and the interval transport capacity risk of the operation interval, and predicting a road network global transport capacity risk corresponding to the rail transit road network according to the line transport capacity risk corresponding to each line. According to the invention, in the process of predicting the transport capacity risk of the whole road network, the position relationship between different stations and intervals and lines and the attribute change in time sequence are considered, and the accuracy of the prediction result is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, electronic device and storage medium for predicting rail transit capacity risk. Background Art

[0002] Rail transit plays an increasingly important role in modern urban transportation due to its advantages such as large capacity, good punctuality, high safety, environmental friendliness and low cost, and has become the backbone and important support of modern urban transportation. Although rail transit is safer than conventional road transportation, due to the large scale of the rail transit network, heavy transportation tasks and close coupling between lines, once a failure or safety accident occurs, it will have a great impact on urban transportation. Therefore, how to effectively evaluate and predict the overall risk of the rail transit network and then reduce this overall risk and its impact on the transportation capacity of the rail transit network has always been one of the key issues in the research of rail transit. Summary of the invention

[0003] In view of this, the present disclosure proposes a rail transit capacity risk prediction method, device, electronic device and storage medium, aiming to accurately predict the risks of the rail transit network.

[0004] According to a first aspect of the present disclosure, a method for predicting rail transit capacity risk is provided, the method comprising:

[0005] Determine a rail transit network including at least one line, each of the lines including at least two stations, and an operating interval between every two stations;

[0006] Periodically determining a risk attribute set, wherein the risk attribute set determined in each period includes at least one risk attribute value of each of the stations and the operating interval at a corresponding time of the period;

[0007] After each time a risk attribute set is obtained, predicting the network capacity risk of the rail transit network at a corresponding time in the next cycle based on the risk attribute set according to the trained Bayesian network;

[0008] Wherein, the Bayesian network predicts the station capacity risk of each of the stations and the interval capacity risk of each of the operating intervals according to the corresponding risk attribute values;

[0009] According to the station capacity risk of each line including the station and the interval capacity risk including the operation interval, predicting the line capacity risk corresponding to each line;

[0010] According to the line capacity risk corresponding to each of the lines, the network capacity risk corresponding to the rail transit network is predicted.

[0011] In a possible implementation, the risk attribute value of the station includes the station passenger flow saturation and the station stranded passenger evacuation time. The station passenger flow saturation is used to characterize the relationship between the actual passenger flow and the passenger flow capacity of the station at the corresponding time, and the station stranded passenger evacuation time is used to characterize the time required for passengers in the station to completely leave the station; the risk attribute value of the operating interval includes the interval passenger flow saturation used to characterize the relationship between the actual passenger flow and the passenger flow capacity of the interval at the corresponding time.

[0012] In a possible implementation, the periodically determining a risk attribute set includes:

[0013] Periodically obtaining the station passenger flow, number of stranded passengers, station passenger flow capacity and station passenger evacuation speed of each station in the rail transit network, as well as the interval passenger flow and interval passenger flow capacity of each operating interval according to a preset time period;

[0014] Determine the station passenger flow saturation of each station at a corresponding time according to the ratio of the station passenger flow in each cycle to the station passenger flow capacity;

[0015] Determining the evacuation time of stranded passengers at each station at a corresponding time according to the ratio of the number of stranded passengers at the station in each cycle to the evacuation speed of passengers at the station;

[0016] Determining the interval passenger flow saturation of each interval at a corresponding time according to the ratio of the interval passenger flow in each cycle to the interval passenger flow capacity;

[0017] The risk attribute set corresponding to the moment is determined according to the station passenger flow saturation and the evacuation time of stranded passengers at each of the stations at the corresponding moment of each cycle, and the interval passenger flow saturation of each of the intervals.

[0018] In a possible implementation, after obtaining the risk attribute set each time, predicting the network capacity risk of the rail transit network at a corresponding time in the next cycle based on the risk attribute set according to the trained Bayesian network includes:

[0019] After each risk attribute set is obtained, the risk attribute set corresponding to the current moment is input into the trained Bayesian network, and the corresponding road network capacity risk is output;

[0020] Among them, the risk attribute value corresponding to each of the stations is the risk attribute value at the corresponding moment of the current cycle.

[0021] In a possible implementation, after obtaining the risk attribute set each time, predicting the network capacity risk of the rail transit network at a corresponding time in the next cycle based on the risk attribute set according to the trained Bayesian network includes:

[0022] After each risk attribute set is obtained, the risk attribute set corresponding to the current moment and the risk attribute set obtained in the previous cycle are input into the trained Bayesian network together, and the corresponding road network capacity risk is output;

[0023] The risk attribute value corresponding to each of the stations includes the risk attribute value at the current moment and the risk attribute value corresponding to the previous period.

[0024] In a possible implementation, the training process of the Bayesian network includes:

[0025] Determine a training data set including a plurality of sample attribute sets having corresponding station risk labels, section risk labels, line risk labels, and road network risk labels;

[0026] The network parameters in the Bayesian network are determined according to the training data set to obtain a trained Bayesian network.

[0027] In a possible implementation, the determining includes a plurality of training data sets having sample attribute sets corresponding to station risk labels, section risk labels, line risk labels, and road network risk labels, including:

[0028] Determine a sample traffic network including at least one sample route, each of the sample routes includes at least two sample stations, and a sample interval is formed between every two sample stations;

[0029] Determine a plurality of sample attribute information corresponding to each of the sample stations and the sample intervals in the sample transportation network at at least one time;

[0030] Determine a sample attribute set according to the sample attribute information of each of the sample stations and the sample interval;

[0031] Calculate, according to the sample attribute set, a station risk label corresponding to each of the sample stations, an interval risk label corresponding to each of the sample intervals, a line risk label of each of the sample lines, and a network risk label of the sample transportation network;

[0032] A training data set is determined based on each of the sample attribute sets, and the corresponding station risk labels, line risk labels, and road network risk labels.

[0033] In a possible implementation, the sample attribute information includes the passenger flow of the sample station, the number of stranded passengers at the sample station, the passenger flow capacity of the sample station, the passenger evacuation speed of the sample station, the passenger flow of the sample interval, and the passenger flow capacity of the sample interval.

[0034] In a possible implementation manner, determining a sample attribute set according to the sample attribute information of each of the sample stations and the sample intervals includes:

[0035] Determine the sample station passenger flow saturation of each sample station at a corresponding time according to the corresponding sample station passenger flow and the sample station passenger flow capacity ratio;

[0036] Determine the evacuation time of stranded passengers at each sample station at a corresponding time according to the ratio of the number of stranded passengers at the corresponding sample station to the evacuation speed of passengers at the sample station;

[0037] Determine the sample interval passenger flow saturation of each sample interval according to the corresponding sample interval passenger flow and the sample interval passenger flow capacity ratio;

[0038] The corresponding sample attribute set is determined according to the sample station passenger flow saturation and the sample station stranded passenger evacuation time of each of the sample stations at the corresponding time, and the sample interval passenger flow saturation of each of the sample intervals.

[0039] In a possible implementation, the step of calculating, according to the sample attribute set, a station risk label corresponding to each of the sample stations, an interval risk label corresponding to each of the sample intervals, a line risk label of each of the sample lines, and a road network risk label of the sample transportation road network includes:

[0040] Determine the sample interval passenger flow saturation of each sample interval as the corresponding interval risk label;

[0041] The station risk label of each sample station is obtained by calculating the corresponding sample station passenger flow saturation and the weighted sum of the sample station stranded passenger evacuation time;

[0042] Obtaining a corresponding line risk label by calculating a weighted sum of the station risk label of each of the sample stations in each of the sample lines and the interval risk label of each of the sample intervals included therein;

[0043] The corresponding station risk label is obtained by calculating the weighted sum of the station risk label of each of the sample stations in the sample transportation network and the interval risk label of each of the sample intervals included therein.

[0044] In a possible implementation, the sample attribute information is real data obtained through collection, or simulated data obtained through simulation modeling.

[0045] In a possible implementation, determining the network parameters in the Bayesian network according to the training data set to obtain a trained Bayesian network includes:

[0046] Inputting the data in the training data set into a preset log-likelihood function, wherein the log-likelihood function includes at least two candidate parameters;

[0047] Calculating the gradient of each candidate parameter in the log-likelihood function to obtain a corresponding gradient equation;

[0048] Solving the equation group according to each of the gradient equations obtains a solution for each of the candidate parameters as a network parameter in the Bayesian network.

[0049] According to a second aspect of the present disclosure, a rail transit capacity risk prediction device is provided, the device comprising:

[0050] A network determination module, used to determine a rail transit network including at least one line, each of which includes at least two stations, and an operating interval is between every two stations;

[0051] An attribute set determination module, used for periodically determining a risk attribute set, wherein the risk attribute set determined in each period includes at least one risk attribute value of each of the stations and the operating interval at a corresponding time of the period;

[0052] A risk prediction module, configured to predict the network capacity risk of the rail transit network at a corresponding time in the next cycle based on the risk attribute set according to the trained Bayesian network after each acquisition of the risk attribute set;

[0053] Wherein, the Bayesian network predicts the station capacity risk of each of the stations and the interval capacity risk of each of the operating intervals according to the corresponding risk attribute values;

[0054] According to the station capacity risk of each line including the station and the interval capacity risk including the operation interval, predicting the line capacity risk corresponding to each line;

[0055] According to the line capacity risk corresponding to each of the lines, the network capacity risk corresponding to the rail transit network is predicted.

[0056] In a possible implementation, the risk attribute value of the station includes the station passenger flow saturation and the station stranded passenger evacuation time. The station passenger flow saturation is used to characterize the relationship between the actual passenger flow and the passenger flow capacity of the station at the corresponding time, and the station stranded passenger evacuation time is used to characterize the time required for passengers in the station to completely leave the station; the risk attribute value of the operating interval includes the interval passenger flow saturation used to characterize the relationship between the actual passenger flow and the passenger flow capacity of the interval at the corresponding time.

[0057] In a possible implementation, the attribute set determination module is further configured to:

[0058] Periodically obtaining the station passenger flow, number of stranded passengers, station passenger flow capacity and station passenger evacuation speed of each station in the rail transit network, as well as the interval passenger flow and interval passenger flow capacity of each operating interval according to a preset time period;

[0059] Determine the station passenger flow saturation of each station at a corresponding time according to the ratio of the station passenger flow in each cycle to the station passenger flow capacity;

[0060] Determining the evacuation time of stranded passengers at each station at a corresponding time according to the ratio of the number of stranded passengers at the station in each cycle to the evacuation speed of passengers at the station;

[0061] Determining the interval passenger flow saturation of each interval at a corresponding time according to the ratio of the interval passenger flow in each cycle to the interval passenger flow capacity;

[0062] The risk attribute set corresponding to the moment is determined according to the station passenger flow saturation and the evacuation time of stranded passengers at each of the stations at the corresponding moment of each cycle, and the interval passenger flow saturation of each of the intervals.

[0063] In a possible implementation, the risk prediction module is further used to:

[0064] After each risk attribute set is obtained, the risk attribute set corresponding to the current moment is input into the trained Bayesian network, and the corresponding road network capacity risk is output;

[0065] Among them, the risk attribute value corresponding to each of the stations is the risk attribute value at the corresponding moment of the current cycle.

[0066] In a possible implementation, the risk prediction module is further used to:

[0067] After each risk attribute set is obtained, the risk attribute set corresponding to the current moment and the risk attribute set obtained in the previous cycle are input into the trained Bayesian network together, and the corresponding road network capacity risk is output;

[0068] The risk attribute value corresponding to each of the stations includes the risk attribute value at the current moment and the risk attribute value corresponding to the previous period.

[0069] In a possible implementation, the training process of the Bayesian network includes:

[0070] Determine a training data set including a plurality of sample attribute sets having corresponding station risk labels, section risk labels, line risk labels, and road network risk labels;

[0071] The network parameters in the Bayesian network are determined according to the training data set to obtain a trained Bayesian network.

[0072] In a possible implementation, the determining includes a plurality of training data sets having sample attribute sets corresponding to station risk labels, section risk labels, line risk labels, and road network risk labels, including:

[0073] Determine a sample traffic network including at least one sample route, each of the sample routes includes at least two sample stations, and a sample interval is formed between every two sample stations;

[0074] Determine a plurality of sample attribute information corresponding to each of the sample stations and the sample intervals in the sample transportation network at at least one time;

[0075] Determine a sample attribute set according to the sample attribute information of each of the sample stations and the sample interval;

[0076] Calculate, according to the sample attribute set, a station risk label corresponding to each of the sample stations, an interval risk label corresponding to each of the sample intervals, a line risk label of each of the sample lines, and a network risk label of the sample transportation network;

[0077] A training data set is determined based on each of the sample attribute sets, and the corresponding station risk labels, line risk labels, and road network risk labels.

[0078] In a possible implementation, the sample attribute information includes the passenger flow of the sample station, the number of stranded passengers at the sample station, the passenger flow capacity of the sample station, the passenger evacuation speed of the sample station, the passenger flow of the sample interval, and the passenger flow capacity of the sample interval.

[0079] In a possible implementation manner, determining a sample attribute set according to the sample attribute information of each of the sample stations and the sample intervals includes:

[0080] Determine the sample station passenger flow saturation of each sample station at a corresponding time according to the corresponding sample station passenger flow and the sample station passenger flow capacity ratio;

[0081] Determine the evacuation time of stranded passengers at each sample station at a corresponding time according to the ratio of the number of stranded passengers at the corresponding sample station to the evacuation speed of passengers at the sample station;

[0082] Determine the sample interval passenger flow saturation of each sample interval according to the corresponding sample interval passenger flow and the sample interval passenger flow capacity ratio;

[0083] The corresponding sample attribute set is determined according to the sample station passenger flow saturation and the sample station stranded passenger evacuation time of each of the sample stations at the corresponding time, and the sample interval passenger flow saturation of each of the sample intervals.

[0084] In a possible implementation, the step of calculating, according to the sample attribute set, a station risk label corresponding to each of the sample stations, an interval risk label corresponding to each of the sample intervals, a line risk label of each of the sample lines, and a road network risk label of the sample transportation road network includes:

[0085] Determine the sample interval passenger flow saturation of each sample interval as the corresponding interval risk label;

[0086] The station risk label of each sample station is obtained by calculating the corresponding sample station passenger flow saturation and the weighted sum of the sample station stranded passenger evacuation time;

[0087] Obtaining a corresponding line risk label by calculating a weighted sum of the station risk label of each of the sample stations in each of the sample lines and the interval risk label of each of the sample intervals included therein;

[0088] The corresponding station risk label is obtained by calculating the weighted sum of the station risk label of each of the sample stations in the sample transportation network and the interval risk label of each of the sample intervals included therein.

[0089] In a possible implementation, the sample attribute information is real data obtained through collection, or simulated data obtained through simulation modeling.

[0090] In a possible implementation, determining the network parameters in the Bayesian network according to the training data set to obtain a trained Bayesian network includes:

[0091] Inputting the data in the training data set into a preset log-likelihood function, wherein the log-likelihood function includes at least two candidate parameters;

[0092] Calculating the gradient of each candidate parameter in the log-likelihood function to obtain a corresponding gradient equation;

[0093] Solving the equation group according to each of the gradient equations obtains a solution for each of the candidate parameters as a network parameter in the Bayesian network.

[0094] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0095] According to a fourth aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0096] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0097] In an embodiment of the present disclosure, a rail transit network including at least one line is determined, and each line includes at least two stations. A risk attribute set including at least one risk attribute value for each station and operating interval at a corresponding time of the period is periodically determined, and the station capacity risk of each station and the interval capacity risk of each operating interval are predicted according to the corresponding risk attribute values ​​based on the trained Bayesian network, and the corresponding line capacity risk is predicted based on the station capacity risk of the stations and the interval capacity risk of the operating intervals of each line, and then the corresponding network capacity risk of the rail transit network is predicted based on the line capacity risk corresponding to each line. In the process of predicting the capacity risk of the entire network, the present disclosure takes into account the positional relationship between different stations and lines, thereby improving the accuracy of the prediction results.

[0098] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0100] Figure 1 A flow chart showing a method for predicting rail transit capacity risk according to an embodiment of the present disclosure;

[0101] Figure 2 A schematic diagram of determining the transport capacity risk of a road network according to an embodiment of the present disclosure is shown;

[0102] Figure 3 A schematic diagram showing a rail transit capacity risk prediction device according to an embodiment of the present disclosure;

[0103] Figure 4 A schematic diagram showing an electronic device according to an embodiment of the present disclosure;

[0104] Figure 5 A schematic diagram showing another electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0105] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0106] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0107] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the subject matter of the present disclosure.

[0108] The rail transit capacity risk prediction method of the embodiment of the present disclosure can be executed by an electronic device such as a terminal device or a server. Among them, the terminal device can be any fixed or mobile terminal such as a user equipment (UE), a mobile device, a user terminal, a terminal, a cellular phone, a cordless phone, a personal digital assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The server can be a single server or a server cluster composed of multiple servers. Any electronic device can implement the rail transit capacity risk prediction method of the embodiment of the present disclosure by calling the computer-readable instructions stored in the memory by the processor.

[0109] Figure 1 A flow chart of a method for predicting rail transit capacity risk according to an embodiment of the present disclosure is shown. Figure 1 As shown, the rail transit capacity risk prediction method of the embodiment of the present disclosure may include the following steps S10-S30.

[0110] Step S10: Determine a rail transit network including at least one line.

[0111] In a possible implementation, the rail transit network for which the transport capacity risk needs to be predicted is determined by an electronic device. The rail transit network may be a network for rail vehicles such as a railway network or a subway network, which includes at least one line, each line also includes at least two stations, and there is a corresponding vehicle operation interval between every two adjacent stations. Exemplarily, in the case where the rail transit network is a subway network, it may include Metro Line 1 and Line 2. Further, Metro Line 1 may include Metro Station 1, Metro Station 2, Metro Station 3 and Metro Station 4 in sequence, wherein Metro Station 1 and Metro Station 2, Metro Station 2 and Metro Station 3, and Metro Station 3 and Metro Station 4 have corresponding operation intervals respectively. Metro Line 2 may include Metro Station 5, Metro Station 3 and Metro Station 6 in sequence, wherein Metro Station 5 and Metro Station 3, and Metro Station 3 and Metro Station 6 have corresponding operation intervals respectively.

[0112] Step S20: periodically determine a risk attribute set.

[0113] In a possible implementation, after determining the rail transit network for which the transportation risk needs to be predicted, the electronic device may periodically detect the risk attribute of each station in the rail transit network to determine the risk attribute set corresponding to the rail transit network at the corresponding time of the current cycle, for predicting the risk of the rail transit network at the corresponding time of the next cycle. The risk attribute set determined in each cycle may include at least one risk attribute value of each station at the corresponding time of the cycle.

[0114] Optionally, based on experience in the actual application process, at least one risk attribute that will affect the risk of the network transportation capacity can be predetermined, and the value of the risk attribute of each station is obtained as the risk attribute value in each cycle to obtain the risk attribute set corresponding to the rail transit network. Exemplarily, the embodiment of the present disclosure can predetermine that the risk attribute value includes the station passenger flow saturation and the station stranded passenger evacuation time. Among them, the station passenger flow saturation is used to characterize the relationship between the actual passenger flow and the passenger flow passing capacity of the station at the corresponding time, and the station stranded passenger evacuation time is used to characterize the time required for passengers in the station to completely leave the station. That is, the electronic device can periodically obtain the station passenger flow saturation and station stranded passenger evacuation time of each station in the rail transit network, so as to determine the risk attribute set of the rail transit network at the corresponding time of the cycle according to the station passenger flow saturation and station stranded passenger evacuation time of each station. Alternatively, the risk attribute value can also include other attribute values ​​such as the interval passenger flow saturation of the operating interval between two stations to characterize the relationship between the actual passenger flow and the passenger flow passing capacity of the corresponding time interval.

[0115] Further, the station passenger flow saturation and the station stranded passenger evacuation time can be determined by the station passenger flow, the number of stranded passengers at the station, the station passenger flow capacity and the station passenger evacuation speed. Among them, the station passenger flow saturation can be the ratio of the station passenger flow and the station passenger flow capacity at the corresponding time, and the station passenger evacuation speed can be the ratio of the number of stranded passengers at the station and the station passenger evacuation speed at the corresponding time. That is, the process of the electronic device periodically determining the risk attribute set can be to periodically obtain the station passenger flow, the number of stranded passengers at the station, the station passenger flow capacity and the station passenger evacuation speed of each station in the rail transit network according to a preset time period. Then, the station passenger flow saturation of each station at the corresponding time is determined according to the ratio of the station passenger flow and the station passenger flow capacity of each cycle. The stranded passenger evacuation time of each station at the corresponding time is determined according to the ratio of the number of stranded passengers at the station and the station passenger evacuation speed of each cycle. Then, according to the station passenger flow saturation and the station stranded passenger evacuation time of each station at the corresponding time of each cycle, the risk attribute set corresponding to the rail transit network at the time is determined.

[0116] Optionally, when the risk attribute set also includes the interval passenger flow saturation of the operating interval, the interval passenger flow saturation can be determined based on the interval passenger flow and interval passenger flow capacity of each operating interval. That is, while periodically obtaining the station passenger flow, the number of stranded passengers, the station passenger flow capacity and the station passenger evacuation speed of each station in the rail transit network according to a preset time period, the interval passenger flow and interval passenger flow capacity of each operating interval can also be obtained, and then the interval passenger flow saturation of each interval at the corresponding moment is determined based on the ratio of the interval passenger flow and the interval passenger flow capacity of each cycle. Finally, the risk attribute set corresponding to the moment is determined based on the station passenger flow saturation and the station stranded passenger evacuation time of each station at the corresponding moment of each cycle, as well as the interval passenger flow saturation of each interval.

[0117] Step S30: after each acquisition of a risk attribute set, predict the network capacity risk of the rail transit network at a corresponding time in the next cycle based on the risk attribute set according to the trained Bayesian network.

[0118] In a possible implementation, after periodically acquiring a risk attribute set according to a preset time period, the electronic device predicts the network capacity risk of the rail transit network at a corresponding time in the next period according to the risk attribute set corresponding to the rail transit network in the current period. The capacity risk can represent the overall safety risk of the rail transit network, for example, the possibility of a safety accident caused by passenger flow exceeding the carrying capacity.

[0119] Optionally, the process of predicting the network capacity risk of the next cycle based on the acquired risk attribute set in the embodiment of the present disclosure can be implemented through a trained Bayesian network. Among them, the Bayesian network can consider the position relationship and connectivity relationship of each station in the rail transit network in the process of predicting the network capacity risk to increase the accuracy of the prediction result. That is, the Bayesian network can predict the capacity risk layer by layer according to the topological relationship, first predict the station capacity risk of each station and the interval capacity risk of each operating interval according to the corresponding risk attribute value, and then predict the line capacity risk corresponding to each line according to the station capacity risk of the station included in each line and the interval capacity risk of the included operating interval, and finally predict the network capacity risk corresponding to the rail transit network according to the line capacity risk corresponding to each line.

[0120] Figure 2 FIG. 2 is a schematic diagram showing a method for determining the risk of road network transportation capacity according to an embodiment of the present disclosure. Figure 2 As shown, the Bayesian network of the embodiment of the present disclosure can predict the station capacity risk of the station according to the station passenger flow saturation of each station and the evacuation time of the stranded passengers at the station, and then predict the line capacity risk of the line according to the station capacity risk of multiple stations in the same line, and finally predict the global capacity risk of the rail transit network according to the capacity risk of each line. Optionally, in order to further improve the accuracy of the prediction result, the risk attribute set determined by the electronic device can also include the interval passenger flow saturation corresponding to the operating interval between adjacent stations, which is determined by calculating the ratio of the interval passenger flow and the interval passenger flow capacity. The Bayesian network can predict the station capacity risk of the station according to the station passenger flow saturation of each station and the evacuation time of the stranded passengers at the station, and predict the interval capacity risk according to the interval passenger flow saturation of each operating interval. Further, the line capacity risk of the line is predicted according to the station capacity risk of multiple stations in the same line, and the interval capacity risk of the operating interval between adjacent stations, and finally the global capacity risk of the rail transit network is predicted according to the capacity risk of each line.

[0121] Further, the Bayesian network of the embodiment of the present disclosure can only consider the influence of the position relationship and connectivity relationship of each station in the rail transit network on the network capacity risk during the prediction process, that is, after each risk attribute set is obtained, the risk attribute set corresponding to the current moment is input into the trained Bayesian network, and the corresponding network capacity risk is output. Among them, the risk attribute value corresponding to each station is the risk attribute value at the corresponding moment of the current cycle. Alternatively, the Bayesian network of the embodiment of the present disclosure can also consider the influence of the time sequence of the risk attribute set on the network capacity risk during the prediction process, that is, after each risk attribute set is obtained, the risk attribute set corresponding to the current moment and the risk attribute set obtained in the previous cycle are input into the trained Bayesian network together, and the corresponding network capacity risk is output. Among them, the risk attribute value corresponding to each station includes the risk attribute value at the current moment and the risk attribute value corresponding to the previous cycle. Alternatively, the embodiment of the present disclosure can also predetermine a time window, input the risk attribute set corresponding to the current moment and the risk attribute set obtained in multiple cycles within the time window between the current moment into the trained Bayesian network together, and output the corresponding network capacity risk.

[0122] In a possible implementation, the training process of the Bayesian network of the embodiment of the present disclosure can be executed by an electronic device, or deployed in an electronic device that currently predicts the risk of road network transportation capacity after being executed by other devices and used directly. The training process can be to first determine a training data set including a plurality of sample attribute sets with corresponding station risk labels, line risk labels, interval risk labels and road network risk labels, and then determine the network parameters in the Bayesian network according to the training data set to obtain a trained Bayesian network. Among them, the determination process of the training data set can be to first determine a sample transportation road network including at least one sample line, each sample line including at least two sample stations, and a sample interval between each two sample stations. Then determine a plurality of sample attribute information corresponding to each sample station and sample interval in the sample transportation road network at at least one time. Then determine a sample attribute set according to the sample attribute information of each sample station and sample interval. According to the sample attribute set, calculate the station risk label and interval risk label corresponding to each sample station, the line risk label of each sample line and the road network risk label of the sample transportation road network. Finally, determine the training data set according to each sample attribute set, and the corresponding station risk label, line risk label, interval risk label and road network risk label.

[0123] Optionally, the sample attribute information may include the passenger flow of the sample station, the number of stranded passengers at the sample station, the passenger flow capacity of the sample station, the passenger evacuation speed of the sample station, the passenger flow of the sample interval, and the passenger flow capacity of the sample interval. The sample attribute set may be determined by part of or all of the data, that is, the passenger flow saturation of the sample station at the corresponding time of each sample station is determined according to the corresponding ratio of the passenger flow of the sample station and the passenger flow capacity of the sample station. The passenger flow saturation of the sample interval of each sample interval is determined according to the corresponding ratio of the passenger flow of the sample interval and the passenger flow capacity of the sample interval. The evacuation time of the stranded passengers of each sample station at the corresponding time is determined according to the ratio of the number of stranded passengers at the corresponding sample station and the passenger evacuation speed of the sample station. The corresponding sample attribute set is further determined according to the passenger flow saturation of the sample station at each sample station at the corresponding time, the stranded passenger evacuation time of the sample station, and the passenger flow saturation of the sample interval of each sample interval. Wherein, the sample attribute information may be real data obtained by historical collection, or may also be simulation data obtained by simulation modeling.

[0124] Further, after determining a plurality of sample attribute information, the station risk label corresponding to each sample station, the line risk label of each sample interval and the road network risk label of the sample transportation network can also be calculated according to the sample attribute information corresponding to each sample station. Specifically, the interval risk label of each sample interval can be determined according to the corresponding sample interval passenger flow and the sample interval passenger flow capacity ratio, that is, the sample interval passenger flow saturation is directly determined as the corresponding interval risk label. The station risk label of each sample station is obtained by calculating the weighted sum of the corresponding sample station passenger flow saturation and the sample station stranded passenger evacuation time. The corresponding line risk label is obtained by calculating the station risk label of each sample station in each sample line and the weighted sum of the interval risk label of each sample interval included therein. The corresponding station risk label is then obtained by calculating the station risk label of each sample station in the sample transportation network and the weighted sum of the interval risk label of each sample interval included therein. Optionally, the interval risk label of each sample interval can also be stored in the training data set as the label corresponding to the sample attribute set.

[0125] After determining the training data set, the network parameters in the Bayesian network can be determined according to the training data set to obtain a trained Bayesian network. The data in the training data set can be input into a preset log-likelihood function, which includes at least two candidate parameters, and then the gradient of each candidate parameter in the log-likelihood function is calculated to obtain a corresponding gradient equation. Finally, the system of equations is solved according to each gradient equation to obtain the solution of each candidate parameter as the network parameter in the Bayesian network.

[0126] Optionally, the network parameters in the Bayesian network may include a first network parameter for predicting station capacity risk and / or interval capacity risk, a second network parameter for predicting line capacity risk, and a third network parameter for predicting road network capacity risk. Each set of network parameters needs to be calculated separately by the above-mentioned log-likelihood function, that is, the first network parameter can be determined based on the sample attribute set and station risk label in the training data set, the second network parameter can be determined based on the station risk label, interval risk label and line risk label in the training data set, and the third network parameter can be determined based on the line risk label and road network risk label in the training data set. The log-likelihood function can be

[0127]

[0128] Where Y is the parent node, X is the corresponding child node, and K is the number of child nodes of the parent node Y. For example, when Y is the station risk label, X includes the sample attribute information of the station, and K is the number of sample attribute information of the station. When Y is the sample line label, X includes the station risk labels of all sample stations in the sample line and the interval risk labels of the sample intervals, and K is the sum of the number of sample stations and the number of sample intervals in the sample line. When Y is the road network risk label, X includes the sample line labels of all sample lines, and K is the sum of the number of sample lines. M is the number of X samples corresponding to Y in the training data set, β is the candidate parameter, D is the training data set, σ 2 is the sample variance, which can be calculated by the following formula:

[0129]

[0130] in, is the sample covariance of Y and X in the training data set, is the sample variance of X in the training data set.

[0131] After determining the log-likelihood function, the gradient of each candidate parameter is calculated to obtain the following formula:

[0132]

[0133] Further, the formula obtained by finding the gradient of multiple candidate parameters is used to construct a system of equations including K+1 equations, and solve k+1 variables β0, β1, …, β k , let β=(β1,…,β k ) T The result of further solution is:

[0134]

[0135]

[0136] in, They represent the sample means of variables Y and X in the training data set D respectively.

[0137] Based on the above technical features, the disclosed embodiment can take into account the positional relationship between different stations and sections and lines in the road network, as well as the attribute changes in time series, in the process of predicting the transportation capacity risk of the entire road network, thereby improving the accuracy of the prediction results. At the same time, the disclosed embodiment predicts the transportation capacity risk of the road network layer by layer through the Bayesian network layering, thereby improving the interpretability of the risk prediction process. At the same time, when the prediction result is a high risk, the risk points in the rail transit road network can be accurately located, which can help to quickly solve the risk problem.

[0138] Figure 3 A schematic diagram of a rail transit capacity risk prediction device according to an embodiment of the present disclosure is shown. Figure 3 As shown, the rail transit capacity risk prediction device of the embodiment of the present disclosure may include:

[0139] A network determination module 30 is used to determine a rail transit network including at least one line, each of which includes at least two stations, and an operating interval is between every two stations;

[0140] An attribute set determination module 31, used for periodically determining a risk attribute set, wherein the risk attribute set determined in each period includes at least one risk attribute value of each of the stations and the operating interval at a corresponding time of the period;

[0141] The risk prediction module 32 is used to predict the network capacity risk of the rail transit network at a corresponding time in the next cycle based on the risk attribute set according to the trained Bayesian network after each acquisition of the risk attribute set;

[0142] Wherein, the Bayesian network predicts the station capacity risk of each of the stations and the interval capacity risk of each of the operating intervals according to the corresponding risk attribute values;

[0143] According to the station capacity risk of each line including the station and the interval capacity risk including the operation interval, predicting the line capacity risk corresponding to each line;

[0144] According to the line capacity risk corresponding to each of the lines, the network capacity risk corresponding to the rail transit network is predicted.

[0145] In a possible implementation, the risk attribute value of the station includes the station passenger flow saturation and the station stranded passenger evacuation time. The station passenger flow saturation is used to characterize the relationship between the actual passenger flow and the passenger flow capacity of the station at the corresponding time, and the station stranded passenger evacuation time is used to characterize the time required for passengers in the station to completely leave the station; the risk attribute value of the operating interval includes the interval passenger flow saturation used to characterize the relationship between the actual passenger flow and the passenger flow capacity of the interval at the corresponding time.

[0146] In a possible implementation, the attribute set determination module 31 is further configured to:

[0147] Periodically obtaining the station passenger flow, number of stranded passengers, station passenger flow capacity and station passenger evacuation speed of each station in the rail transit network, as well as the interval passenger flow and interval passenger flow capacity of each operating interval according to a preset time period;

[0148] Determine the station passenger flow saturation of each station at a corresponding time according to the ratio of the station passenger flow in each cycle to the station passenger flow capacity;

[0149] Determining the evacuation time of stranded passengers at each station at a corresponding time according to the ratio of the number of stranded passengers at the station in each cycle to the evacuation speed of passengers at the station;

[0150] Determining the interval passenger flow saturation of each interval at a corresponding time according to the ratio of the interval passenger flow in each cycle to the interval passenger flow capacity;

[0151] The risk attribute set corresponding to the moment is determined according to the station passenger flow saturation and the evacuation time of stranded passengers at each of the stations at the corresponding moment of each cycle, and the interval passenger flow saturation of each of the intervals.

[0152] In a possible implementation, the risk prediction module 32 is further configured to:

[0153] After each risk attribute set is obtained, the risk attribute set corresponding to the current moment is input into the trained Bayesian network, and the corresponding road network capacity risk is output;

[0154] Among them, the risk attribute value corresponding to each of the stations is the risk attribute value at the corresponding moment of the current cycle.

[0155] In a possible implementation, the risk prediction module 32 is further configured to:

[0156] After each risk attribute set is obtained, the risk attribute set corresponding to the current moment and the risk attribute set obtained in the previous cycle are input into the trained Bayesian network together, and the corresponding road network capacity risk is output;

[0157] The risk attribute value corresponding to each of the stations includes the risk attribute value at the current moment and the risk attribute value corresponding to the previous period.

[0158] In a possible implementation, the training process of the Bayesian network includes:

[0159] Determine a training data set including a plurality of sample attribute sets having corresponding station risk labels, section risk labels, line risk labels, and road network risk labels;

[0160] The network parameters in the Bayesian network are determined according to the training data set to obtain a trained Bayesian network.

[0161] In a possible implementation, the determining includes a plurality of training data sets having sample attribute sets corresponding to station risk labels, section risk labels, line risk labels, and road network risk labels, including:

[0162] Determine a sample traffic network including at least one sample route, each of the sample routes includes at least two sample stations, and a sample interval is formed between every two sample stations;

[0163] Determine a plurality of sample attribute information corresponding to each of the sample stations and the sample intervals in the sample transportation network at at least one time;

[0164] Determine a sample attribute set according to the sample attribute information of each of the sample stations and the sample interval;

[0165] Calculate, according to the sample attribute set, a station risk label corresponding to each of the sample stations, an interval risk label corresponding to each of the sample intervals, a line risk label of each of the sample lines, and a network risk label of the sample transportation network;

[0166] A training data set is determined based on each of the sample attribute sets, and the corresponding station risk labels, line risk labels, and road network risk labels.

[0167] In a possible implementation, the sample attribute information includes the passenger flow of the sample station, the number of stranded passengers at the sample station, the passenger flow capacity of the sample station, the passenger evacuation speed of the sample station, the passenger flow of the sample interval, and the passenger flow capacity of the sample interval.

[0168] In a possible implementation manner, determining a sample attribute set according to the sample attribute information of each of the sample stations and the sample intervals includes:

[0169] Determine the sample station passenger flow saturation of each sample station at a corresponding time according to the corresponding sample station passenger flow and the sample station passenger flow capacity ratio;

[0170] Determine the evacuation time of stranded passengers at each sample station at a corresponding time according to the ratio of the number of stranded passengers at the corresponding sample station to the evacuation speed of passengers at the sample station;

[0171] Determine the sample interval passenger flow saturation of each sample interval according to the corresponding sample interval passenger flow and the sample interval passenger flow capacity ratio;

[0172] The corresponding sample attribute set is determined according to the sample station passenger flow saturation and the sample station stranded passenger evacuation time of each of the sample stations at the corresponding time, and the sample interval passenger flow saturation of each of the sample intervals.

[0173] In a possible implementation, the step of calculating, according to the sample attribute set, a station risk label corresponding to each of the sample stations, an interval risk label corresponding to each of the sample intervals, a line risk label of each of the sample lines, and a road network risk label of the sample transportation road network includes:

[0174] Determine the sample interval passenger flow saturation of each sample interval as the corresponding interval risk label;

[0175] The station risk label of each sample station is obtained by calculating the corresponding sample station passenger flow saturation and the weighted sum of the sample station stranded passenger evacuation time;

[0176] Obtaining a corresponding line risk label by calculating a weighted sum of the station risk label of each of the sample stations in each of the sample lines and the interval risk label of each of the sample intervals included therein;

[0177] The corresponding station risk label is obtained by calculating the weighted sum of the station risk label of each of the sample stations in the sample transportation network and the interval risk label of each of the sample intervals included therein.

[0178] In a possible implementation, the sample attribute information is real data obtained through collection, or simulated data obtained through simulation modeling.

[0179] In a possible implementation, determining the network parameters in the Bayesian network according to the training data set to obtain a trained Bayesian network includes:

[0180] Inputting the data in the training data set into a preset log-likelihood function, wherein the log-likelihood function includes at least two candidate parameters;

[0181] Calculating the gradient of each candidate parameter in the log-likelihood function to obtain a corresponding gradient equation;

[0182] Solving the equation group according to each of the gradient equations obtains a solution for each of the candidate parameters as a network parameter in the Bayesian network.

[0183] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0184] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0185] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0186] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0187] Figure 4 A schematic diagram of an electronic device 800 according to an embodiment of the present disclosure is shown. For example, the electronic device 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0188] Reference Figure 4 , the electronic device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0189] The processing component 802 generally controls the overall operation of the electronic device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0190] The memory 804 is configured to store various types of data to support operations on the electronic device 800. Examples of such data include instructions for any application or method operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0191] The power supply component 806 provides power to the various components of the electronic device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the electronic device 800.

[0192] The multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the electronic device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0193] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the electronic device 800 is in an operating mode, such as a call mode, a recording mode, and a voice recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0194] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0195] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the electronic device 800. For example, the sensor assembly 814 can detect the open / closed state of the electronic device 800, the relative positioning of the components, such as the display and keypad of the electronic device 800, and the sensor assembly 814 can also detect the position change of the electronic device 800 or a component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0196] The communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices. The electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0197] In an exemplary embodiment, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above methods.

[0198] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 804 including computer program instructions, which can be executed by a processor 820 of an electronic device 800 to perform the above method.

[0199] Figure 5 1 is a schematic diagram showing another electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server or a terminal device. Figure 5, the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0200] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output (I / O) interface 1958. The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™ or the like.

[0201] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0202] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0203] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0204] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0205] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0206] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0207] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0208] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0209] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0210] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A rail transit capacity risk prediction method, characterized in that: The method comprises: Determine a rail transit network including at least one line, each of the lines including at least two stations, and an operating interval between every two stations; Periodically determining a risk attribute set, wherein the risk attribute set determined in each period includes at least one risk attribute value of each of the stations and the operating interval at a corresponding time of the period; After each time a risk attribute set is obtained, predicting the network capacity risk of the rail transit network at a corresponding time in the next cycle based on the risk attribute set according to the trained Bayesian network; Wherein, the Bayesian network predicts the station capacity risk of each of the stations and the interval capacity risk of each of the operating intervals according to the corresponding risk attribute values; According to the station capacity risk of each line including the station and the interval capacity risk including the operation interval, predicting the line capacity risk corresponding to each line; According to the line capacity risk corresponding to each of the lines, the network capacity risk corresponding to the rail transit network is predicted.

2. The method according to claim 1, characterized in that The risk attribute values ​​of the station include the station passenger flow saturation and the evacuation time of stranded passengers. The station passenger flow saturation is used to characterize the relationship between the actual passenger flow and the passenger flow capacity of the station at the corresponding time, and the station stranded passenger evacuation time is used to characterize the time required for passengers in the station to completely leave the station; the risk attribute values ​​of the operating interval include the interval passenger flow saturation used to characterize the relationship between the actual passenger flow and the passenger flow capacity of the interval at the corresponding time.

3. The method according to claim 2, characterized in that The periodically determining a risk attribute set includes: Periodically obtaining the station passenger flow, number of stranded passengers, station passenger flow capacity and station passenger evacuation speed of each station in the rail transit network, as well as the interval passenger flow and interval passenger flow capacity of each operating interval according to a preset time period; Determine the station passenger flow saturation of each station at a corresponding time according to the ratio of the station passenger flow in each cycle to the station passenger flow capacity; Determining the evacuation time of stranded passengers at each station at a corresponding time according to the ratio of the number of stranded passengers at the station in each cycle to the evacuation speed of passengers at the station; Determining the interval passenger flow saturation of each interval at a corresponding time according to the ratio of the interval passenger flow in each cycle to the interval passenger flow capacity; The risk attribute set corresponding to the moment is determined according to the station passenger flow saturation and the evacuation time of stranded passengers at each of the stations at the corresponding moment of each cycle, and the interval passenger flow saturation of each of the intervals.

4. The method according to any one of claims 1 to 3, characterized in that: After each acquisition of the risk attribute set, predicting the network capacity risk of the rail transit network at a corresponding time in the next cycle based on the risk attribute set according to the trained Bayesian network includes: After each risk attribute set is obtained, the risk attribute set corresponding to the current moment is input into the trained Bayesian network, and the corresponding road network capacity risk is output; Among them, the risk attribute value corresponding to each of the stations is the risk attribute value at the corresponding moment of the current cycle.

5. The method according to any one of claims 1 to 3, characterized in that: After each acquisition of the risk attribute set, predicting the network capacity risk of the rail transit network at a corresponding time in the next cycle based on the risk attribute set according to the trained Bayesian network includes: After each risk attribute set is obtained, the risk attribute set corresponding to the current moment and the risk attribute set obtained in the previous cycle are input into the trained Bayesian network together, and the corresponding road network capacity risk is output; The risk attribute value corresponding to each of the stations includes the risk attribute value at the current moment and the risk attribute value corresponding to the previous period.

6. The method according to any one of claims 1 to 5, characterized in that: The training process of the Bayesian network includes: Determine a training data set including a plurality of sample attribute sets having corresponding station risk labels, section risk labels, line risk labels, and road network risk labels; The network parameters in the Bayesian network are determined according to the training data set to obtain a trained Bayesian network.

7. The method according to claim 6, characterized in that The determination includes a plurality of training data sets having sample attribute sets corresponding to station risk labels, section risk labels, line risk labels, and road network risk labels, including: Determine a sample traffic network including at least one sample route, each of the sample routes includes at least two sample stations, and a sample interval is formed between every two sample stations; Determine a plurality of sample attribute information corresponding to each of the sample stations and the sample intervals in the sample transportation network at at least one time; Determine a sample attribute set according to the sample attribute information of each of the sample stations and the sample interval; Calculate, according to the sample attribute set, a station risk label corresponding to each of the sample stations, an interval risk label corresponding to each of the sample intervals, a line risk label of each of the sample lines, and a network risk label of the sample transportation network; A training data set is determined based on each of the sample attribute sets, and the corresponding station risk labels, line risk labels, and road network risk labels.

8. The method according to claim 7, characterized in that The sample attribute information includes the passenger flow of the sample station, the number of stranded passengers at the sample station, the passenger flow capacity of the sample station, the passenger evacuation speed of the sample station, the passenger flow of the sample interval and the passenger flow capacity of the sample interval.

9. The method according to claim 8, characterized in that The determining of the sample attribute set according to the sample attribute information of each of the sample stations and the sample intervals includes: Determine the sample station passenger flow saturation of each sample station at a corresponding time according to the corresponding sample station passenger flow and the sample station passenger flow capacity ratio; Determine the evacuation time of stranded passengers at each sample station at a corresponding time according to the ratio of the number of stranded passengers at the corresponding sample station to the evacuation speed of passengers at the sample station; Determine the sample interval passenger flow saturation of each sample interval according to the corresponding sample interval passenger flow and the sample interval passenger flow capacity ratio; The corresponding sample attribute set is determined according to the sample station passenger flow saturation and the sample station stranded passenger evacuation time of each of the sample stations at the corresponding time, and the sample interval passenger flow saturation of each of the sample intervals.

10. The method according to claim 9, characterized in that The step of calculating, according to the sample attribute set, a station risk label corresponding to each of the sample stations, an interval risk label corresponding to each of the sample intervals, a line risk label of each of the sample lines, and a road network risk label of the sample transportation road network includes: Determine the sample interval passenger flow saturation of each sample interval as the corresponding interval risk label; The station risk label of each sample station is obtained by calculating the corresponding sample station passenger flow saturation and the weighted sum of the sample station stranded passenger evacuation time; Obtaining a corresponding line risk label by calculating a weighted sum of the station risk label of each of the sample stations in each of the sample lines and the interval risk label of each of the sample intervals included therein; The corresponding station risk label is obtained by calculating the weighted sum of the station risk label of each of the sample stations in the sample transportation network and the interval risk label of each of the sample intervals included therein.

11. The method according to any one of claims 7 to 10, characterized in that: The sample attribute information is real data obtained through collection, or simulated data obtained through simulation modeling.

12. The method according to any one of claims 6 to 11, characterized in that: Determining the network parameters in the Bayesian network according to the training data set to obtain a trained Bayesian network includes: Inputting the data in the training data set into a preset log-likelihood function, wherein the log-likelihood function includes at least two candidate parameters; Calculating the gradient of each candidate parameter in the log-likelihood function to obtain a corresponding gradient equation; Solving the system of equations according to each of the gradient equations obtains a solution for each of the candidate parameters as a network parameter in the Bayesian network.

13. A rail transit capacity risk prediction device, characterized in that: The device comprises: A network determination module, used to determine a rail transit network including at least one line, each of which includes at least two stations, and an operating interval is between every two stations; An attribute set determination module, used for periodically determining a risk attribute set, wherein the risk attribute set determined in each period includes at least one risk attribute value of each of the stations and the operating interval at a corresponding time of the period; A risk prediction module, configured to predict the network capacity risk of the rail transit network at a corresponding time in the next cycle based on the risk attribute set according to the trained Bayesian network after each acquisition of the risk attribute set; Wherein, the Bayesian network predicts the station capacity risk of each of the stations and the interval capacity risk of each of the operating intervals according to the corresponding risk attribute values; According to the station capacity risk of each line including the station and the interval capacity risk including the operation interval, predicting the line capacity risk corresponding to each line; According to the line capacity risk corresponding to each of the lines, the network capacity risk corresponding to the rail transit network is predicted.

14. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement the method described in any one of claims 1 to 12 when executing the instructions stored in the memory.

15. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 12 is implemented.

Images