A method and device for automatically discovering problems in a bus network

Abstract

The present invention discloses a method and device for automatically discovering problems in a bus network. The method includes obtaining historical passenger flow data, determining the cross-sectional average passenger flow, high-level average passenger flow, and low-level average passenger flow of each station, determining the station imbalance rate based on the high-level average passenger flow and the low-level average passenger flow, and determining the bus lines with a station imbalance rate greater than a preset threshold as problem lines. According to the cross-sectional passenger flow of each station of the problem lines, a passenger flow waveform diagram of the problem lines is constructed, and the peaks and valleys of the passenger flow waveform diagram are determined. According to the peaks and valleys of the passenger flow waveform diagram, the problems corresponding to the problem lines are determined. By analyzing the boarding and alighting, cross-sectional passenger flow, OD passenger flow, and transfer passenger flow of the bus line stations, the problem that the layout of the line stations does not match the passenger flow is discovered and adjustment and optimization suggestions are proposed, providing a means for automatically discovering problems for bus network optimization, effectively improving the problem discovery rate and reducing the analysis workload of the network optimization personnel.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of transportation technologies, and in particular, to a method and device for automatically discovering problems in a bus network. Background Art

[0002] In a bus network optimization system, the key is to find out the problems existing in the existing bus network, and then make adjustments and optimizations according to the problems to improve the bus service level and reduce the bus operation cost.

[0003] The discovery of bus line problems mainly relies on passenger flow data. The sources of passenger flow data can be signaling data, bus IC card (Integrated Circuit Card) (including mobile payment) data, and bus passenger flow counter data. Now, with the popularization of mobile payment, the proportion of bus IC card (including mobile payment) payment methods in passengers' payment methods has been very high. The payment proportion in developed cities has exceeded 80%, and good passenger flow data analysis results (including OD (Origin Destination)) can be achieved through passenger flow analysis technologies such as travel chains. Therefore, relying on IC card passenger flow data is an ideal source of passenger flow data. However, at present, the discovery of bus line problems is all manual, which results in high labor costs and low efficiency. Summary of the Invention

[0004] Embodiments of the present invention provide a method and device for automatically discovering problems in a bus network, so as to effectively improve the problem discovery rate and reduce the analysis workload of network optimization personnel, and effectively improve the bus service level and reduce the operation cost through network adjustment.

[0005] In a first aspect, embodiments of the present invention provide a method for automatically discovering problems in a bus network, including:

[0006] Obtaining historical passenger flow data of multiple dimensions of each station on a bus line;

[0007] According to the historical passenger flow data of the multiple dimensions, determining the cross-sectional average passenger flow, high-level average passenger flow, and low-level average passenger flow of any dimension of each station;

[0008] According to the high-level average passenger flow and low-level average passenger flow of any dimension of each station, determining the station imbalance rate of any dimension of the bus line; and determining the bus line with the station imbalance rate of any dimension greater than a preset threshold as a problem line under any dimension;

[0009] According to the cross-sectional passenger flow of each station on the problem line under any dimension, constructing a passenger flow waveform diagram of the problem line under any dimension, and determining the peaks and valleys of the passenger flow waveform diagram;

[0010] Based on the peaks and valleys of the passenger flow waveform diagram, determine the problems corresponding to the problem line.

[0011] In the above technical solution, through the analysis of the boarding and alighting, section passenger flow, OD passenger flow, and transfer passenger flow at the bus line stops, the problem that the layout of the line stops does not match the passenger flow is automatically discovered for the scenario, and adjustment and optimization suggestions are put forward, providing a means for automatic problem discovery for bus network optimization, effectively improving the problem discovery rate and reducing the analysis workload of the network optimization personnel. Through network adjustment, the service level of the bus is effectively improved and the operating cost is reduced.

[0012] Optionally, the determining the cross-section average passenger flow, high-level average passenger flow, and low-level average passenger flow of any dimension of each stop according to the historical passenger flow data of the multiple dimensions includes:

[0013] For any dimension of the multiple dimensions, count the cross-section passenger flow in the historical passenger flow data of any dimension of each stop to determine the cross-section average passenger flow corresponding to any dimension of each stop;

[0014] Count the cross-section passenger flow greater than the cross-section average passenger flow in any dimension of each stop to determine the high-level average passenger flow of any dimension of each stop;

[0015] Count the cross-section passenger flow less than the cross-section average passenger flow in any dimension of each stop to determine the low-level average passenger flow of any dimension of each stop.

[0016] Optionally, the determining the station imbalance rate of any dimension of the bus line according to the high-level average passenger flow and low-level average passenger flow of any dimension of each stop includes:

[0017] Determine whether the ratio of the high-level average passenger flow to the low-level average passenger flow is greater than the ratio threshold;

[0018] If so, determine the number of stations where the cross-section passenger flow is above the high-level average passenger flow and the number of stations where the cross-section passenger flow is below the low-level average passenger flow in any dimension;

[0019] Determine the ratio of the number of stations where the cross-section passenger flow is above the high-level average passenger flow and the number of stations where the cross-section passenger flow is below the low-level average passenger flow in any dimension to the total number of stations of the bus line as the station imbalance rate of any dimension of the bus line.

[0020] Optionally, the constructing the passenger flow waveform diagram of the problem line in any dimension according to the cross-section passenger flow of each stop of the problem line in any dimension, and determining the peaks and valleys of the passenger flow waveform diagram includes:

[0021] Determine the continuous average value of each station on the problem line in any dimension according to the cross-sectional passenger flow of each station on the problem line and the preset continuous average parameter in any dimension;

[0022] Construct a passenger flow waveform diagram of the problem line in any dimension according to the continuous average value of each station on the problem line in any dimension;

[0023] If the continuous average value in the passenger flow waveform diagram of the problem line in any dimension is greater than the high average passenger flow, determine the peak, and determine the station with the continuous average value greater than the high average passenger flow as the starting station of the peak, and determine the station located after the starting station of the peak and with the continuous average value less than the high average passenger flow as the ending station of the peak;

[0024] If the continuous average value in the passenger flow waveform diagram of the problem line in any dimension is less than the low average passenger flow, determine the trough, and determine the station with the continuous average value less than the low average passenger flow as the starting station of the trough, and determine the station located after the starting station of the trough and with the continuous average value greater than the low average passenger flow as the ending station of the trough.

[0025] Optionally, determining the problem corresponding to the problem line according to the peak and trough of the passenger flow waveform diagram includes:

[0026] Determine the number of the first peak, the last peak and the troughs between the first peak and the last peak in the passenger flow waveform diagram;

[0027] If no peak appears at a preset number of stations after the starting station of the problem line or at a preset number of stations before the ending station of the problem line, determine that the problem corresponding to the problem line is a one-way multi-sub-line problem;

[0028] If no peak appears at a preset number of stations after the starting station of the problem line and at a preset number of stations before the ending station of the problem line, determine that the problem corresponding to the problem line is a two-way multi-sub-line problem;

[0029] If the number of peaks of the problem line is greater than the number threshold, a suspected major station line is determined; according to the boarding passenger flow and alighting passenger flow of each station on the suspected major station line, the average boarding passenger flow and the average alighting passenger flow of each station on the suspected major station line are determined, and according to the boarding passenger flow greater than the average boarding passenger flow, the average high boarding passenger flow is determined; according to the alighting passenger flow greater than the average alighting passenger flow, the average high alighting passenger flow is determined; if there is a station on the suspected major station line where the boarding passenger flow is greater than the average high boarding passenger flow and the alighting passenger flow is greater than the average high alighting passenger flow, it is determined that the problem of the suspected major station line is the major station passenger flow problem.

[0030] Optionally, after determining the problem corresponding to the problem line according to the peaks and valleys of the passenger flow waveform diagram, the method further includes:

[0031] If the problem corresponding to the problem line is a one-way multi-sub-line problem or a two-way multi-sub-line problem, when it is determined that the cross-sectional passenger flow of a preset number of stations after the starting station of the problem line or a preset number of stations before the ending station of the problem line is less than the low average passenger flow, it is determined that the problem line is a truncated line, and the truncated station is determined; when it is determined that the cross-sectional passenger flow of a preset number of stations after the starting station of the problem line or a preset number of stations before the ending station of the problem line is greater than the low average passenger flow, it is determined that the problem line is a multi-section passenger flow line, and the demarcation station is determined;

[0032] If it is a major station passenger flow problem corresponding to the problem line, the stations with boarding passenger flow greater than the average high boarding passenger flow and alighting passenger flow greater than the average high alighting passenger flow are determined as major stations.

[0033] Optionally, the method further includes:

[0034] Obtain the transfer passenger flow data of the bus line;

[0035] According to the transfer passenger flow data of the bus line, transfer pairs are determined, and each transfer pair includes a source station and a destination station;

[0036] Traverse each transfer pair, taking the starting transfer pair as the source station as the starting point of the transfer chain, determine whether there is a subsequent transfer pair as the transfer pair of the source one-way for the destination station of the starting transfer pair. If so, add the subsequent transfer pair as the transfer pair of the source one-way to the bottom of the transfer chain; and determine whether there is a subsequent transfer pair as the transfer pair of the destination one-way for the source one-way. If it exists, insert the subsequent transfer pair of the source one-way as the transfer pair of the destination one-way in front of the transfer pair of the source one-way in the transfer chain;

[0037] Traverse the passenger flow of each transfer station in the transfer chain and the order of each transfer station to construct a list of stations for the new line;

[0038] If the IDs of the source station and the target station in the transfer chain are different, determine the distance between the source station and the target station. When it is determined that the distance is greater than the distance threshold, add the target station after the source station in the bus line where the source station is located, or add the source station before the target station in the bus line where the target station is located.

[0039] In a second aspect, an embodiment of the present invention provides a device for automatically discovering problems in a bus network, including:

[0040] An acquisition unit for acquiring historical passenger flow data of each station of a bus line in multiple dimensions;

[0041] A processing unit for determining the cross-sectional average passenger flow, the high-level average passenger flow, and the low-level average passenger flow of any dimension of each station according to the historical passenger flow data of multiple dimensions; determining the station imbalance rate of any dimension of the bus line according to the high-level average passenger flow and the low-level average passenger flow of any dimension of each station; and determining the bus line with the station imbalance rate of any dimension greater than a preset threshold as the problem line under any dimension; constructing a passenger flow waveform diagram of the problem line under any dimension according to the cross-sectional passenger flow of each station of the problem line under any dimension, and determining the peaks and valleys of the passenger flow waveform diagram; determining the problems corresponding to the problem line according to the peaks and valleys of the passenger flow waveform diagram.

[0042] Optionally, the processing unit is specifically configured to:

[0043] For any dimension in the multiple dimensions, count the cross-sectional passenger flow in the historical passenger flow data of any dimension of each station to determine the cross-sectional average passenger flow corresponding to any dimension of each station;

[0044] Count the cross-sectional passenger flow greater than the cross-sectional average passenger flow in any dimension of each station to determine the high-level average passenger flow of any dimension of each station;

[0045] Count the cross-sectional passenger flow less than the cross-sectional average passenger flow in any dimension of each station to determine the low-level average passenger flow of any dimension of each station.

[0046] Optionally, the processing unit is specifically configured to:

[0047] Determine whether the ratio of the high-level average passenger flow to the low-level average passenger flow is greater than a ratio threshold;

[0048] If so, determine the number of stations where the cross-sectional passenger flow in any dimension is above the high average passenger flow and the number of stations where the cross-sectional passenger flow is below the low average passenger flow;

[0049] Determine the ratio of the number of stations where the cross-sectional passenger flow in any dimension is above the high average passenger flow and the number of stations where the cross-sectional passenger flow is below the low average passenger flow to the total number of stations on the bus line as the station imbalance rate in any dimension of the bus line.

[0050] Optionally, the processing unit is specifically configured to:

[0051] Determine the continuous average value of each station on the problem line in any dimension according to the cross-sectional passenger flow of each station on the problem line in any dimension and the preset continuous average parameter;

[0052] Construct a passenger flow waveform diagram of the problem line in any dimension according to the continuous average value of each station on the problem line in any dimension;

[0053] If the continuous average value in the passenger flow waveform diagram of the problem line in any dimension is greater than the high average passenger flow, determine the peak, and determine the station where the continuous average value is greater than the high average passenger flow as the starting station of the peak, and determine the station after the starting station of the peak and where the continuous average value is less than the high average passenger flow as the ending station of the peak;

[0054] If the continuous average value in the passenger flow waveform diagram of the problem line in any dimension is less than the low average passenger flow, determine the trough, and determine the station where the continuous average value is less than the low average passenger flow as the starting station of the trough, and determine the station after the starting station of the trough and where the continuous average value is greater than the low average passenger flow as the ending station of the trough.

[0055] Optionally, the processing unit is specifically configured to:

[0056] Determine the number of the first peak, the last peak and the troughs between the first peak and the last peak in the passenger flow waveform diagram;

[0057] If no peak appears at a preset number of stations after the starting station of the problem line or at a preset number of stations before the ending station of the problem line, determine that the problem corresponding to the problem line is a one-way multi-sub-line problem;

[0058] If no peak appears at a preset number of stations after the starting station of the problem line and at a preset number of stations before the ending station of the problem line, determine that the problem corresponding to the problem line is a two-way multi-sub-line problem;

[0059] If the number of peaks of the problem line is greater than the number threshold, a suspected large station line is determined; according to the boarding passenger flow and alighting passenger flow of each station on the suspected large station line, the average boarding passenger flow and the average alighting passenger flow of each station on the suspected large station line are determined, and according to the boarding passenger flow greater than the average boarding passenger flow, the average high boarding passenger flow is determined; according to the alighting passenger flow greater than the average alighting passenger flow, the average high alighting passenger flow is determined; if there is a station on the suspected large station line where the boarding passenger flow is greater than the average high boarding passenger flow and the alighting passenger flow is greater than the average high alighting passenger flow, it is determined that the problem of the suspected large station line is the large station passenger flow problem.

[0060] Optionally, the processing unit is further configured to:

[0061] After determining the problem corresponding to the problem line according to the peaks and valleys of the passenger flow waveform diagram, if the problem corresponding to the problem line is a one-way multi-sub-line problem or a two-way multi-sub-line problem, when it is determined that the cross-sectional passenger flow of a preset number of stations after the starting station of the problem line or a preset number of stations before the ending station of the problem line is less than the low average passenger flow, it is determined that the problem line is a truncated line, and the truncated station is determined; when it is determined that the cross-sectional passenger flow of a preset number of stations after the starting station of the problem line or a preset number of stations before the ending station of the problem line is greater than the low average passenger flow, it is determined that the problem line is a multi-interval passenger flow line, and the demarcation station is determined;

[0062] If it is the large station passenger flow problem corresponding to the problem line, the stations with boarding passenger flow greater than the average high boarding passenger flow and alighting passenger flow greater than the average high alighting passenger flow are determined as large station sites.

[0063] Optionally, the processing unit is further configured to:

[0064] Obtain the transfer passenger flow data of the bus line;

[0065] According to the transfer passenger flow data of the bus line, transfer pairs are determined, and each transfer pair includes a source station and a destination station;

[0066] Traverse each transfer pair, use the starting transfer pair as the source station as the starting point of the transfer chain, determine whether there is a subsequent transfer pair as the transfer pair of the source one-way for the destination station of the starting transfer pair, if so, add the subsequent transfer pair as the transfer pair of the source one-way to the bottom of the transfer chain; and determine whether there is a subsequent transfer pair as the transfer pair of the destination one-way for the source one-way, if it exists, insert the subsequent transfer pair of the source one-way as the transfer pair of the destination one-way in front of the transfer pair of the source one-way in the transfer chain;

[0067] Traverse the passenger flow of each transfer station in the transfer chain and the order of each transfer station to construct a list of stations for the new line;

[0068] If the IDs of the source station and the target station in the transfer chain are different, determine the distance between the source station and the target station. When it is determined that the distance is greater than the distance threshold, add the target station after the source station in the bus line where the source station is located, or add the source station before the target station in the bus line where the target station is located.

[0069] In a third aspect, an embodiment of the present invention further provides a computing device, including:

[0070] A memory for storing program instructions;

[0071] A processor for calling the program instructions stored in the memory and executing the method for automatically discovering bus network problems as described above according to the obtained program.

[0072] In a fourth aspect, an embodiment of the present invention further provides a computer-readable non-volatile storage medium, including computer-readable instructions. When a computer reads and executes the computer-readable instructions, the computer is caused to execute the method for automatically discovering bus network problems as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0074] Figure 1 A schematic diagram of a system architecture provided by an embodiment of the present invention;

[0075] Figure 2 A flowchart of a method for automatically discovering bus network problems provided by an embodiment of the present invention;

[0076] Figure 3 A schematic diagram of an average passenger flow provided by an embodiment of the present invention;

[0077] Figure 4 A schematic diagram of a passenger flow waveform diagram provided by an embodiment of the present invention;

[0078] Figure 5 A schematic diagram of a passenger flow waveform diagram provided by an embodiment of the present invention;

[0079] Figure 6 A schematic diagram of a passenger flow waveform diagram provided by an embodiment of the present invention;

[0080] Figure 7 A schematic diagram of a transfer line provided by an embodiment of the present invention;

[0081] Figure 8 A schematic diagram of a transfer line provided by an embodiment of the present invention;

[0082] Figure 9 A schematic diagram of a transfer line provided by an embodiment of the present invention;

[0083] Figure 10 A schematic structural diagram of a device for automatically discovering problems in a bus network provided by an embodiment of the present invention. Detailed implementation manners

[0084] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part rather than all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0085] Figure 1 An exemplary system architecture applicable to an embodiment of the present invention is shown. The system architecture can be divided into three parts, including a passenger flow analysis and import service 100, a network problem analysis service 200, and a network problem display system 300.

[0086] Among them, the passenger flow analysis and import service 100 is used to analyze data such as IC cards and passenger flow counters, form passenger flow data such as OD in transfer and one-way dimensions, boarding and alighting at stations in one-way dimensions, and sections, and store them in a database.

[0087] The network problem analysis service 200, namely the system described in the document, automatically analyzes problems existing in the lines according to basic data such as lines and stations and passenger flow data.

[0088] The network problem display system 300 presents the analyzed problems to the user in forms, GIS maps, etc.

[0089] It should be noted that the above Figure 1 shown structure is only an example, and the embodiments of the present invention are not limited thereto.

[0090] Based on the above description, Figure 2 The flow of a method for automatically discovering problems in a bus network provided by an embodiment of the present invention is shown in detail. This flow can be executed by a device for automatically discovering problems in a bus network.

[0091] As Figure 2As shown in the figure, the process specifically includes:

[0092] Step 201: Obtain historical passenger flow data of multiple dimensions for each station on the bus line.

[0093] In the embodiments of the present invention, bus lines are all composed of one or more one-way trips, such as the upward and downward trips. Therefore, in the following description, the one-way trip is used as the unit. Usually, the OD passenger flow is only the passenger flow from station O to station D. The multiple dimensions refer to three dimensions: the whole day, peak hours, and off-peak hours. The embodiments of the present invention are only for illustrative purposes, and in the actual implementation process, it is not limited to the above three dimensions.

[0094] Read the one-way trip and station data of the bus line from the database and construct a one-way trip-station relationship data structure. Read the historical passenger flow data (boarding, alighting, section, OD) of each station for the three dimensions of the whole day, peak hours, and off-peak hours in one day. That is, the historical passenger flow data includes boarding passenger flow, alighting passenger flow, section passenger flow, and OD passenger flow, etc.

[0095] Step 202: According to the historical passenger flow data of the multiple dimensions, determine the section average passenger flow, high average passenger flow, and low average passenger flow of any dimension of each station.

[0096] Specifically, for any one of the multiple dimensions, first, count the section passenger flow in the historical passenger flow data of any dimension of each station to determine the section average passenger flow corresponding to any dimension of each station. Then, count the section passenger flow greater than the section average passenger flow in any dimension of each station to determine the high average passenger flow of any dimension of each station. Finally, count the section passenger flow less than the section average passenger flow in any dimension of each station to determine the low average passenger flow of any dimension of each station. It is equivalent to first calculating the section average passenger flow, and then calculating the high average passenger flow and low average passenger flow on the basis of the section average passenger flow.

[0097] Among them, the calculated section average passenger flow, high average passenger flow, and low average passenger flow can be as Figure 3 shown.

[0098] Step 203: According to the high average passenger flow and low average passenger flow of any dimension of each station, determine the station imbalance rate of any dimension of the bus line; and determine the bus line with the station imbalance rate of any dimension greater than the preset threshold as the problem line under any dimension.

[0099] Specifically, determine whether the ratio of the high average passenger flow to the low average passenger flow is greater than the ratio threshold. If so, determine the number of stations where the cross-sectional passenger flow in any dimension is above the high average passenger flow and the number of stations where the cross-sectional passenger flow is below the low average passenger flow. The ratio of the number of stations where the cross-sectional passenger flow in any dimension is above the high average passenger flow and the number of stations where the cross-sectional passenger flow is below the low average passenger flow to the total number of stations on the bus line is determined as the station imbalance rate of any dimension of the bus line. This ratio threshold can be set based on experience.

[0100] If the difference between the high average passenger flow and the low average passenger flow is large (e.g., the high average passenger flow divided by the low average passenger flow is greater than 2 (the ratio threshold)), it is considered that the passenger flow imbalance is relatively good. At this time, calculate all the stations above the high average passenger flow and below the low average passenger flow, accumulate to get the number of stations Co, and then divide Co by the total number of stations to obtain the station imbalance rate P.

[0101] If the station imbalance rate P is greater than the ratio threshold, it is considered that there may be problems with the passenger flow distribution and further analysis is required. Therefore, the bus lines with the station imbalance rate in any dimension greater than the preset threshold can be determined as the problem lines in any dimension.

[0102] Step 204, according to the cross-sectional passenger flow of each station of the problem line in any dimension, construct the passenger flow waveform diagram of the problem line in any dimension, and determine the peaks and valleys of the passenger flow waveform diagram.

[0103] After determining the problem line, the passenger flow waveform diagram can be constructed. Specifically, first, according to the cross-sectional passenger flow of each station of the problem line in any dimension and the preset continuous average parameter, determine the continuous average value of each station of the problem line in any dimension. Then, according to the continuous average value of each station of the problem line in any dimension, construct the passenger flow waveform diagram of the problem line in any dimension.

[0104] If the continuous average value in the passenger flow waveform diagram of the problem line in any dimension is greater than the high average passenger flow, determine the peak, and determine the starting station of the peak as the station where the continuous average value is greater than the high average passenger flow, and determine the ending station of the peak as the station where the continuous average value is less than the high average passenger flow after the starting station of the peak; if the continuous average value in the passenger flow waveform diagram of the problem line in any dimension is less than the low average passenger flow, determine the valley, and determine the starting station of the valley as the station where the continuous average value is less than the low average passenger flow, and determine the ending station of the valley as the station where the continuous average value is greater than the low average passenger flow after the starting station of the valley. Among them, the continuous average parameter of the continuous average value can be set based on experience, and this continuous average parameter refers to starting from which station to calculate the continuous average value.

[0105] When calculating the waveform diagram, continuous averaging is used for calculation. The default continuous averaging parameter K is 3. The continuous averaging parameter K is obtained by dividing the total number of stations by 10, which is not less than 1 and not greater than 3. Then, starting from the Kth station, the continuous average value is calculated for each station. Assuming the station number is I, in fact, the continuous average value of I and the (K - 1) stations before I is calculated. If the continuous average value is greater than the high average passenger flow, it indicates the occurrence of a peak. After the occurrence of a peak, if the value is lower than the high average, it indicates the end of the peak; if it is less than the low average passenger flow in the second step, it indicates the occurrence of a trough. After the occurrence of a trough, if the value is higher than the low average passenger flow, it indicates the occurrence of a peak. In this way, the construction of the spatial waveform distribution model of the one-way station data and the determination of peaks and troughs are completed.

[0106] Step 205, according to the peaks and troughs of the passenger flow waveform diagram, determine the problems corresponding to the problem line.

[0107] After determining the peaks and troughs, problem analysis can be carried out. Specifically, the first peak, the last peak, and the number of troughs between the first peak and the last peak in the passenger flow waveform diagram can be determined. Then, the analysis is carried out, which is specifically divided into the following situations:

[0108] The first situation:

[0109] If no peak appears at a preset number of stations after the starting station of the problem line or at a preset number of stations before the ending station of the problem line, it is determined that the problem corresponding to the problem line is a one-way multi-sub-line problem.

[0110] The second situation:

[0111] If no peak appears at both a preset number of stations after the starting station of the problem line and at a preset number of stations before the ending station of the problem line, it is determined that the problem corresponding to the problem line is a two-way multi-sub-line problem.

[0112] The third situation:

[0113] If the number of peaks of the problem line is greater than the quantity threshold, a suspected large-station line is determined; according to the boarding passenger flow and alighting passenger flow of each station on the suspected large-station line, the average boarding passenger flow and the average alighting passenger flow of each station on the suspected large-station line are determined, and according to the boarding passenger flow greater than the average boarding passenger flow, the high average boarding passenger flow is determined; according to the alighting passenger flow greater than the average alighting passenger flow, the high average alighting passenger flow is determined; if there is a station on the suspected large-station line where the boarding passenger flow is greater than the high average boarding passenger flow and the alighting passenger flow is greater than the high average alighting passenger flow, it is determined that the problem of the suspected large-station line is a large-station passenger flow problem.

[0114] For example, such as Figure 4 、 Figure 5 、Figure 6 As shown, first find the first peak, the last peak, and the number of valleys in the middle. If there are no peaks at the stations in the front small part (such as 1 / 4) or the back small part (such as 1 / 4), it is considered that the passenger flow at the front end or the back end is small. If there are a small number of valleys (such as within 3) in the middle, it is considered that the passenger flow in the middle is small and may need to be truncated in the middle (take the valley with the least passenger flow). If the number of peaks is greater than a certain number (such as 3), it is considered that it may be a large station train. These one-way trips are judged as suspect one-way trips with problems, and then use the OD data of these suspect one-way trips with problems and the passenger flow getting on and off at each station to judge whether it is a one-way trip with problems of large station trains.

[0115] There are two algorithms for the problem of large station trains. The first is to calculate the average boarding passenger flow Vu and the average alighting passenger flow Vd of each station, and calculate the high-level average boarding passenger flow Vuh for the boarding passenger flow greater than Vu, and calculate the high-level average alighting passenger flow Vdh for the alighting passenger flow greater than Vd. Then traverse the one-way stations, and take the stations where the boarding passenger flow is greater than Vuh and the alighting passenger flow is greater than Vdh as large station sites (that is, the stations with a large number of passengers getting on and off). The second algorithm is based on the first one. Use the OD data on the one-way trip to rank and select some of the most OD data, retain the data where the O or D site of this OD data falls on the sites selected in the first step, and include the corresponding sites as large station sites. If the number of large stations in a one-way trip exceeds 3 and is greater than 1 / 4 of the total number of stations, it is considered that a large station line can be opened.

[0116] After determining the problems corresponding to the problem lines, it is also necessary to determine the optimization suggestions, which can specifically include: If the problems corresponding to the problem lines are one-way multi-sub-line problems or two-way multi-sub-line problems, when the section passenger flow at a preset number of stations after the starting station of the problem line or at a preset number of stations before the ending station of the problem line is less than the low-level average passenger flow, determine the problem line as a truncated line and determine the truncated station; when the section passenger flow at a preset number of stations after the starting station of the problem line or at a preset number of stations before the ending station of the problem line is greater than the low-level average passenger flow, determine the problem line as a multi-section passenger flow line and determine the demarcation station; if it is a large station passenger flow problem corresponding to the problem line, the stations where the boarding passenger flow is greater than the high-level average boarding passenger flow and the alighting passenger flow is greater than the high-level average alighting passenger flow are determined as large station sites.

[0117] That is to say, for the determination of one-way passenger flow problems, it can include first judging the truncated or interrupted passenger flow (using the full-day passenger flow). If the passenger flow at the front end or the rear end is small and the passenger flow is lower than the low average value, it is considered that truncation is possible. If it is a truncatable line, the start or end station of the demarcation peak at the beginning or end is found as the truncation station, and it is respectively prompted that the passenger flow of the first few stations is very small, the passenger flow of the last few stations is very small, or the passenger flow at both ends is very small. If the passenger flow at the front or rear is higher than the low average, it is considered that it may be multi-section passenger flow, and then judge the situation of less passenger flow at both ends in the multi-section passenger flow (peak, off-peak, full-day), and respectively prompt that the passenger flow of the first few stations is less, the passenger flow of the last few stations is less, or the passenger flow at both ends is less, and mark the demarcation stations according to the start and end peaks.

[0118] If it is the intermediate truncated passenger flow, the trough with the smallest passenger flow within the two peaks at the beginning and end is taken as the truncated trough, and the stations between the start and end stations of the trough are considered as the stations discarded in the middle after the line is truncated into two lines.

[0119] Finally, the large-station passenger flow problem is completed. The large-station problem will record the list of large-station site numbers.

[0120] In the specific implementation process, the above various types of line passenger flow problems, suggestions, demarcation stations, and passenger flow statistical information used for analysis are finally stored in the database, and the table structure is shown in Table 1.

[0121] Table 1

[0122]

[0123] In the specific implementation process, a problem travel analysis service can be implemented to perform problem analysis once a day and store the results in the database, and regularly query and count the number of times the same problem appears on the same line within a recent period (such as 7 days). If the number of times exceeds the set number (such as 5 times), it is considered that the problem frequently appears on this line, then it is determined that there is this problem on this line and it is displayed to the user through the page to prompt the user to adjust this line. After the user adjusts the line according to the suggestion, the actual line adjustment can be implemented after verification through simulation.

[0124] The embodiment of the present invention can also perform transfer problem analysis, which can specifically include:

[0125] First, obtain the transfer passenger flow data of the bus line, and determine the transfer pairs according to the transfer passenger flow data of the bus line. The transfer pairs include the source station and the target station.

[0126] Then traverse each transfer pair. Using the starting transfer pair's source station as the starting point of the transfer chain, determine whether the target station of the starting transfer pair has a subsequent transfer pair as the transfer pair for the source one-way trip. If so, add the subsequent transfer pair as the transfer pair for the source one-way trip to the bottom of the transfer chain; and determine whether there is a subsequent transfer pair for the source one-way trip as the transfer pair for the target one-way trip. If there is a subsequent transfer pair for the source one-way trip as the transfer pair for the target one-way trip, then insert the subsequent transfer pair for the source one-way trip in front of the transfer pair for the source one-way trip in the transfer chain; traverse the passenger flow at each transfer station in the transfer chain and the order of each transfer station to construct the station list of the new line.

[0127] If the IDs of the source station and the target station in the transfer chain are different, then determine the distance between the source station and the target station. When it is determined that the distance is greater than the distance threshold, add the target station after the source station in the bus line where the source station is located, or add the source station before the target station in the bus line where the target station is located.

[0128] Transfer can analyze whether a new line can be formed based on large transfer stations according to macroscopic transfer, and microscopically find adjacent transfer stations based on the transfer ratio of one-way stations to judge the problem of adjusting line stations.

[0129] As Figure 7 shown, the dark color indicates a large passenger flow (high vehicle load factor). There is a transfer between two lines. At this time, if a line 3 as shown by the dotted line is planned according to the passenger flow quantity and transfer direction, then transfer can be effectively reduced and riding comfort can be improved.

[0130] The scenario of adjusting line stations can be as Figure 8 shown. There is a large non-homogeneous station passenger transfer between two lines. If the boarding station of the transfer in line 2 is added to line 1 or the alighting station of the transfer in line 1 is added to line 2, then the transfer distance can be reduced.

[0131] The specific implementation process can be divided into the following steps:

[0132] 1. Obtain transfer data information with a large transfer passenger flow:

[0133] Sort the transfer summary data by the transfer passenger flow quantity, obtain the transfer data with a transfer passenger flow greater than the set threshold and rank them by the transfer volume. The information includes the source line, source one-way trip, source station, target line, target one-way trip, target station, and transfer passenger flow.

[0134] 2. Obtain the passenger flow OD information at the one-way trip dimension.

[0135] According to the one-way trips and station data involved in the transfer in the first step, use these data as conditions to obtain the passenger flow OD information at the one-way trip dimension from the one-way trip dimension OD data table, including the one-way trip, departure station, and arrival station.

[0136] 3. Analyze whether a new line is needed based on transfer problems:

[0137] First, traverse the transfer pairs that may have problems obtained in the previous step. Then, for each transfer pair, look downwards to find whether there is a subsequent transfer pair for the target one-way trip as the transfer pair of the source one-way trip. If it exists, add it to the bottom of the transfer chain; then look for whether there is a subsequent transfer pair for the source one-way trip as the transfer pair of the target one-way trip. If it exists, insert it in front of this one-way trip pair to form a transfer chain. As Figure 9 shown, there is a passenger flow transfer at the station between one-way trips A and B, and there is a passenger flow transfer at the station between B and C, then a one-way transfer chain from A to B to C is formed.

[0138] Then, traverse the transfer chain, and form a list of stations that can be used to construct a new line according to the passenger flow of the transfer stations and the order of the stations before and after (as Figure 9 shown, it must be constructed according to the order of the stations before and after). Traverse these stations to calculate the average OD passenger flow of the stations (the average of the O passenger flow + D passenger flow of each station). Retain the stations with a passenger flow greater than the average OD passenger flow. If the remaining number of stations is greater than or equal to a set value such as 5, then construct a new line, and the new line includes these found stations. Then remove the transfer pairs corresponding to these stations from the transfer pair list obtained in the first step for the next line adjustment process.

[0139] 4. Analyze whether there is a transfer line adjustment based on transfer problems:

[0140] Traverse the remaining transfer pairs in step 3. If the IDs of the source station and the target station of the transfer pair are different, it is considered not a same-station transfer. At this time, calculate the distance between the source station and the target station. If the distance is within the set distance range (such as 100 to 1000 meters), then consider the transfer pair that needs to adjust the line and put it into the adjusted transfer pair array. If the transfer pair is from station AT of line A to station BT of line B, then it is considered that station BT can be added after station AT of line A or station AT can be added before station BT of line B. If AT or BT is the first or last station, it is considered that there is a line extension (first station extension or last station extension).

[0141] Finally, store the analyzed new line and the included station data, the adjusted line and the corresponding adjusted station data in the database and display them to the user through the problem analysis page. The user can make corresponding line adjustments and simulations based on this.

[0142] In an embodiment of the present invention, historical passenger flow data of multiple dimensions of each station on a bus line is obtained. According to the historical passenger flow data of multiple dimensions, the cross-section average passenger flow, high-position average passenger flow, and low-position average passenger flow of any dimension of each station are determined. According to the high-position average passenger flow and low-position average passenger flow of any dimension of each station, the station imbalance rate of any dimension of the bus line is determined, and the bus line with the station imbalance rate of any dimension greater than a preset threshold is determined as a problem line under any dimension. According to the cross-section passenger flow of each station of the problem line under any dimension, a passenger flow waveform diagram of the problem line under any dimension is constructed, and the peak and trough of the passenger flow waveform diagram are determined. According to the peak and trough of the passenger flow waveform diagram, the problem corresponding to the problem line is determined. By analyzing the boarding and alighting, cross-section passenger flow, OD passenger flow, and transfer passenger flow of bus line stations, the problem that the layout of line stations does not match the passenger flow is automatically discovered for the scenario, and adjustment and optimization suggestions are put forward, providing a means for automatically discovering problems in bus network optimization, effectively improving the problem discovery rate and reducing the analysis workload of network optimization personnel. By adjusting the network, the service level of the bus is effectively improved and the operation cost is reduced.

[0143] Based on the same technical concept, Figure 10 Exemplarily, the structure of a device for automatically discovering bus network problems provided by an embodiment of the present invention is shown. The device can execute the process of automatically discovering bus network problems.

[0144] As Figure 10 shown, the device specifically includes:

[0145] An acquisition unit 1001, configured to acquire historical passenger flow data of multiple dimensions of each station on a bus line;

[0146] A processing unit 1002, configured to determine the cross-section average passenger flow, high-position average passenger flow, and low-position average passenger flow of any dimension of each station according to the historical passenger flow data of multiple dimensions; determine the station imbalance rate of any dimension of the bus line according to the high-position average passenger flow and low-position average passenger flow of any dimension of each station; and determine the bus line with the station imbalance rate of any dimension greater than a preset threshold as the problem line under any dimension; construct a passenger flow waveform diagram of the problem line under any dimension according to the cross-section passenger flow of each station of the problem line under any dimension, and determine the peak and trough of the passenger flow waveform diagram; and determine the problem corresponding to the problem line according to the peak and trough of the passenger flow waveform diagram.

[0147] Optionally, the processing unit 1002 is specifically configured to:

[0148] For any one of the multiple dimensions, count the cross-sectional passenger flow in the historical passenger flow data of any dimension of each station, and determine the cross-sectional average passenger flow corresponding to any dimension of each station;

[0149] Count the cross-sectional passenger flow in any dimension of each station that is greater than the cross-sectional average passenger flow, and determine the high-level average passenger flow of any dimension of each station;

[0150] Count the cross-sectional passenger flow in any dimension of each station that is less than the cross-sectional average passenger flow, and determine the low-level average passenger flow of any dimension of each station.

[0151] Optionally, the processing unit 1002 is specifically configured to:

[0152] Determine whether the ratio of the high-level average passenger flow to the low-level average passenger flow is greater than the ratio threshold;

[0153] If so, determine the number of stations where the cross-sectional passenger flow in any dimension is above the high-level average passenger flow and the number of stations where the cross-sectional passenger flow in any dimension is below the low-level average passenger flow;

[0154] Determine the ratio of the number of stations where the cross-sectional passenger flow in any dimension is above the high-level average passenger flow and the number of stations where the cross-sectional passenger flow in any dimension is below the low-level average passenger flow to the total number of stations on the bus line as the station imbalance rate of any dimension of the bus line.

[0155] Optionally, the processing unit 1002 is specifically configured to:

[0156] According to the cross-sectional passenger flow of each station on the problem line in any dimension and the preset continuous average parameter, determine the continuous average value of each station on the problem line in any dimension;

[0157] Construct a passenger flow waveform diagram of the problem line in any dimension according to the continuous average value of each station on the problem line in any dimension;

[0158] If the continuous average value in the passenger flow waveform diagram of the problem line in any dimension is greater than the high-level average passenger flow, determine the peak, and determine the starting station of the peak as the station where the continuous average value is greater than the high-level average passenger flow, and determine the ending station of the peak as the station where the continuous average value is less than the high-level average passenger flow after the starting station of the peak;

[0159] If the continuous average value in the passenger flow waveform diagram of the problem line under any dimension is less than the low average passenger flow, a trough is determined, the station where the continuous average value is less than the low average passenger flow is determined as the starting station of the trough, and the station located after the starting station of the trough and with a continuous average value greater than the low average passenger flow is determined as the ending station of the trough.

[0160] Optionally, the processing unit 1002 is specifically configured to:

[0161] Determine the number of the first peak, the last peak, and the troughs between the first peak and the last peak in the passenger flow waveform diagram;

[0162] If no peak appears at a preset number of stations after the starting station of the problem line or at a preset number of stations before the ending station of the problem line, it is determined that the problem corresponding to the problem line is a one-way multi-sub-line problem;

[0163] If no peak appears at a preset number of stations after the starting station of the problem line and at a preset number of stations before the ending station of the problem line, it is determined that the problem corresponding to the problem line is a two-way multi-sub-line problem;

[0164] If the number of peaks of the problem line is greater than the number threshold, a suspected large station line is determined; according to the boarding passenger flow and alighting passenger flow of each station on the suspected large station line, the average boarding passenger flow and average alighting passenger flow of each station on the suspected large station line are determined, and according to the boarding passenger flow greater than the average boarding passenger flow, the high average boarding passenger flow is determined; according to the alighting passenger flow greater than the average alighting passenger flow, the high average alighting passenger flow is determined; if there is a station on the suspected large station line where the boarding passenger flow is greater than the high average boarding passenger flow and the alighting passenger flow is greater than the high average alighting passenger flow, it is determined that the problem of the suspected large station line is a large station passenger flow problem.

[0165] Optionally, the processing unit 1002 is further configured to:

[0166] After determining the problems corresponding to the problem line based on the peaks and valleys of the passenger flow waveform diagram, if the problems corresponding to the problem line are one-way multi-sub-line problems or two-way multi-sub-line problems, when it is determined that the sectional passenger flow of a preset number of stations after the starting station of the problem line or a preset number of stations before the ending station of the problem line is less than the low average passenger flow, determine that the problem line is a truncated line and determine the truncated station; when it is determined that the sectional passenger flow of a preset number of stations after the starting station of the problem line or a preset number of stations before the ending station of the problem line is greater than the low average passenger flow, determine that the problem line is a multi-section passenger flow line and determine the demarcation station;

[0167] If it is a large station passenger flow problem corresponding to the problem line, the stations where the boarding passenger flow is greater than the average value of the high boarding passenger flow and the alighting passenger flow is greater than the average value of the high alighting passenger flow are determined as large station sites.

[0168] Optionally, the processing unit 1002 is further configured to:

[0169] Obtain the transfer passenger flow data of the bus line;

[0170] Determine transfer pairs according to the transfer passenger flow data of the bus line, where the transfer pairs include source stations and target stations;

[0171] Traverse each transfer pair. Taking the source station of the starting transfer pair as the starting point of the transfer chain, determine whether there is a subsequent transfer pair as the transfer pair of the source one-way for the target station of the starting transfer pair. If so, add the subsequent transfer pair as the transfer pair of the source one-way to the bottom of the transfer chain; and determine whether there is a subsequent transfer pair as the transfer pair of the target one-way for the source one-way. If it exists, insert the subsequent transfer pair of the source one-way as the transfer pair of the target one-way in front of the transfer pair of the source one-way in the transfer chain;

[0172] Traverse the passenger flow of each transfer station and the order of each transfer station in the transfer chain to construct a station list of the new line;

[0173] If the IDs of the source station and the target station in the transfer chain are different, determine the distance between the source station and the target station. When it is determined that the distance is greater than the distance threshold, add the target station after the source station in the bus line where the source station is located, or add the source station before the target station in the bus line where the target station is located.

[0174] Based on the same technical concept, an embodiment of the present invention further provides a computing device, including:

[0175] A memory for storing program instructions;

[0176] A processor, configured to call program instructions stored in a memory and execute the above method for automatically discovering problems in a bus network according to the obtained program.

[0177] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable non-volatile storage medium, including computer-readable instructions, which, when read and executed by a computer, cause the computer to execute the above method for automatically discovering problems in a bus network.

[0178] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0179] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the specified functions in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0180] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the specified functions in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0181] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0182] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A method for automatically discovering problems in a bus network, characterized in that, Including: Obtaining historical passenger flow data of multiple dimensions for each station on a bus line; For any one of the multiple dimensions, statistically analyzing the sectional passenger flow in the historical passenger flow data of any one dimension for each station to determine the sectional average passenger flow corresponding to any one dimension of each station; Statistically analyzing the sectional passenger flow greater than the sectional average passenger flow in any one dimension of each station to determine the high-level average passenger flow of any one dimension of each station; Statistically analyzing the sectional passenger flow less than the sectional average passenger flow in any one dimension of each station to determine the low-level average passenger flow of any one dimension of each station; Determining whether the ratio of the high-level average passenger flow to the low-level average passenger flow is greater than a ratio threshold; If so, determining the number of stations where the sectional passenger flow is above the high-level average passenger flow and the number of stations where the sectional passenger flow is below the low-level average passenger flow in any one dimension; Determining the ratio of the number of stations where the sectional passenger flow is above the high-level average passenger flow and the number of stations where the sectional passenger flow is below the low-level average passenger flow in any one dimension to the total number of stations on the bus line as the station imbalance rate of any one dimension of the bus line; and determining the bus line with the station imbalance rate of any one dimension greater than a preset threshold as the problematic line in any one dimension; According to the sectional passenger flow of each station on the problematic line in any one dimension and a preset continuous average parameter, determining the continuous average value of each station on the problematic line in any one dimension; Constructing a passenger flow waveform diagram of the problematic line in any one dimension according to the continuous average value of each station on the problematic line in any one dimension; If the continuous average value in the passenger flow waveform diagram of the problematic line in any one dimension is greater than the average passenger flow, determining a peak, determining the station with the continuous average value greater than the high-level average passenger flow as the starting station of the peak, and determining the station after the starting station of the peak and with the continuous average value less than the high-level average passenger flow as the ending station of the peak; If the continuous average value in the passenger flow waveform diagram of the problematic line in any one dimension is less than the low-level average passenger flow, determining a trough, determining the station with the continuous average value less than the low-level average passenger flow as the starting station of the trough, and determining the station after the starting station of the trough and with the continuous average value greater than the low-level average passenger flow as the ending station of the trough; Determining the number of the first peak, the last peak, and the troughs between the first peak and the last peak in the passenger flow waveform diagram; If no peak appears at a preset number of stations after the starting station of the problematic line or at a preset number of stations before the ending station of the problematic line, determining that the problem corresponding to the problematic line is a one-way multi-sub-line problem; If no peak appears at a preset number of stations after the starting station of the problematic line and at a preset number of stations before the ending station of the problematic line, determining that the problem corresponding to the problematic line is a two-way multi-sub-line problem; If the number of peaks of the problematic line is greater than a number threshold, determining a suspected large-station line; Based on the boarding passenger flow and alighting passenger flow of each station on the suspected major station line, determine the average boarding passenger flow and average alighting passenger flow of each station on the suspected major station line, and determine the average high boarding passenger flow based on the boarding passenger flow greater than the average boarding passenger flow; determine the average high alighting passenger flow based on the alighting passenger flow greater than the average alighting passenger flow; if there is a station on the suspected major station line where the boarding passenger flow is greater than the average high boarding passenger flow and the alighting passenger flow is greater than the average high alighting passenger flow, then determine that the problem of the suspected major station line is the major station passenger flow problem.

2. The method according to claim 1, wherein The method further includes: If the problem corresponding to the problem line is a one-way multi-sub-line problem or a two-way multi-sub-line problem, when it is determined that the sectional passenger flow of a preset number of stations after the starting station of the problem line or a preset number of stations before the ending station of the problem line is less than the low average passenger flow, determine that the problem line is a truncated line and determine the truncated station; when it is determined that the sectional passenger flow of a preset number of stations after the starting station of the problem line or a preset number of stations before the ending station of the problem line is greater than the low average passenger flow, determine that the problem line is a multi-section passenger flow line and determine the boundary station; If it is a major station passenger flow problem corresponding to the problem line, the stations where the boarding passenger flow is greater than the average high boarding passenger flow and the alighting passenger flow is greater than the average high alighting passenger flow are determined as major stations.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Obtain the transfer passenger flow data of the bus line; Based on the transfer passenger flow data of the bus line, determine transfer pairs, where each transfer pair includes a source station and a target station; Traverse each transfer pair, with the starting transfer pair as the source station as the starting point of the transfer chain, determine whether there is a subsequent transfer pair as the transfer pair of the source one-way trip for the target station of the starting transfer pair. If so, add the subsequent transfer pair as the transfer pair of the source one-way trip to the bottom of the transfer chain; and determine whether there is a subsequent transfer pair as the transfer pair of the target one-way trip for the source one-way trip. If there is, insert the subsequent transfer pair of the source one-way trip as the transfer pair of the target one-way trip in front of the transfer pair of the source one-way trip in the transfer chain; Traverse the passenger flow of each transfer station and the order of each transfer station in the transfer chain to construct a list of stations for the new line; If the IDs of the source station and the target station in the transfer chain are different, determine the distance between the source station and the target station. When it is determined that the distance is greater than the distance threshold, add the target station after the source station in the bus line where the source station is located, or add the source station before the target station in the bus line where the target station is located.

4. An apparatus for automatically detecting problems in a bus network, characterized in that, For executing the method according to any one of claims 1 to 3, it includes: An acquisition unit for acquiring historical passenger flow data of multiple dimensions of each station of the bus line; A processing unit, configured to determine the cross-sectional average passenger flow, the high-level average passenger flow, and the low-level average passenger flow of any dimension of each station according to the historical passenger flow data of the multiple dimensions; determine the station imbalance rate of any dimension of the bus line according to the high-level average passenger flow and the low-level average passenger flow of any dimension of each station; and determine the bus line with the station imbalance rate of any dimension greater than a preset threshold as the problem line under any dimension; construct a passenger flow waveform diagram of the problem line under any dimension according to the cross-sectional passenger flows of the stations of the problem line under any dimension, and determine the peaks and valleys of the passenger flow waveform diagram; and determine the problem corresponding to the problem line according to the peaks and valleys of the passenger flow waveform diagram.

5. A computing device, characterized in that, Comprising: A memory, configured to store program instructions; A processor, configured to call the program instructions stored in the memory and execute the method according to any one of claims 1 to 3 according to the obtained program.

6. A computer-readable non-volatile storage medium, characterized in that, Comprising computer-readable instructions, when a computer reads and executes the computer-readable instructions, the computer is caused to execute the method according to any one of claims 1 to 3.

Images