Data processing method and related device applied to rail transit system

Abstract

The present application discloses a data processing method and related devices applied to rail transit systems, which determines the identification of a closed station after receiving station closure indication information, determines a detection target based on the identification of the closed station, and performs an abnormality test on the passenger flow data of the detection target to obtain a corresponding detection result. An affected cause analysis is performed on the affected inspection target, and the affected cause analysis is associated with the closed station identification. When a station is closed, the relevant impact caused by the station closure can be determined based on the closed station identification, and the corresponding traffic deployment strategy can be executed by obtaining the affected cause analysis associated with the closed station identification, thereby solving the problem in the related technology of lacking a corresponding control method for the traffic system based on the station closure information.

Description

Background Art

[0002] As transportation becomes more convenient, the number of transportation tools and routes increases. When large-scale meetings or important events are held, subways, buses and other transportation stations will be closed to avoid safety hazards such as crowds. With the current trend of increasing scale of rail transit networks, station closures are bound to lead to increased passenger flow at nearby stations and the need for some passengers to transfer to other means of transportation. In the prior art, there is a lack of a method for controlling the transportation system based on station closure information. Summary of the invention

[0003] The purpose of this application is to provide a data processing method for rail transit systems. By quantitatively analyzing the relevant data of closed stations, the possible impact of closed stations can be obtained, and then a traffic deployment strategy can be formulated based on the impact, thereby solving the problem in related technologies of lacking a corresponding control method for the traffic system based on closed station information.

[0004] In a first aspect, an embodiment of the present application provides a data processing method applied to a rail transit system, the method comprising:

[0005] In response to the station closure indication information, parsing the station closure identification from the station closure indication information;

[0006] Finding parameter information of the affected target object associated with the closed station identifier from the learned knowledge information;

[0007] Acquire and execute a traffic deployment strategy for the affected target object according to the parameter information of the affected target object;

[0008] The affected target objects are determined according to the following method:

[0009] Screening detection targets according to the station closure identification;

[0010] Acquire passenger flow data corresponding to the detection target;

[0011] Performing abnormality detection on the detection target according to the passenger flow data of the detection target to obtain a detection result;

[0012] If the detection result indicates that the detection target is an abnormal point, the detection target is determined to be the affected target object.

[0013] In a second aspect, an embodiment of the present application provides a data processing device applied to a rail transit system, the device comprising:

[0014] A station identification module, configured to respond to the station closure indication information and parse the station closure indication information to obtain a station closure identification;

[0015] A parameter information confirmation module, used to search for parameter information of an affected target object associated with the closed station identifier from the learned knowledge information;

[0016] A deployment strategy confirmation module, used to obtain and execute a traffic deployment strategy for the affected target object according to the parameter information of the affected target object;

[0017] The affected target objects are determined according to the following method:

[0018] Screening detection targets according to the station closure identification;

[0019] Acquire passenger flow data corresponding to the detection target;

[0020] Performing abnormality detection on the detection target according to the passenger flow data of the detection target to obtain a detection result;

[0021] If the detection result indicates that the detection target is an abnormal point, the detection target is determined to be the affected target object.

[0022] In the third aspect, another embodiment of the present application also provides an electronic device, comprising at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any data processing method provided in the embodiments of the present application for application to a rail transit system.

[0023] In a fourth aspect, another embodiment of the present application further provides a computer storage medium, wherein the computer storage medium stores a computer program, and the computer program is used to enable a computer to execute any data processing method applied to a rail transit system provided in an embodiment of the present application.

[0024] In the embodiment of the present application, after receiving the station closure indication information, the station closure mark is determined. The detection target is determined according to the mark of the station closure, and the passenger flow data of the detection target is tested for abnormality to obtain the corresponding detection result. By identifying the detection result, the detection target determined as the abnormal point is obtained. The relevant impact caused by the station closure is obtained by determining the detection target as the abnormal point, and the corresponding traffic deployment strategy is executed according to the obtained relevant impact, so as to provide effective data for intelligent traffic control.

[0025] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. Obviously, the drawings introduced below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a schematic diagram of an application environment according to an embodiment of the present application;

[0028] Figure 2a An overall flow chart provided according to an embodiment of the present application;

[0029] Figure 2b A schematic diagram of abnormal passenger flow at an affected station according to an embodiment of the present application;

[0030] Figure 3a The following is an overall flow chart of abnormality inspection for affected stations according to one embodiment of the present application;

[0031] Figure 3b The following is an overall flow chart of abnormality checking for affected paths according to one embodiment of the present application;

[0032] Figure 4 A flow chart of a data processing device applied to a rail transit system according to an embodiment of the present disclosure;

[0033] Figure 5 The figure is a structural diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0034] The technical solutions in the embodiments of the present application will be described clearly and in detail below in conjunction with the accompanying drawings. In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in the text is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, in the description of the embodiments of the present application, "multiple" means two or more than two.

[0035] In the description of the embodiments of the present application, unless otherwise specified, the term "multiple" refers to two or more, and other quantifiers are similar and should be understood. The preferred embodiments described herein are only used to illustrate and explain the present application, and are not used to limit the present application. In addition, the embodiments of the present application and the features therein may be combined with each other if there is no conflict.

[0036] To further illustrate the technical solution provided by the embodiment of the present application, this is described in detail below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiment of the present application provides the method operation steps as shown in the following embodiments or drawings, more or fewer operation steps may be included in the method based on routine or no creative labor. In the steps where there is no necessary causal relationship logically, the execution order of these steps is not limited to the execution order provided by the embodiment of the present application. The method can be executed in the order of the method shown in the embodiment or drawings or in parallel during the actual processing process or when the control device is executed.

[0037] The inventive concept of the present application is: determine the detection target for the station closure mark, and the detection target is selected according to the location of the station closure in the road network and various traffic routes. By checking the abnormality of the passenger flow data in the detection target, it can be obtained whether the detection target will be affected by the closure of the station. When the abnormality check is performed on the passenger flow data in the detection target, the historical AFC data (Automatic Fare Collection System, urban rail transit automatic ticket collection system) of the detection target and the corresponding station closure data are analyzed to obtain the test result of whether the inspection target will be affected by the closure of the station. The affected cause analysis is performed for the affected inspection target, and the affected cause analysis is associated with the station closure mark. So that when the station is closed, the relevant impact that the station closure will cause can be determined according to the station closure mark, and the corresponding traffic deployment strategy is executed by obtaining the affected cause analysis associated with the station closure mark, thereby reducing the adverse effects that may be caused by the station closure.

[0038] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or be understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the written description, claims, and drawings.

[0039] The data processing method applied to the rail transit system in the embodiment of the present application is described in detail below with reference to the accompanying drawings.

[0040] See also Figure 1 , is a schematic diagram of an application environment according to an embodiment of the present application.

[0041] like Figure 1 As shown, the application environment may include, for example, a network 10 , a server 20 , at least one terminal device 30 , and a database 40 .

[0042] The server 20 is used to provide the operation time information of the transportation means, and the transportation means may be public transportation means such as subways, buses, light rails, ferries, etc., or non-public transportation means such as corporate shuttle buses and flights. The server 20 may be a control server for various types of transportation means, and the estimated departure time of each shift of transportation means can be scheduled through the server 20. When each shift of transportation means departs on time, the server 20 records the estimated departure time of each shift of transportation means in the database 40 through the network 10.

[0043] In addition, the server 20 can also be a master control server for issuing instructions to each station in the traffic network. When the server 20 receives the instruction information of the closure of station A in the subway line, the identification of the closed station is parsed from the instruction information. According to the identification, the cause analysis of the affected stations and affected routes associated with the closure station identification is searched in the database 20 through the network 10. The traffic deployment strategy corresponding to the cause analysis is distributed to at least one terminal device 30 through the network 10. Among them, the terminal device 30 can be a communication device of some affected stations, such as a mobile phone, a laptop computer, etc.

[0044] Figure 2a A schematic flow chart of a data processing method applied to a rail transit system provided by an embodiment of the present application is shown, including:

[0045] Step 201: In response to station closure indication information, parse the station closure identification from the station closure indication information.

[0046] Step 202: Searching for parameter information of the affected target object associated with the closed station identifier from the learned knowledge information.

[0047] Step 203: acquiring and executing a traffic deployment strategy for the affected target object according to the parameter information of the affected target object;

[0048] The affected target objects are determined according to the following method:

[0049] Screening detection targets according to the station closure identification;

[0050] Acquire passenger flow data corresponding to the detection target;

[0051] Performing abnormality detection on the detection target according to the passenger flow data of the detection target to obtain a detection result;

[0052] If the detection result indicates that the detection target is an abnormal point, the detection target is determined to be the affected target object.

[0053] When analyzing the impact of a closed station, it is first necessary to determine the target objects affected by the closure. Since each station in the transportation network is fixed (that is, each route in the network is fixed, and passenger flow can only flow along fixed routes in the network unless transferring to other means of transportation), if a station in the transportation network is closed, passengers who want to reach their destination without transferring to other means of transportation can only choose the nearest station or transfer to other routes that can reach their destination. Therefore, when a station is closed, the nearest station of the closed station and the station corresponding to the route with the closed station as a transfer station will be affected by effects such as a sharp increase in passenger flow. Through the above analysis, it can be determined that the target objects affected by the station closure can be divided into affected stations and affected routes. The following will explain how to determine the affected stations and related parameter information, and how to determine the affected routes and related parameter information, which specifically include the following two parts:

[0054] Part 1: Identify the affected stations and related parameter information

[0055] Other stations in the transportation network where the closed station is located are selected as target stations for detection. By performing an abnormal analysis on the passenger flow data of the target station, it is determined whether the station corresponding to the detection target is affected by the station closure, and then the stations affected by the station closure are determined.

[0056] After determining that the detection target is the target station, this application uses an anomaly detection algorithm to calculate the historical passenger flow and the passenger flow to be tested of the target station, and uses the historical passenger flow data to perform an abnormal point test on the passenger flow data to determine whether the passenger flow to be tested is an abnormal point. If the passenger flow to be tested is an abnormal point, it means that there is a large abnormality in the passenger flow data of the target station before and after the station closure, that is, the target station is affected by the station closure and is an affected station. Among them, the historical passenger flow is expressed as the number of people entering and leaving the target station within a specified time period before the station closure, and the passenger flow to be tested is expressed as the number of people entering and leaving the target station within a specified time period after the station closure.

[0057] The inventors considered that among many anomaly detection algorithms, the Grubbs criterion algorithm has the characteristic of assuming that the data follows a normal distribution and is suitable for detecting abnormal data when the data volume is small. Therefore, the Grubbs criterion algorithm can be used to calculate the historical passenger flow and the passenger flow to be tested of the target station. When implemented, the historical passenger flow data and the passenger flow data to be tested can be input into the Grubbs criterion formula as sample data. If the obtained sample residual is not less than the critical value, the sample data is determined to be abnormal data. The Grubbs criterion formula is shown in the following formula (1):

[0058]

[0059] Among them, V i represents the sample residual; X i Represents sample data; represents the sample mean; σ(x) represents the sample standard deviation; g(n,a) represents the critical value, which can be determined from the critical value table of the Grubbs criterion through n and α; n is the number of samples; α is the risk value, which is a preset value, usually preset to 0.01 or 0.05. Of course, it can be set according to actual conditions during specific implementation.

[0060] In order to understand how to determine outliers through the Grubbs criterion algorithm, the number of people entering the target station is explained. For example, the number of people entering the target station in the specified time period 5 days before the station closure is 82, 78, 80, 79, and 76 respectively. The number of people entering the target station in the specified time period after the station closure is 91. Among them, α is preset to 0.05. From the above data, it can be seen that X in the Grubbs criterion formula i =91; V i =91-81=10; σ(x)=5.3; n=6; According to n=6, α=0.05, we can find g(n,a)=1.82 by searching the critical value table; Since V i =10, g(n,a)×σ(x)=1.82×5.3=9.646, so V i >g(n,a)×σ(x), that is, the number of people to be tested is 91, which is abnormal data, and the target station is a station affected by the closure.

[0061] The inventors also considered that according to the normal distribution theory, The probability is about 99.7%. Therefore, according to the Laida criterion algorithm, the historical passenger flow data and the passenger flow data to be tested are input as sample data into the Laida criterion formula. If the obtained sample residual is greater than 3σ, the sample data is determined to be abnormal data. The Laida formula is shown in the following formula (2):

[0062]

[0063] Among them, V i represents the sample residual; X i Represents sample data; represents the sample mean; σ(x) represents the sample standard deviation.

[0064] In order to understand how to determine outliers through the Grubbs criterion algorithm, the number of people entering the target station is explained. For example, it is determined that the number of people entering the target station in the specified time period 3 days before the station closure is 8, 7, and 9 respectively, and the number of people entering the target station in the specified time period after the station closure is 100. From the above data, it can be seen that X in the Laida criterion formula i =100; σ(x)=13.6;Since V i =51, 3×σ(x)=40.8, so V i >3σ, that is, the number of people to be tested is 100, which is abnormal data, and the target station is a station affected by the closure.

[0065] In addition, since the passenger flow of the target station also satisfies the Poisson distribution, the Poisson distribution-based anomaly test algorithm can be used to determine whether the passenger flow to be tested at the target station is abnormal. Poisson distribution is a discrete probability distribution. If the passenger flow of the target station before and after the station closure is not abnormal, the passenger flow data corresponding to the station closure before and after the station closure should satisfy the same distribution, and hypothesis testing is performed based on this. Among them, the basic idea of ​​hypothesis testing is the idea of ​​small probability proof by contradiction. The idea of ​​small probability means that small probability events (P<0.01 or P<0.05) basically will not occur in a single test. The idea of ​​proof by contradiction is to first propose a hypothesis, and then use appropriate statistical methods to determine the probability of the hypothesis being true, and then determine whether the hypothesis is true based on the probability. The Poisson distribution formula is shown in the following formula (3):

[0066]

[0067] Among them, P represents probability; K represents expected result; λ≈sample mean.

[0068] After determining the anomaly detection algorithm for the target station, in order to ensure the accuracy of the test results, based on the basic principle of ensemble learning (establishing multiple base learners and combining them with a certain strategy to obtain more accurate results), at least two of the above three anomaly detection algorithms are used as base learners to perform anomaly detection on the relevant data of the target station, and the test results are verified by voting to obtain the final conclusion of whether the target station is an affected station. Among them, when the voting method is verified for the test results, if the majority of the test results of the three base learners are affected stations, the target station is determined to be an affected station. If two base learners are taken, multiple groups of data in different specified time periods are selected for testing. After the test results are divided into abnormal and non-abnormal categories, the category with the largest number is selected as the final test result.

[0069] Based on the combination of base learners and voting methods, the target station is detected for anomalies, and after the affected stations are determined, the parameter information of the affected stations is obtained by performing anomaly analysis on the relevant data in the anomaly detection process. In order to facilitate understanding of how to obtain the parameter information of the affected stations, the relevant data of a specific station closure is used for explanation.

[0070] From the first train on September 1 (Saturday) to 17:00 on September 3 (Monday), the Olympic Park Station on Line 8 and Line 15 will be closed. During the closure period, trains can pass through the station, but are not allowed to stop. The number of people entering the station during the morning peak hours (7:00-9:00) on weekdays from June to August is used as the historical passenger flow data, and the number of people entering the station during the morning peak hours on September 3 is used as the passenger flow data to be detected. Anomaly detection is performed, and the abnormal entry volume recognition results are shown in Table 1;

[0071] Table 1. Abnormal station entry volume recognition results

[0072]

[0073]

[0074] From the data in Table 1, we can see that due to the closure of the Olympic Park Station, the number of inbound stations adjacent to it has changed. Among them, according to the deviation rate, the number of inbound stations at the South Gate of the Forest Park has increased the most. Next, the historical number of outbound stations and the number of outbound stations to be tested in the same time period of the target station are detected for anomalies, and the abnormal outbound volume recognition results are shown in Table 2;

[0075] Table 2 Abnormal station entry volume recognition results

[0076]

[0077] By analyzing the data in Table 2 from the perspective of exit volume, it is found that the exit volume at the south gate of Forest Park still changes the most during the morning peak period. Further analysis shows that the number of exits at the Olympic Park decreased by 13,427, and the total increase in the number of exits at the stations around the Olympic Park was 8,352. The reduction in the number of people entering the station was 37.8%, indicating that the closure of the station caused 37.8% of the travel demand to give up traveling or change to other means of transportation, and the remaining travel demand was allocated to the surrounding stations. At the same time, due to the closure of the transfer station, the passenger flow of the transfer stations around the station that can transfer through other lines increased, and the number of entrances and exits also increased accordingly.

[0078] The abnormal inbound volume and abnormal outbound volume are further combined, such as Figure 2bAs shown in the figure, it can be seen that the affected stations are all on the same line as the closed station and are adjacent stations, with no more than 2 adjacent stations, and are basically within 3km around the closed station. Therefore, when the station is closed, it is necessary to adjust the number of staff on duty at the affected station in a timely manner, and take countermeasures such as adding ticket gates and limiting the number of people entering the station.

[0079] In a possible embodiment, if the affected target object is an affected station, the parameter information associated with the affected station includes: the number of employees on duty, the employee duty schedule, and traffic control equipment of the affected station.

[0080] Part 2: Determine the affected paths and related parameter information

[0081] After determining that the affected target object is the affected path, in order to ensure the accuracy of the anomaly detection, the passenger flow data when the passenger flow flows between the closed station and a certain station should be obtained. Among the various traffic routes in the traffic network where the closed station is located, select the closed station as any one of the departure, destination and transfer stations in the traffic route. When the closed station is the departure or destination of the route, the route is used as the target path. When the closed station is used as the transfer station of the route, the route from the departure point to the closed station of the route is used as the target path, and the route from the closed station to the destination of the route is used as the target path.

[0082] In addition, the inventors found that in the affected path, the main transformation parameters should include travel time (the time spent passing the target path) in addition to passenger flow. Due to the regularity of passenger flow in the traffic network (stations are fixed, and passenger flow follows a fixed trajectory unless transferring to other means of transportation), when determining whether the target path is an affected path, it can be further transformed into the identification of abnormal passenger flow and abnormal travel time of the target path.

[0083] When identifying abnormal passenger flow, an abnormal detection algorithm is used to calculate the historical passenger flow and the passenger flow to be tested of the target station, and the abnormal point detection is performed on the passenger flow data to be tested through the historical passenger flow data to determine whether the passenger flow to be tested is an abnormal point. If the passenger flow to be tested is an abnormal point, it means that there is a large abnormality in the passenger flow data of the target station before and after the station closure, that is, the target station is affected by the station closure and is an affected station. Among them, the historical passenger flow represents the number of people passing through the target path within a specified time period before the station closure, and the passenger flow to be tested represents the number of people passing through the target path within a specified time period after the station closure. In specific implementation, the historical passenger flow and the passenger flow to be tested of the target path can be input into the base learner based on the Grubbs criterion, the Laida criterion and the Poisson distribution anomaly detection algorithm, and the voting method is used to determine whether the target path is an affected path.

[0084] When identifying abnormal travel time, the historical travel time is determined by the historical passenger flow of the target station, and the travel time to be tested is determined by the passenger flow to be tested of the target station. The historical travel time is represented by the time it takes for the passenger flow to pass through the target path within a specified time period before the station is closed. The travel time to be tested is represented by the time it takes for the passenger flow to pass through the target path within a specified time period after the station is closed.

[0085] When selecting anomaly detection algorithms for the historical travel time data and the travel time data to be tested of the target path, since the Mann-Whitney rank sum test algorithm is suitable for testing whether two independent samples have significant differences, its test principle is to establish a hypothesis. If the hypothesis is established, the two samples are merged and assigned to the corresponding level of each data according to the size. Then the sample data will be randomly distributed on the level sequence. After the sample data levels are accumulated, the sum of the two samples should be similar or the same. Therefore, this algorithm can be used to detect anomalies on the target path. In addition, the anomaly detection methods similar to the Mann-Whitney rank sum test algorithm include the independent sample T test algorithm and the Wilcoxon rank sum test algorithm. The general processes of the above three algorithms are similar, and they are all attached with a critical value table. By testing the difference between the two groups of sample data, a hypothesis is first established. Then the historical travel time data of the target path and the travel time data to be tested are used as two groups of sample data, and the corresponding statistical values ​​are obtained according to the formula corresponding to the anomaly detection algorithm. Finally, the statistical value is compared with the critical value in the attached table to determine whether the original hypothesis is established. In order to facilitate the understanding of the general process of the above three algorithms, the Mann-Whitney rank sum test algorithm is used as an example to illustrate:

[0086] During implementation, the historical travel time data and the distribution of the travel time data to be tested are input into the Mann-Whitney rank sum test formula as sample data. If the obtained sample statistic is greater than the critical value, the hypothesis is determined to be established. The Mann-Whitney rank sum test formula is shown in the following formula (4):

[0087]

[0088] Among them, U is the sample statistic; R is the sample rank; n is the number of samples.

[0089] For example, it is determined that the travel time of the target path in the specified time period three days before the station closure is 23 minutes, 24 minutes and 25 minutes. After the station closure, the three travel times of the target path in the specified time period are 47 minutes, 48 ​​minutes and 49 minutes; if the assumption is that there is no significant difference in travel time before and after the station closure and α is preset to 0.05, then from the above data, it can be seen that R1 in the Mann-Whitney rank sum test formula is the rank sum of 23, 24, and 25, that is, R1=1+2+3=6, and the corresponding R2=15; n1=n2=3; U1=3×3+3×4 / 2-6=9; when α=0.05, n1=3, and n2=3, query the appendix of the Mann-Whitney rank sum test to obtain U α . If U α ≥U1, the established hypothesis is not valid, that is, the travel time to be tested is abnormal data, and the target path is an affected path.

[0090] In a possible embodiment, a base learner is established based on the Mann-Whitney rank sum test algorithm, the independent sample T test algorithm, and the Wilcoxon rank sum test algorithm, and a voting method is used to vote on the test results to obtain a final test result of whether the target path is an affected path.

[0091] Based on the combination of base learners and voting methods, the passenger flow and travel time in the target path are detected for anomalies, and after the affected path is determined, the parameter information of the affected path is obtained by performing anomaly analysis on the relevant data in the anomaly detection process. In order to facilitate understanding of how to obtain the parameter information of the affected path, the closure of the Olympic Park Station from September 1 to 3 (Saturday to Monday) in Part 1 is used as an example for explanation.

[0092] Based on the AFC data of the morning rush hour on weekdays in the past two months before the station closure, the historical passenger flow data of the target road and the passenger flow data to be detected during the morning rush hour on September 3 were counted, and the abnormal passenger flow distribution was identified based on the base learner. In addition, since the passenger flow characteristics of the Monday morning rush hour are different from those of the morning rush hours on other weekdays, the historical travel time data of the morning rush hour on all Mondays in the past two months and the travel time data to be detected during the morning rush hour on September 3 should be selected, and the abnormal travel time distribution should be identified based on the base learner. After sorting the relevant data after identification, the number of affected paths is obtained. The details are shown in Table 3;

[0093] Table 3. Affected path identification results

[0094]

[0095] Through the data analysis in Table 3, it is found that among the unscreened possible affected paths, some paths have very little passenger flow for a long time, which is quite different from the results after screening. In addition, by comparing the affected paths with only abnormal passenger flow with the total number of paths, it is found that the number of reduced passenger flow is relatively constant. By comparing the affected paths with only abnormal travel time with the total number of paths, it is found that the affected paths with only abnormal travel time and the proportion of affected paths are positively correlated with passenger flow. The above analysis is used to formulate parameter information associated with the affected paths.

[0096] In one possible embodiment, if the affected target object is an affected path, when the station is a transfer station, the passenger flow on the affected path moves to the station within a preset range based on the closed station. When the closed station is a transfer station, and the time taken to complete the journey in the target path by other means is greater than the preset time, there is no path with a similar travel time to the target path. When the closed station is a transfer station, and the closed station is the only departure or destination in the target path, the passenger flow will choose other travel methods or give up traveling due to the closure of the station.

[0097] After obtaining the affected target object and the parameter information associated with the affected target object through the relevant anomaly detection method in Part 1 and Part 2, the relevant information is stored. In order to find the corresponding affected target object and parameter information through the identification information of the closed station when a station is closed, and execute the corresponding traffic deployment strategy for the affected target object according to the parameter information.

[0098] After the overall introduction of the data processing method provided by the present application for the rail transit system, in order to facilitate understanding of how the present application determines whether the target station is an affected station, the present application also presents an abnormality detection algorithm flow for the target station related data, as shown in the following figure. Figure 3a As shown, the following steps are included:

[0099] In step 301a, the historical passenger flow and the passenger flow to be tested of the target station in a specified time period are obtained through the AFC system, and then the historical passenger flow data and the passenger flow data to be tested are respectively input into the base learners constructed based on the Grubbs criterion, the Dayla criterion and the Poisson distribution anomaly detection algorithm.

[0100] In step 302a, a test result of whether the target station is an affected station is obtained by using a base learner constructed using the Grubbs criterion, the Dayla criterion, and a Poisson distribution anomaly test algorithm.

[0101] In step 303a, a voting method is performed on the inspection result, and a final result of whether the target station is an affected station is determined according to the voting method.

[0102] In addition, the present application also presents a process of anomaly detection method for target path related data, as shown in the following example: Figure 3b As shown, the following steps are included:

[0103] Since the determination of the affected path is divided into the identification of abnormal passenger flow in the target path and the identification of abnormal travel time in the target path, when the abnormal passenger flow in the target path is identified, step 301b is executed to obtain the historical passenger flow and the passenger flow to be tested of the target path in the specified time period through the AFC system, and then the historical passenger flow data and the passenger flow data to be tested are respectively input into the base learner constructed by the Grubbs criterion, the Dayla criterion and the Poisson distribution anomaly detection algorithm.

[0104] Then, step 302b is executed to obtain a test result of whether the target path is an affected path by using a base learner constructed based on the Grubbs criterion, the Dayla criterion, and the Poisson distribution anomaly test algorithm.

[0105] After the test result is obtained, step 303b is executed to perform a voting method on the test result to determine whether the target path is the final result of the affected path.

[0106] When the travel time anomaly in the target path is identified, the historical passenger flow of the target path within the specified time period and the historical travel time and the travel time to be tested corresponding to the passenger flow to be tested are obtained, and then step 304b is executed to input the historical travel time data and the travel time data to be tested into the base learner constructed by the Mann-Whitney rank sum test algorithm, the independent sample T test algorithm and the Wilcoxon rank sum test algorithm respectively.

[0107] Then, step 305b is executed to obtain a test result of whether the target path is an affected path by using base learners constructed by the Mann-Whitney rank sum test algorithm, the independent sample T test algorithm, and the Wilcoxon rank sum test algorithm.

[0108] After the test result is obtained, step 306b is executed to perform a voting method on the test result to determine whether the target path is the final result of the affected path.

[0109] Based on the same inventive concept, the present application also provides a data processing device 400 applied to a rail transit system, such as Figure 4 As shown, the device comprises:

[0110] The station identification module 401 is used to parse the station identification from the station closure indication information in response to the station closure indication information;

[0111] The parameter information confirmation module 402 is used to search the parameter information of the affected target object associated with the closed station identification from the learned knowledge information;

[0112] A deployment strategy confirmation module 403 is used to obtain and execute a traffic deployment strategy for the affected target object according to the parameter information of the affected target object;

[0113] The affected target objects are determined according to the following method:

[0114] Screening detection targets according to the station closure identification;

[0115] Acquire passenger flow data corresponding to the detection target;

[0116] Performing abnormality detection on the detection target according to the passenger flow data of the detection target to obtain a detection result;

[0117] If the detection result indicates that the detection target is an abnormal point, the detection target is determined to be the affected target object.

[0118] In a possible embodiment, the detection target includes a target station and a target path;

[0119] The target path includes any one of the following three target paths:

[0120] The path between the station and the closed station is used as the target path; wherein the closed station is used as the departure point or destination of the target path;

[0121] When the closed station serves as a transfer station in the total route, the path from the departure point of the total route to the closed station is used as the target path, and the path from the closed station to the destination of the total route is used as the target path.

[0122] In a possible embodiment, the deployment strategy confirmation module includes:

[0123] A first data acquisition unit is used for acquiring a first historical passenger flow and a first passenger flow to be checked of the target station within a first specified time period if the detection target is the target station; wherein the first historical passenger flow is used to express the first passenger flow of the target station within the first specified time period before the station is closed, and the first passenger flow to be checked is used to express the first passenger flow of the target station within the first specified time period after the station is closed, wherein the first passenger flow is data on the number of people entering the station or data on the number of people leaving the station;

[0124] A first inspection result confirmation unit, configured to perform a first abnormal point inspection on the first passenger flow to be inspected by using the first historical passenger flow to obtain a first inspection result;

[0125] The first target object confirmation unit is used to determine the target station as the affected target object if the first inspection result indicates that the first passenger flow to be inspected is an abnormal point.

[0126] In a possible embodiment, the first inspection result confirmation unit performs a first abnormal point inspection on the first passenger flow to be inspected through the first historical passenger flow, and when obtaining a first inspection result, is configured as follows:

[0127] Taking the first historical passenger flow and the first passenger flow to be tested as sample data, a plurality of abnormal point detection methods are respectively used to perform abnormality detection on the sample data to obtain detection results corresponding to each abnormal point detection method; wherein the plurality of abnormal point detection methods include at least two of the Grubbs criterion, the Laida criterion, and an abnormality method based on Poisson distribution;

[0128] The detection results corresponding to the anomaly detection methods are voted on using a voting method to obtain a final detection result of whether the first passenger flow to be tested is the anomaly point.

[0129] In a possible embodiment, the deployment strategy confirmation module includes:

[0130] a second data acquisition unit, for acquiring a second historical passenger flow and a second passenger flow to be checked of the target path within a specified time period if the detection target is the target path; wherein the second historical passenger flow is used to express a second passenger flow with the closed station as the departure point or the destination of the target path within a second specified time period before the station is closed, and the passenger flow to be checked is used to express a second passenger flow with the closed station as the departure point or the destination of the target path within the second specified time period after the station is closed, wherein the second passenger flow is data on the number of people passing through the target path;

[0131] A second inspection result confirmation unit, configured to perform the abnormal point inspection on the second passenger flow to be inspected by using the second historical passenger flow to obtain a second inspection result;

[0132] The second target object confirmation unit is used to determine the station corresponding to the second passenger flow to be inspected as the affected target object if the second inspection result indicates that the second passenger flow to be inspected is the abnormal point.

[0133] In a possible embodiment, the second inspection result confirmation unit performs a second abnormal point inspection on the second passenger flow to be inspected through the second historical passenger flow, and when obtaining the second inspection result, is configured as follows:

[0134] The second historical passenger flow and the second passenger flow to be tested are used as sample data, and a plurality of abnormal point detection methods are respectively used to perform abnormality detection on the sample data to obtain detection results corresponding to each abnormality detection method; wherein the plurality of abnormal point detection methods include at least two of the Grubbs criterion, the Laida criterion, and a Poisson distribution-based abnormality method;

[0135] The detection results corresponding to the anomaly detection methods are voted on using a voting method to obtain a final detection result of whether the second passenger flow to be tested is the anomaly point.

[0136] In a possible embodiment, the deployment strategy confirmation module further includes:

[0137] a third data acquisition unit, configured to determine historical travel time data and to-be-checked travel time data according to the second historical passenger flow and the second to-be-checked passenger flow; wherein the historical travel time data is the time required for the second passenger flow corresponding to the second historical passenger flow to pass through the target path, and the to-be-checked travel time data is the time required for the second passenger flow corresponding to the second to-be-checked passenger flow to pass through the target path;

[0138] A third inspection result confirmation unit, configured to perform the abnormal point inspection on the to-be-inspected travel time data through the historical travel time data to obtain a third inspection result;

[0139] The third target object confirmation unit is used to determine the station corresponding to the travel data to be checked as the affected target object if the third inspection result indicates that the travel data to be checked is the abnormal point.

[0140] In a possible embodiment, the third inspection result confirmation unit performs the abnormal point inspection on the to-be-inspected travel time data through the historical travel time data, and when obtaining the third inspection result, is configured as follows:

[0141] The historical travel time data and the to-be-tested travel time data are used as sample data, and a plurality of outlier detection methods are respectively used to perform anomaly detection on the sample data to obtain detection results corresponding to the anomaly detection methods; wherein the plurality of outlier detection methods include at least two of an independent sample T test, a Mann-Whitney rank sum test, and a Wilcoxon signed rank test;

[0142] The detection results corresponding to the anomaly detection methods are voted on using a voting method to obtain a final detection result of whether the travel time data to be tested is the anomaly point.

[0143] In a possible embodiment, when the affected target object is an affected path, the station type of the closed station for the affected path includes a first type and a second type; wherein the first type indicates that the closed station is the departure point or destination of the target path, and the second type indicates that the closed station is a transfer station in the target path;

[0144] The parameter information of the affected path includes:

[0145] When the closed station is of the first type, only the affected path is inaccessible;

[0146] When the closed station is of the second type, the passenger flow on the affected route is transferred to stations within a preset range based on the closed station;

[0147] When the closed station is of the second type, and the time taken to complete the journey on the target path by other means is greater than the preset time, there is no path with a travel time close to that of the target path;

[0148] When the closed station is of the second type and the closed station is the only departure point or destination in the target route, the user is affected by the closure of the station and chooses other travel modes or gives up traveling;

[0149] If the affected target object is an affected station, the parameter information includes at least one of the following parameters of the affected station: the number of employees on duty, the employee duty roster, and traffic control equipment.

[0150] After introducing the data processing method and device applied to the rail transit system according to the exemplary embodiment of the present application, next, an electronic device according to another exemplary embodiment of the present application is introduced.

[0151] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0152] In some possible implementations, the electronic device according to the present application may include at least one processor and at least one memory. The memory stores program code, and when the program code is executed by the processor, the processor executes the steps of the data processing method applied to the rail transit system according to various exemplary embodiments of the present application described above in this specification. For example, the processor may execute the steps in the data processing method applied to the rail transit system.

[0153] Refer to the following Figure 5 The electronic device 130 according to this embodiment of the present application is described. Figure 5 The electronic device 130 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0154] like Figure 5 As shown, the electronic device 130 is in the form of a general electronic device. The components of the electronic device 130 may include but are not limited to: the at least one processor 131, the at least one memory 132, and a bus 133 connecting different system components (including the memory 132 and the processor 131).

[0155] Bus 133 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a processor, or a local bus using any of a variety of bus architectures.

[0156] The memory 132 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 1321 and / or a cache memory 1322 , and may further include a read-only memory (ROM) 1323 .

[0157] The memory 132 may also include a program / utility 1325 having a set (at least one) of program modules 1324, such program modules 1324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0158] The electronic device 130 may also communicate with one or more external devices 134 (e.g., keyboards, pointing devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 130, and / or communicate with any device that enables the electronic device 130 to communicate with one or more other electronic devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 135. Furthermore, the electronic device 130 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 136. As shown, the network adapter 136 communicates with other modules for the electronic device 130 via a bus 133. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 130, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0159] In some possible implementations, various aspects of a data processing method applied to a rail transit system provided by the present application may also be implemented in the form of a program product, which includes a program code. When the program product runs on a computer device, the program code is used to enable the computer device to execute the steps of data processing applied to a rail transit system according to various exemplary embodiments of the present application described above in this specification.

[0160] The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0161] The program product for data processing applied to rail transit systems of the embodiments of the present application may adopt a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on electronic devices. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0162] The readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0163] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0164] The program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user electronic device, partially on the user device, as an independent software package, partially on the user electronic device and partially on the remote electronic device, or entirely on the remote electronic device or server. In the case of a remote electronic device, the remote electronic device can be connected to the user electronic device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external electronic device (for example, using an Internet service provider to connect through the Internet).

[0165] It should be noted that, although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into multiple units to be embodied.

[0166] In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0167] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0168] The present application is described with reference to the flowcharts and block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and block diagram, as well as the combination of the processes and boxes in the flowchart and block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and block diagram. Figure 1 Process or multiple processes and boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0169] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 Process or multiple processes and boxes Figure 1 A function specified in one or more boxes.

[0170] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 Process or multiple processes and boxes Figure 1 The steps for the functions specified in one or more boxes.

[0171] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0172] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A data processing method applied to a rail transit system, characterized in that: The method comprises: In response to the station closure indication information, parsing the station closure identification from the station closure indication information; Finding parameter information of the affected target object associated with the closed station identifier from the learned knowledge information; Acquire and execute a traffic deployment strategy for the affected target object according to the parameter information of the affected target object; The affected target objects are determined according to the following method: According to the station closure mark, screening detection targets and obtaining passenger flow data corresponding to the detection targets; the detection targets include target stations and target routes; If the detection target is the target station, the first historical passenger flow and the first passenger flow to be checked of the target station in the first specified time period are obtained; wherein the first historical passenger flow is used to express the first passenger flow of the target station in the first specified time period before the station is closed, and the first passenger flow to be checked is used to express the first passenger flow of the target station in the first specified time period after the station is closed, wherein the first passenger flow is the data of the number of people entering the station or the number of people leaving the station; Taking the first historical passenger flow and the first passenger flow to be tested as sample data, a plurality of abnormal point detection methods are respectively used to perform abnormality detection on the sample data to obtain detection results corresponding to each abnormal point detection method; wherein the plurality of abnormal point detection methods include at least two of the Grubbs criterion, the Laida criterion, and an abnormality method based on Poisson distribution; The detection results corresponding to the anomaly detection methods are voted by a voting method to obtain a first detection result of whether the first passenger flow to be tested is a first anomaly point; if the first detection result indicates that the first passenger flow to be tested is a first anomaly point, the target station is determined as the affected target object; If the detection target is the target path, a second historical passenger flow and a second passenger flow to be checked of the target path within a specified time period are obtained; wherein the second historical passenger flow is used to express the second passenger flow with the closed station as the departure point or destination of the target path within a second specified time period before the station is closed, and the passenger flow to be checked is used to express the second passenger flow with the closed station as the departure point or destination of the target path within the second specified time period after the station is closed, wherein the second passenger flow is the number of people passing through the target path; The second historical passenger flow and the second passenger flow to be tested are used as sample data, and a plurality of abnormal point detection methods are respectively used to perform abnormality detection on the sample data to obtain detection results corresponding to each abnormality detection method; wherein the plurality of abnormal point detection methods include at least two of the Grubbs criterion, the Laida criterion, and a Poisson distribution-based abnormality method; A voting method is used to vote on the detection results corresponding to the various abnormality detection methods to obtain a second detection result of whether the second passenger flow to be tested is a second abnormal point; if the second detection result indicates that the second passenger flow to be tested is a second abnormal point, the station corresponding to the second passenger flow to be tested is determined as the affected target object.

2. The method according to claim 1, characterized in that The target path includes any one of the following three target paths: The first type: the path between the reference station and the closed station is used as the target path; wherein the closed station is used as the departure point or destination of the target path; when the closed station is the departure point, the reference station is the corresponding destination; when the closed station is the destination, the reference station is the corresponding departure point; The second method: when the closed station is used as a transfer station in the total route, the path from the departure point of the total route to the closed station is used as the target path; The third type: when the closed station serves as a transfer station in the total route, the path from the closed station to the destination of the total route is used as the target path.

3. The method according to claim 1, characterized in that After obtaining the second historical passenger flow and the second passenger flow to be checked of the target path within the specified time period, the method further includes: Determine historical travel time data and to-be-verified travel time data according to the second historical passenger flow and the second to-be-verified passenger flow; wherein the historical travel time data is the time required for the second passenger flow corresponding to the second historical passenger flow to pass through the target path, and the to-be-verified travel time data is the time required for the second passenger flow corresponding to the second to-be-verified passenger flow to pass through the target path; Performing a third abnormal point test on the to-be-tested travel time data by using the historical travel time data to obtain a third test result; If the third detection result indicates that the travel time data to be checked is the abnormal point, the station corresponding to the travel time data to be checked is determined as the affected target object.

4. The method according to claim 3, characterized in that The performing the abnormal point inspection on the to-be-inspected travel time data by using the historical travel time data to obtain a third inspection result includes: The historical travel time data and the to-be-tested travel time data are used as sample data, and a plurality of outlier detection methods are respectively used to perform anomaly detection on the sample data to obtain detection results corresponding to the anomaly detection methods; wherein the plurality of outlier detection methods include at least two of an independent sample T test, a Mann-Whitney rank sum test, and a Wilcoxon signed rank test; The detection results corresponding to the anomaly detection methods are voted on using a voting method to obtain a final detection result of whether the travel time data to be tested is the anomaly point.

5. The method according to claim 1, characterized in that When the affected target object is an affected path, the station type of the closed station for the affected path includes a first type and a second type; wherein the first type indicates that the closed station is the departure point or destination of the target path, and the second type indicates that the closed station is a transfer station in the target path; The parameter information of the affected path includes: When the closed station is of the first type, only the affected path is inaccessible; When the closed station is of the second type, the passenger flow on the affected route is transferred to stations within a preset range based on the closed station; When the closed station is of the second type, and the time taken to complete the journey on the target path by other means is greater than the preset time, there is no path with a travel time close to that of the target path; When the closed station is of the second type and the closed station is the only departure point or destination in the target route, the user is affected by the closure of the station and chooses other travel modes or gives up traveling; If the affected target object is an affected station, the parameter information includes at least one of the following parameters of the affected station: the number of employees on duty, the employee duty roster, and traffic control equipment.

6. A data processing device applied to a rail transit system, characterized in that: The device comprises: A station identification module, configured to respond to the station closure indication information and parse the station closure indication information to obtain a station closure identification; A parameter information confirmation module, used to search for parameter information of an affected target object associated with the closed station identifier from the learned knowledge information; A deployment strategy confirmation module, used to obtain and execute a traffic deployment strategy for the affected target object according to the parameter information of the affected target object; The affected target objects are determined according to the following method: According to the station closure mark, screening detection targets and obtaining passenger flow data corresponding to the detection targets; the detection targets include target stations and target routes; If the detection target is the target station, the first historical passenger flow and the first passenger flow to be checked of the target station in the first specified time period are obtained; wherein the first historical passenger flow is used to express the first passenger flow of the target station in the first specified time period before the station is closed, and the first passenger flow to be checked is used to express the first passenger flow of the target station in the first specified time period after the station is closed, wherein the first passenger flow is the data of the number of people entering the station or the number of people leaving the station; Taking the first historical passenger flow and the first passenger flow to be tested as sample data, a plurality of abnormal point detection methods are respectively used to perform abnormality detection on the sample data to obtain detection results corresponding to each abnormal point detection method; wherein the plurality of abnormal point detection methods include at least two of the Grubbs criterion, the Laida criterion, and an abnormality method based on Poisson distribution; The detection results corresponding to the anomaly detection methods are voted by a voting method to obtain a first detection result of whether the first passenger flow to be tested is a first anomaly point; if the first detection result indicates that the first passenger flow to be tested is a first anomaly point, the target station is determined as the affected target object; If the detection target is the target path, a second historical passenger flow and a second passenger flow to be checked of the target path within a specified time period are obtained; wherein the second historical passenger flow is used to express the second passenger flow with the closed station as the departure point or destination of the target path within a second specified time period before the station is closed, and the passenger flow to be checked is used to express the second passenger flow with the closed station as the departure point or destination of the target path within the second specified time period after the station is closed, wherein the second passenger flow is the number of people passing through the target path; The second historical passenger flow and the second passenger flow to be tested are used as sample data, and a plurality of abnormal point detection methods are respectively used to perform abnormality detection on the sample data to obtain detection results corresponding to each abnormality detection method; wherein the plurality of abnormal point detection methods include at least two of the Grubbs criterion, the Laida criterion, and a Poisson distribution-based abnormality method; A voting method is used to vote on the detection results corresponding to the various abnormality detection methods to obtain a second detection result of whether the second passenger flow to be tested is a second abnormal point; if the second detection result indicates that the second passenger flow to be tested is a second abnormal point, the station corresponding to the second passenger flow to be tested is determined as the affected target object.

Images