Urban rail network train dispatching auxiliary decision system based on dynamic passenger flow

Through dynamic passenger flow analysis and in-depth mining technology, predicting and responding to the flow of people at peak times, the problem that existing systems cannot effectively deal with large amounts of people during peak periods is solved, and better scheduling decisions and user experience is achieved.

CN114240174BActive Publication Date: 2024-11-26TONGKONG INST (ANHUI) LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111561861.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-16
Publication Date
2024-11-26
Estimated Expiration
2041-12-16

AI Technical Summary

Technical Problem

During peak periods, existing rail transit assisted decision-making systems are difficult to effectively analyze and predict traffic, resulting in the inability to prepare in advance, which may lead to the situation where people are stranded or unable to leave.

Method used

Adopt a city rail network driving scheduling assisted decision-making system based on dynamic passenger flow, including basic prediction unit, integer unit, central control unit and load-bearing scheduling unit, to predict passenger flow through gray model, and generate over-limit signals by deeply mining past data and Adding points automatically recommends increasing transportation capacity to ensure that the system can cope with the flow of people at peak times.

Benefits of technology

Effectively predict and deal with the flow of people at peak moments, avoid disorderly allocation, ensure smooth passage of personnel, and improve the system's response capabilities and user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114240174B_ABST
    Figure CN114240174B_ABST
Patent Text Reader

Abstract

The present invention discloses an auxiliary decision-making system for urban rail line network vehicle scheduling based on dynamic passenger flow. The basic prediction unit predicts the passenger flow at peak hours with the help of a gray model to obtain the passenger flow at the corresponding station. Then, the passenger flow is received with the help of a data integration unit and transmitted to a central control unit. Of course, the data integration unit can also update the passenger flow to a certain extent according to actual data before transmitting it to the central control unit. The present application provides two methods. Then, the load-bearing scheduling unit is used to perform two types of deep mining according to past data and the actual search flow of all single transport lines, and generate over-limit signals and additional points according to the results of the deep mining. The central control unit is used to make relevant suggestions to the management personnel according to the over-limit signals and additional points, so as to better cope with the large number of people at peak hours and avoid disordered deployment, resulting in the situation where people are stranded or unable to leave. The present application is simple, effective, and easy to use.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of urban rail transit assistance, and in particular relates to an auxiliary decision-making system for urban rail line network vehicle dispatching based on dynamic passenger flow. Background Art

[0002] The patent with publication number CN101266679 provides a rail transit decision-making assistance system, which is used to realize a multi-layer decision-making assistance support platform with the basic data of the entire railway network as the main body, and complete the passenger flow analysis, capital flow analysis, ticket card flow analysis and real-time monitoring of ticket information and management information; the system processes real-time data in categories, priorities and batches; the decision-making assistance system includes a metadata acquisition module, a data transmission module, a data collection module, a data processing module, and a decision support module connected in sequence. The rail transit decision-making assistance system disclosed by the present invention combines system technology, process technology and correlation technology to form a six-layer control structure of the assembly line, so as to realize a multi-layer decision-making assistance support platform with the basic data of the entire railway network as the main body, and complete the functions of passenger flow analysis, capital flow analysis, ticket card flow analysis and real-time monitoring of ticket information and management information.

[0003] However, for special periods with peak passenger flow, there is a lack of effective analysis and prediction. It is necessary to make a certain degree of correction prediction of the passenger flow based on the actual results, give relevant suggestions for the actual results based on the prediction, and prepare for the large passenger flow in advance. Based on this, a solution is provided. Summary of the invention

[0004] The purpose of the present invention is to provide an auxiliary decision-making system for urban rail line network traffic dispatching based on dynamic passenger flow.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] The urban rail network driving dispatch auxiliary decision-making system based on dynamic passenger flow includes a basic prediction unit, a data integration unit, a central control unit, a load dispatch unit and a display unit;

[0007] The basic prediction unit is used to predict the passenger flow at peak times by using a grey model to obtain the passenger flow at corresponding stations, where the peak times are holidays and Spring Festival travel;

[0008] The basic prediction unit is used to transmit the passenger flow to the data integration unit, and the data integration unit receives the passenger flow and transmits it to the central control unit;

[0009] The load dispatching unit is used to perform two types of deep mining based on past data and the actual search flow of all single transport lines, and generate over-limit signals and additional points based on the results of deep mining;

[0010] The load-carrying scheduling unit is used to transmit the over-limit signal and additional item points to the central control unit, and the central control unit is used to transmit the over-limit signal and additional item points to the display unit. When the display unit receives the over-limit signal and additional item points transmitted by the central control unit, it automatically displays "The current project cannot carry this transportation, it is recommended to add + additional item points".

[0011] Furthermore, the load dispatching unit is used to collect past data, which includes the total passenger flow of the corresponding station in the past three years and the passenger flow component corresponding to a single transport line, and conduct in-depth mining of the past data;

[0012] The past data specifically includes a single transport line group formed by combining a number of single transport lines, and the corresponding passenger flow components constitute a passenger flow component group;

[0013] A single transportation line refers to several types of transportation included in the corresponding city, including subways, buses, taxis and others.

[0014] Furthermore, the specific methods of deep mining are:

[0015] Step 1: Obtain past data, namely the total flow of people, single transport line groups and corresponding flow component groups;

[0016] Step 2: Select any single transport line from the single transport line group, obtain its passenger flow weight for three consecutive years, divide the corresponding passenger flow weight by the total passenger flow of the year, and obtain the three single passenger ratios;

[0017] Step 3: Calculate the average of the three individual human proportions. If the difference between the three individual human proportions and the average is less than X1, where X1 is a user-preset value, the average is marked as the corresponding individual transportation line’s confirmed proportion.

[0018] Otherwise, the previous year’s single-item personnel ratio will be marked as the corresponding single-item transportation line’s confirmed ratio;

[0019] Step 4: Then, the remaining single transport lines in the single transport line group are processed from step 2 to step 3 to obtain the confirmed proportion of all single transport lines;

[0020] Step 5: Obtain all single transport lines and directly obtain the full passenger flow of the single transport lines at the corresponding peak time;

[0021] Step 6: Then, multiply the passenger flow and the corresponding confirmed proportion to obtain the predicted passenger flow of all single transport lines;

[0022] Step 7: Then calculate the deviation visual ratio according to the formula. The specific deviation visual ratio calculation formula is:

[0023] Deviation ratio = (predicted passenger flow - full load passenger flow) / full load passenger flow;

[0024] Step 8: Add the deviation ratios of all single transport lines to obtain the direction finding deviation;

[0025] If the direction finding deviation is greater than X2, an over-limit signal is generated, and the single transport line whose deviation ratio exceeds X2 is marked as an additional point; otherwise, no processing is performed. Here, X2 is a preset value by the management personnel, specifically 1.25.

[0026] Furthermore, the value of X2 in step eight is specifically determined according to the following method:

[0027] Starting from the direction finding deviation value of 1.1, a field simulation is performed, or the actual scene measurement situation is performed;

[0028] Get the actual time taken by each passenger in the corresponding passenger flow to leave the station within three kilometers after arriving at the corresponding station;

[0029] The actual time is averaged to obtain the mean departure time. When the mean departure time is less than 40 minutes, the direction finding deviation is increased by 0.05 each time until the mean departure time is greater than or equal to 40 minutes. At this time, the corresponding lateral deviation is marked as X2.

[0030] Furthermore, it also includes a data collection unit and a counterpart acquisition unit;

[0031] The data collection unit is used to retrieve online data 15 days before the peak time arrives, and obtain the actual number of people arriving at this site based on the online ticket purchase port;

[0032] The data collection unit is used to transmit the real number of people flow to the counterpart acquisition unit, and the counterpart acquisition unit is used to transmit the real number of people flow to the number integration unit;

[0033] Before transmitting the passenger flow to the central control unit, the data integration unit is also used to comprehensively calculate the actual passenger flow in combination with the passenger flow predicted by the basic prediction unit to complete the update of the passenger flow value;

[0034] The data integration unit is used to transmit the updated passenger traffic to the central control unit.

[0035] Furthermore, it also includes an active collection unit;

[0036] The active collection unit is used to communicate with the passenger's terminal to obtain the destination and transportation line after the user arrives at the station. The destination is the direction the passenger needs to go after arriving at the station, and the transportation line is the means of transportation taken by the passenger to reach the destination. The active collection unit is used to aggregate all the destinations and transportation lines to obtain the actual search flow of each single transportation line;

[0037] The active collection unit is used to transmit the actual search flow of all single transport lines to the bearer scheduling unit. The bearer scheduling unit receives the actual search flow of all single transport lines and performs deep mining on it. The specific steps of deep mining are:

[0038] S1: Get the full passenger flow of all single transport lines at the corresponding peak time;

[0039] S2: Calculate the deviation ratio of each single transport line according to the formula. The specific deviation ratio calculation formula is:

[0040] Deviation ratio = (actual search flow*X4-full load flow) / full load flow;

[0041] In the formula, X4 is the preset value, and the specific value is 1.05;

[0042] S3: Add the deviation ratios of all single transport lines to obtain the direction finding deviation;

[0043] If the direction finding deviation is greater than X2, an over-limit signal is generated, and the single transport line with the deviation ratio exceeding X2 is marked as an additional point; otherwise, no processing is done. Here, X2 is a value preset by the management personnel, and the specific value can be 1.25;

[0044] The central control unit controls the display unit to perform the same processing as in the first embodiment for the additional item point and the over-limit signal;

[0045] Furthermore, it also includes an interactive unit and an item terminal;

[0046] The active collection unit is also used to collect the destination and transportation line of the user after arriving at the station, and transmit the destination and transportation line of the corresponding user to the central control unit with the help of the load dispatching unit. The central control unit is used to automatically plan the waiting point and the shortest path to the waiting point according to the destination and transportation line in combination with the map library of the station. The waiting point is the waiting position when the user takes the transportation line to reach the destination;

[0047] The central control unit is used to transmit the waiting point and the shortest path to the waiting point to the sub-item terminal through the interactive unit. The sub-item terminal is the smart device of the corresponding user.

[0048] Furthermore, arriving at this station refers to this station being a terminal station or a transfer station.

[0049] Furthermore, the specific method of comprehensive calculation is as follows:

[0050] When the passenger flow is less than the actual number of people, the actual number of people is increased by 2%, and the passenger flow value is updated according to the obtained value;

[0051] When the passenger flow is greater than the actual number of people, the difference between the two is calculated, and half of the difference is taken as the measured increment. The actual number of people is added to the measured increment, and the passenger flow value is updated according to the obtained value.

[0052] Beneficial effects of the present invention:

[0053] The present invention predicts the passenger flow at peak hours by means of a gray model through a basic prediction unit to obtain the passenger flow at the corresponding station; then the passenger flow is received by means of a data integration unit and transmitted to the central control unit; of course, the data integration unit can also update the passenger flow to a certain extent according to actual data before transmitting it to the central control unit. This application provides two methods;

[0054] Afterwards, the load-carrying dispatching unit is used to conduct two types of deep mining based on past data and the actual search flow of all single transport lines, and to generate over-limit signals and additional points based on the results of the deep mining; the central control unit is used to give relevant suggestions to the management personnel based on the over-limit signals and additional points, so as to better cope with the large flow of people at peak times and avoid disordered deployment, which may cause people to be stranded or unable to leave; this application is simple, effective, and easy to use. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0056] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0057] like Figure 1 As shown, the urban rail network traffic scheduling auxiliary decision system based on dynamic passenger flow provided by this application;

[0058] As the first embodiment of the present invention, it includes a basic prediction unit, a data integration unit, a central control unit, a load scheduling unit and a display unit;

[0059] The basic prediction unit is used to predict the passenger flow at peak times with the help of a grey model to obtain the passenger flow at the corresponding station, where the peak times refer to holidays and Spring Festival travel; the grey model is specifically disclosed in the paper "Optimization of Grey Model in the Application of Passenger Flow Prediction during Spring Festival Travel", Qin Yuanqing1, Chen Shaohong2, Sun Debao1, Guo Hewei3 (1. Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, Hubei; 2. Guangzhou Branch of Yangcheng Railway Corporation, Guangzhou 510100, Guangdong; 3. Science and Technology Industry Corporation of Xiaogan Vocational and Technical College, Xiaogan 432100, Hubei); no specific details are given here;

[0060] The basic prediction unit is used to transmit the passenger flow to the data integration unit, and the data integration unit receives the passenger flow and transmits it to the central control unit;

[0061] The load dispatching unit is used to collect past data, which includes the total passenger flow of the corresponding station in the past three years, and the passenger flow components corresponding to the single transport line. Here, several single transport lines are combined into a single transport line group, and the corresponding passenger flow components constitute a passenger flow component group. The single transport line refers to several types of transportation included in the corresponding city, including subway, bus, taxi and others. Others here refer to riding a bicycle, walking or being picked up by someone; and deep mining of past data is carried out. The specific methods of deep mining are:

[0062] Step 1: Obtain past data, namely the total flow of people, single transport line groups and corresponding flow component groups;

[0063] Step 2: Select any single transport line from the single transport line group, obtain its passenger flow weight for three consecutive years, divide the corresponding passenger flow weight by the total passenger flow of the year, and obtain the three single passenger ratios;

[0064] Step 3: Calculate the average of the three individual human proportions. If the difference between the three individual human proportions and the average is less than X1, where X1 is a user-preset value, the average is marked as the corresponding individual transportation line’s confirmed proportion.

[0065] Otherwise, the previous year’s single-item personnel ratio will be marked as the corresponding single-item transportation line’s confirmed ratio;

[0066] Step 4: Then, the remaining single transport lines in the single transport line group are processed from step 2 to step 3 to obtain the confirmed proportion of all single transport lines;

[0067] Step 5: Obtain all single transport lines and directly obtain the full passenger flow of the single transport lines at the corresponding peak time;

[0068] Step 6: Then, multiply the passenger flow and the corresponding confirmed proportion to obtain the predicted passenger flow of all single transport lines;

[0069] Step 7: Then calculate the deviation visual ratio according to the formula. The specific deviation visual ratio calculation formula is:

[0070] Deviation ratio = (predicted passenger flow - full load passenger flow) / full load passenger flow

[0071] Step 8: Add the deviation ratios of all single transport lines to obtain the direction finding deviation;

[0072] If the direction finding deviation is greater than X2, an over-limit signal is generated, and the single transport line with the deviation ratio exceeding X2 is marked as an additional point; otherwise, no processing is performed. Here, X2 is a value preset by the management personnel, and the specific value can be 1.25 or other reasonable values;

[0073] Of course, there is another way to calculate the value of X2 here, the specific calculation method is:

[0074] Starting from the direction finding deviation value of 1.1, a field simulation is performed, or the actual scene measurement situation is performed;

[0075] Get the actual time taken by each passenger in the corresponding passenger flow to leave the station within three kilometers after arriving at the corresponding station;

[0076] The actual time is averaged to obtain the mean departure time. When the mean departure time is less than 40 minutes, the direction finding deviation is increased by 0.05 each time until the mean departure time is greater than or equal to 40 minutes. At this time, the corresponding lateral deviation is marked as X2; the 40 minutes here can also be set to 1 hour;

[0077] The load dispatching unit is used to transmit the over-limit signal and additional item points to the central control unit, and the central control unit is used to transmit the over-limit signal and additional item points to the display unit. When the display unit receives the over-limit signal and additional item points transmitted by the central control unit, it automatically displays "The current project cannot carry this transportation, it is recommended to add + additional item points";

[0078] As a second embodiment of the present invention, based on the first embodiment, the present invention further includes a data collection unit, a counterpart acquisition unit, an active collection unit, an interaction unit and a sub-item terminal;

[0079] The data collection unit is used to retrieve online data 15 days before the peak time arrives, and obtain the actual number of people arriving at this station according to the online ticket purchase port. Arriving at this station refers to the situation that this station is a terminal station or a transfer station; the data collection unit is used to transmit the actual number of people to the counterpart acquisition unit, and the counterpart acquisition unit is used to transmit the actual number of people to the number integration unit. The number integration unit is used to comprehensively calculate the actual number of people in combination with the passenger flow predicted by the basic prediction unit. The specific method of comprehensive calculation is:

[0080] When the passenger flow is less than the actual number of people, the actual number of people is increased by 2%, the obtained value is marked as the new passenger flow, and the new passenger flow is re-substituted into the step of transmitting to the central control unit in the first embodiment;

[0081] When the passenger flow is greater than the actual number of people flow, the difference between the two is obtained, and half of the difference is taken as the measured increment, the actual number of people flow is added to the measured increment, and the obtained value is marked as the new passenger flow, and the new passenger flow is re-substituted into the step of transmitting to the central control unit in the first embodiment;

[0082] The central control unit receives the data transmitted by the data integration unit to the passenger flow;

[0083] The active collection unit is used to communicate with the passenger's terminal to obtain the destination and transportation line after the user arrives at the station. The destination is the direction the passenger needs to go after arriving at the station, and the transportation line is the means of transportation taken by the passenger to reach the destination. The active collection unit is used to aggregate all the destinations and transportation lines to obtain the actual search flow of each single transportation line;

[0084] The active collection unit is used to transmit the actual search flow of all single transport lines to the bearer scheduling unit. The bearer scheduling unit receives the actual search flow of all single transport lines and performs deep mining on it. The specific steps of deep mining are:

[0085] S1: Get the full passenger flow of all single transport lines at the corresponding peak time;

[0086] S2: Calculate the deviation ratio of each single transport line according to the formula. The specific deviation ratio calculation formula is:

[0087] Deviation ratio = (actual search flow*X4-full load flow) / full load flow;

[0088] In the formula, X4 is a preset value, which is 1.05 or other values, used to more realistically predict the peak traffic volume. Therefore, the actual search traffic volume is magnified to a certain extent here.

[0089] S3: Add the deviation ratios of all single transport lines to obtain the direction finding deviation;

[0090] If the direction finding deviation is greater than X2, an over-limit signal is generated, and the single transport line with the deviation ratio exceeding X2 is marked as an additional point; otherwise, no processing is performed. Here, X2 is a value preset by the management personnel, and the specific value can be 1.25 or other reasonable values;

[0091] The central control unit controls the display unit to perform the same processing as in the first embodiment for the additional item point and the over-limit signal;

[0092] Of course, in this embodiment, the active collection unit is also used to collect the target destination and transportation line of the user after arriving at the site, and transmit the target destination and transportation line of the corresponding user to the central control unit with the help of the load-bearing scheduling unit. The central control unit is used to automatically plan the waiting point and the shortest path to the waiting point according to the target destination and transportation line in combination with the map library of the site. The waiting point is the waiting position when the user takes the transportation line to reach the target destination. For example, when taking a taxi, the shortest path to the taxi point is automatically planned. If this is a transfer, the path to the transfer waiting area is automatically planned, so that the user can quickly reach the waiting point and avoid congestion; the central control unit is used to transmit the waiting point and the shortest path to the waiting point to the sub-item terminal through the interactive unit. The sub-item terminal is the smart device of the corresponding user, specifically a mobile phone.

[0093] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. The urban rail network traffic dispatch auxiliary decision system based on dynamic passenger flow is characterized by: It includes basic prediction unit, data integration unit, central control unit, load dispatching unit and display unit; The basic prediction unit is used to predict the passenger flow at peak times by using a grey model to obtain the passenger flow at corresponding stations, where the peak times are holidays and Spring Festival travel; The basic prediction unit is used to transmit the passenger flow to the data integration unit, and the data integration unit receives the passenger flow and transmits it to the central control unit; The load dispatching unit is used to perform two types of deep mining based on past data and the actual search flow of all single transport lines, and generate over-limit signals and additional points based on the results of deep mining; The load dispatching unit is used to transmit the over-limit signal and additional item points to the central control unit, and the central control unit is used to transmit the over-limit signal and additional item points to the display unit. When the display unit receives the over-limit signal and additional item points transmitted by the central control unit, it automatically displays "The current project cannot carry this transportation, it is recommended to add + additional item points"; The load dispatching unit is used to collect past data, which includes the total passenger flow of the corresponding station in the past three years and the passenger flow component of a single transport line, and conduct in-depth mining of the past data; The past data specifically includes a single transport line group formed by combining a number of single transport lines, and the corresponding passenger flow components constitute a passenger flow component group; Single transportation line refers to several types of transportation included in the corresponding city, including subway, bus, taxi and others; The specific methods of deep mining are: Step 1: Obtain past data, namely the total flow of people, single transport line groups and corresponding flow component groups; Step 2: Select any single transport line from the single transport line group, obtain its passenger flow weight for three consecutive years, divide the corresponding passenger flow weight by the total passenger flow of the year, and obtain the three single passenger ratios; Step 3: Calculate the average of the three individual human proportions. If the difference between the three individual human proportions and the average is less than X1, where X1 is a user-preset value, the average is marked as the corresponding individual transportation line’s confirmed proportion. Otherwise, the previous year’s single-item personnel ratio will be marked as the corresponding single-item transportation line’s confirmed ratio; Step 4: Then, the remaining single transport lines in the single transport line group are processed from step 2 to step 3 to obtain the confirmed proportion of all single transport lines; Step 5: Obtain all single transport lines and directly obtain the full passenger flow of the single transport lines at the corresponding peak time; Step 6: Then, multiply the passenger flow and the corresponding confirmed proportion to obtain the predicted passenger flow of all single transport lines; Step 7: Then calculate the deviation visual ratio according to the formula. The specific deviation visual ratio calculation formula is: Deviation ratio = (predicted passenger flow - full load passenger flow) / full load passenger flow; Step 8: Add the deviation ratios of all single transport lines to obtain the direction finding deviation; If the direction finding deviation is greater than X2, an over-limit signal is generated, and the single transport line with the deviation ratio exceeding X2 is marked as an additional point; otherwise, no processing is done, where X2 is a preset value for the management personnel; The value of X2 in step eight is determined in the following manner: Starting from the direction finding deviation value of 1.1, a field simulation is performed, or the actual scene measurement situation is performed; Get the actual time taken by each passenger in the corresponding passenger flow to leave the station within three kilometers after arriving at the corresponding station; The actual time is averaged to obtain the mean departure time. When the mean departure time is less than 40 minutes, the direction finding deviation is increased by 0.05 each time until the mean departure time is greater than or equal to 40 minutes. At this time, the corresponding lateral deviation is marked as X2.

2. The urban rail network driving scheduling auxiliary decision system based on dynamic passenger flow according to claim 1 is characterized in that: It also includes data collection units and counterpart acquisition units; The data collection unit is used to retrieve online data 15 days before the peak time arrives, and obtain the actual number of people arriving at this site based on the online ticket purchase port; The data collection unit is used to transmit the real number of people flow to the counterpart acquisition unit, and the counterpart acquisition unit is used to transmit the real number of people flow to the number integration unit; Before transmitting the passenger flow to the central control unit, the data integration unit is also used to comprehensively calculate the actual passenger flow in combination with the passenger flow predicted by the basic prediction unit to complete the update of the passenger flow value; The data integration unit is used to transmit the updated passenger traffic to the central control unit.

3. The urban rail network traffic scheduling auxiliary decision system based on dynamic passenger flow according to claim 1 or 2, characterized in that: It also includes active collection units; The active collection unit is used to communicate with the passenger's terminal to obtain the destination and transportation line after the user arrives at the station. The destination is the direction the passenger needs to go after arriving at the station, and the transportation line is the means of transportation taken by the passenger to reach the destination. The active collection unit is used to aggregate all the destinations and transportation lines to obtain the actual search flow of each single transportation line; The active collection unit is used to transmit the actual search flow of all single transport lines to the bearer scheduling unit. The bearer scheduling unit receives the actual search flow of all single transport lines and performs deep mining on it. The specific steps of deep mining are: S1: Get the full passenger flow of all single transport lines at the corresponding peak time; S2: Calculate the deviation ratio of each single transport line according to the formula. The specific deviation ratio calculation formula is: Deviation ratio = (actual search flow*X4-full load flow) / full load flow; In the formula, X4 is the preset value, and the specific value is 1.05; S3: Add the deviation ratios of all single transport lines to obtain the direction finding deviation; If the direction finding deviation > X2, an over-limit signal is generated, and the single transport line with the deviation ratio exceeding X2 is marked as an additional point; otherwise, no processing is done. Here, X2 is the value preset by the management personnel.

4. The urban rail network traffic scheduling auxiliary decision system based on dynamic passenger flow according to claim 3 is characterized in that: It also includes interactive units and itemized terminals; The active collection unit is also used to collect the destination and transportation line of the user after arriving at the station, and transmit the destination and transportation line of the corresponding user to the central control unit with the help of the load dispatching unit. The central control unit is used to automatically plan the waiting point and the shortest path to the waiting point according to the destination and transportation line in combination with the map library of the station. The waiting point is the waiting position when the user takes the transportation line to reach the destination; The central control unit is used to transmit the waiting point and the shortest path to the waiting point to the sub-item terminal through the interactive unit. The sub-item terminal is the smart device of the corresponding user.

5. The urban rail network traffic scheduling auxiliary decision system based on dynamic passenger flow according to claim 2 is characterized in that: Arrival at this station means that this station is the terminal or transfer station.

6. The urban rail network traffic scheduling auxiliary decision system based on dynamic passenger flow according to claim 2 is characterized in that: The specific method of comprehensive calculation is: When the passenger flow is less than the actual number of people, the actual number of people is increased by 2%, and the passenger flow value is updated according to the obtained value; When the passenger flow is greater than the actual number of people, the difference between the two is calculated, and half of the difference is taken as the measured increment. The actual number of people is added to the measured increment, and the passenger flow value is updated according to the obtained value.