Intelligent command console adaptive adjustment system based on multi-source information fusion

Abstract

The invention discloses an intelligent command console adaptive adjustment system based on multi-source information fusion, which belongs to the technical field of rail transit dispatching command and comprises a rail transit data acquisition module, an external flow data acquisition module, a fuzzy association matching module and a large and small intersection adjustment control module. The rail transit data acquisition module is used for acquiring current rail transit subway data, including subway line station information, station travel interval, station driving time and large and small intersection station information, acquiring real-time subway pedestrian flow data and subway entering people number through a rail transit gate, and establishing a subway flow database; and the external flow acquisition module. According to the intelligent command console adaptive adjustment system based on multi-source information fusion, the configuration of large and small traffic vehicles is dynamically optimized by mining flow relevance data, and collaborative optimization of operation efficiency, service quality and cost control is realized.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of rail transit dispatching command technology, and specifically relates to an intelligent command console adaptive adjustment system based on multi-source information fusion. BACKGROUND

[0002] With the acceleration of urbanization, the subway has become the core backbone of urban public transportation, and its operation efficiency, service quality and operation cost directly affect the efficiency of urban transportation and the travel experience of passengers;

[0003] Current subway operation command relies on fixed route planning or manual experience adjustment, and lacks precise control of the correlation between external flow real-time data and subway route flow, resulting in a prominent imbalance in resource allocation. In passenger flow fluctuation periods, the fixed route mode is difficult to dynamically match demand, resulting in either excessive small route vehicles causing empty running waste or insufficient small route configuration causing excessive congestion, which not only reduces train utilization, but also restricts the improvement of operation efficiency. At the same time, the traditional adjustment method cannot accurately respond to the passenger flow differences of different time periods and different stations. In peak periods, passengers have to wait for a long time due to insufficient vehicle configuration, and in low valley periods, service resources are wasted due to vehicle redundancy, which has the problem of low functionality. SUMMARY

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. To this end, the present application proposes an intelligent command console adaptive adjustment system based on multi-source information fusion, which improves the detection method and processing method to solve the above technical problems.

[0005] In order to achieve the above purpose, the present application adopts the following technical solutions:

[0006] The intelligent command console adaptive adjustment system based on multi-source information fusion comprises a rail transit data acquisition module, an external flow data acquisition module, a fuzzy correlation matching module and a large-small route adjustment control module.

[0007] The rail transit data acquisition module acquires current rail transit subway data, including subway line station information, station travel interval, station travel time, large-small route station information, and collects real-time subway passenger flow data and subway entry number through rail transit gates to establish a subway flow database.

[0008] The external flow acquisition module collects bus lines related to bus platforms around subway line stations, collects the number of people getting on buses at different stations and the number of people getting off at rail transit stations, and calculates the proportion of people getting on at different station time intervals to establish an external flow database.

[0009] The fuzzy correlation matching module performs fuzzy correlation between the external traffic and the subway traffic in different time intervals based on the subway traffic database and the external traffic database to obtain the correlation between the external traffic and the subway route traffic in different time intervals.

[0010] The size route adjustment control module adjusts and controls the current subway line size route vehicle based on the correlation between the external traffic and the subway route traffic in different time intervals, and combines the time interval to count the external traffic real-time data.

[0011] Further, the rail transit data collection module collects current rail transit subway data, including subway line site information, site travel interval, site travel time, size route site information, and collects real-time subway passenger flow data and subway entering passenger number through the rail transit gate machine to establish a subway traffic database, including the following steps:

[0012] Through The subway traffic database of the current urban rail transit is established, the current urban rail transit line site information is collected, the rail transit site information, site travel interval, site travel time and size route site information are integrated, sorted according to the line number and site number, and a structured data table is obtained. In the subway traffic database, a parent file is established according to the line number, and a sub-file is established in the parent file according to the site number to record the relevant integrated data, wherein the size route site information includes the starting site, the terminal site and the passing site of the size route;

[0013] The real-time subway passenger flow of each site is counted by the card swiping or code scanning record of the gate machine of different rail transit sites, the card swiping record of the entering and exiting sites is counted according to the fixed time granularity T, the total number of people entering and leaving the site in the time period is calculated, and the actual boarding personnel ratio under the time granularity accumulation before entering the site is associated by counting the subway boarding number in the site. The specific steps are:

[0014] The card swiping and code scanning records of the gate machine of each site are obtained by data connection with the gate machine equipment of the rail transit system, and passenger flow statistical equipment is set at each site to count the boarding number of each train entering the site by infrared sensor, and the time, site number and corresponding boarding number of each train entering the site are recorded;

[0015] The gate machine records are grouped according to the fixed time granularity T, the entering time of the current vehicle at the site and the exiting time of the last vehicle are based, the time granularity between them is accumulated to obtain the time interval t, and the entering number in the time interval t is counted for each time interval t and site s At the same time, the boarding number of the train e in the time interval is obtained by infrared sensor , calculate the boarding number ratio in the current time interval of the train , record the boarding number ratio data of different stations in different intervals in the subway flow database subfile.

[0016] Further, the external flow data collection module collects bus lines related to bus stations around the subway station, collects boarding numbers of different stations and off-boarding numbers of rail transit stations, counts the boarding number ratio in different time intervals at different stations, and establishes an external flow database, specifically including the following steps:

[0017] Through the geographic information system, the bus station information around the rail transit station is collected by setting a radius centering on the rail transit station to obtain the bus lines associated with different rail transit stations. By connecting the urban public transportation system, the real-time boarding number of the bus is obtained based on the boarding card number of different buses at the station. The off-boarding number and arrival time are counted by the camera at the internal door of the bus.

[0018] Based on the fixed time granularity T, the off-boarding number of the bus station around the current rail transit station is counted. According to the off-boarding number of the bus station around the rail transit station in the time interval and the off-boarding number of the rail transit station in the time interval, the bus boarding number ratio in different time intervals at different stations is calculated. The external flow database is established by MySQL, and the different station files are established and the bus boarding number ratio data in different time intervals are recorded.

[0019] Further, the external flow data collection module collects bus lines related to bus stations around the subway station, collects boarding numbers of different stations and off-boarding numbers of rail transit stations, counts the boarding number ratio in different time intervals at different stations, and establishes an external flow database, specifically including the following steps:

[0020] Based on the fixed time granularity T, the off-boarding number of the bus station around the current rail transit station is counted. According to the off-boarding number of the bus station around the rail transit station in the time interval and the off-boarding number of the rail transit station in the time interval, the bus boarding number ratio in different time intervals at different stations is calculated. The external flow database is established by MySQL, and the different station files are established and the bus boarding number ratio data in different time intervals are recorded. The off-boarding number of the bus station around the current rail transit station is counted based on the fixed time granularity T. The off-boarding number of the bus station around the current rail transit station is counted based on the fixed time granularity T. ;

[0021] An external traffic database is established by MySQL, and different station files are established according to station names in the external traffic database, and the bus entry number ratio of different rail transit stations in different time intervals is recorded.

[0022] Further, the fuzzy correlation matching module, based on the metro traffic database and the external traffic database, collects data, and performs fuzzy correlation on the external traffic and the metro traffic in different time intervals to obtain the correlation of the external traffic and the metro traffic in different time intervals.

[0023] Based on the metro traffic database and the external traffic database, data is collected, the boarding number ratio data and the bus entry number ratio in different time intervals of different rail transit stations are extracted, and the boarding number ratio data and the bus entry number ratio in different time intervals of different rail transit stations are fuzzy correlated to obtain the correlation of the external traffic and the metro traffic in different time intervals.

[0024] Further, the metro traffic database and the external traffic database are based on the metro traffic database and the external traffic database, data is collected, the boarding number ratio data and the bus entry number ratio in different time intervals of different rail transit stations are extracted, and the boarding number ratio data and the bus entry number ratio in different time intervals of different rail transit stations are fuzzy correlated to obtain the correlation of the external traffic and the metro traffic in different time intervals, including the following steps:

[0025] According to the boarding number ratio in the current time interval of the train in the metro traffic database and the external traffic database and the bus entry number ratio of different stations in different time intervals , based on the time interval, the minimum-maximum normalization is performed on and to obtain and ;

[0026] The normalized boarding number ratio and the bus entry number ratio are taken as fuzzy variables, each fuzzy variable is divided into three fuzzy subsets of "low", "medium" and "high", respectively denoted as L, M and H, and the boarding number ratio and the bus entry number ratio are respectively subjected to triangular membership functions to obtain the low membership function , the medium membership function , the high membership function of the boarding number ratio, and the low membership function , the medium membership function , the high membership function and establish fuzzy association rules ;

[0027] For each rule Calculate the membership of the rule premise by taking the minimum operation :

[0028] ;

[0029] where, is the membership of the bus boarding passenger ratio belonging to the fuzzy subset , is the membership of the boarding passenger ratio belonging to the fuzzy subset , , represent the fuzzy subsets of the bus boarding passenger ratio and the boarding passenger ratio, respectively;

[0030] By taking the maximum operation to synthesize the conclusions of all rules, the fuzzy membership function of the association is obtained where the membership of the rule conclusion is equal to the membership of the rule premise, i.e. , is the fuzzy subset of the association, and n is the number of rules. Further de-fuzzification is performed by the barycenter method to obtain the specific association value:

[0031] ;

[0032] where, is the discrete value of the association fuzzy subset, is the corresponding membership.

[0033] Further, the size inter-route adjustment control module, based on the association between external traffic and subway inter-route traffic in different time intervals, statistics external traffic real-time data and combines time interval, adjusts and controls the current subway line size inter-route vehicle, including the following steps:

[0034] By obtaining the association between external traffic and subway inter-route traffic in different time intervals , according to the real-time bus off-site passenger number of different sites s where represents the time interval in which the current time is located;

[0035] When > , then the size inter-route subway association of the current site is adjusted and determined, where is the passenger flow threshold value;

[0036] Set different association threshold values , , the correlation between the external flow and the subway route flow is low, and the number of large-route vehicles on the existing line is reduced;

[0037] When < , the correlation between the external flow and the subway route flow is low, and the number of large-route vehicles on the existing line is reduced;

[0038] When ≤ , the correlation between the external flow and the subway route flow is moderate, and the number of small-route vehicles is increased while the number of large-route vehicles remains unchanged; When

[0039] ≥ , the correlation between the external flow and the subway route flow is high, and the number of large-route vehicles is increased. Compared with the prior art, the present application has the following advantages:

[0040] 1. In the present application, by statistically analyzing real-time data of external flow and combining the correlation between external flow and subway route flow in different time intervals, the number of large-route and small-route vehicles on the subway line is reasonably adjusted and controlled. When the correlation between external flow and subway route flow is high, the number of large-route and small-route vehicles is increased, so that the subway resources are more reasonably allocated, avoiding empty running or excessive crowding of vehicles, improving the utilization rate of trains, and thus improving the operation efficiency of the entire subway system.

[0041] 2. In the present application, based on accurate correlation analysis and real-time data adjustment of vehicle arrangement, the passenger flow demand of different time periods and stations can be better met, and during the peak passenger flow period, the number of large-route vehicles is increased to quickly evacuate a large number of passengers, reducing the waiting time of passengers, and making the travel of passengers more convenient and comfortable.

[0042] 3. In the present application, by optimizing the configuration of large-route and small-route vehicles, unnecessary vehicle investment and waste of operation resources are avoided, the number of vehicles is dynamically adjusted according to the correlation between external flow and subway route flow, the empty mileage and energy consumption of trains are reduced, the labor cost and equipment maintenance cost are reduced, and the economic benefit of subway operation is maximized.

[0043] BRIEF DESCRIPTION OF DRAWINGS

[0044] Figure 1 The block diagram of the intelligent command and control console adaptive adjustment system based on multi-source information fusion of the present application. DETAILED DESCRIPTION

[0045] ​The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] Example 1:

[0047] like Figure 1 As shown, the intelligent command and control console adaptive adjustment system based on multi-source information fusion includes a rail transit data acquisition module, an external traffic flow data acquisition module, a fuzzy correlation matching module, and a large and small route adjustment and control module.

[0048] The rail transit data acquisition module shown collects current rail transit data, including subway line and station information, station travel intervals, station travel times, and information on stations for both long and short routes. Simultaneously, it collects real-time subway passenger flow data and the number of people entering the subway through rail transit turnstiles, establishing a subway flow database. The process includes the following steps:

[0049] pass Establish a current urban rail transit subway traffic database, collect current urban rail transit line and station information, integrate rail transit station information, station travel interval, station travel time, and large and small loop station information, sort them according to line number and station number to obtain structured data tables, create a master file in the subway traffic database according to line number, and create a sub-file in the master file according to station number to record relevant integrated data, including the starting station, ending station, and stations passed through for large and small loops;

[0050] It should be noted that information on urban rail transit line stations can be obtained from rail transit planning and design documents and official databases.

[0051] The real-time passenger flow of the subway at each station is statistically analyzed by recording card swipes or QR code scans at the turnstiles of different rail transit stations. The card swipe records for entering and exiting the station are statistically analyzed according to a fixed time granularity T to calculate the total number of people entering and leaving the station within that time period. Simultaneously, the proportion of passengers actually boarding the subway is correlated with the actual number of passengers boarding the train based on the accumulated time granularity before entering the station. The specific steps are as follows:

[0052] By connecting with the gate equipment of the rail transit system, the card swiping and QR code scanning records of each station gate are obtained. At the same time, passenger flow statistics equipment is set up at each station. Infrared sensors are used to count the number of passengers boarding each train when it enters the station, and the time of each train's entry, station number and the corresponding number of passengers boarding are recorded.

[0053] It should be noted that these records should include the time of card swiping or code scanning, station number, entry and exit identification and other information, which can be obtained by setting infrared sensors on the subway or platform to count the actual boarding number of trains at different stations.

[0054] The gate records are grouped according to a fixed time granularity T, and the time granularity between the entry time of the current vehicle at the station and the exit time of the last vehicle is accumulated to obtain a time interval t. For each time interval t and station s, the number of entries in the time interval is counted Meanwhile, the number of passengers boarding the train e in the time interval is obtained through the infrared sensor The proportion of the number of passengers boarding the train in the current time interval is calculated The proportion of the number of passengers boarding the train in different intervals at different stations is recorded in the subway flow database subfile.

[0055] The external flow collection module collects bus lines related to bus platforms around subway stations, collects the number of passengers boarding buses at different stations and the number of passengers alighting at rail transit stations, counts the proportion of entries in different time intervals at different stations, and establishes an external flow database, which specifically includes the following steps:

[0056] Through a geographic information system, a radius is drawn around the rail transit station to collect information about bus platforms around the current urban rail transit station, obtain bus lines associated with different rail transit stations, connect the urban public transportation system, obtain real-time boarding numbers of buses based on the number of boarding cards at the stations, and count the number of passengers alighting through cameras at the bus doors and the arrival time;

[0057] It should be noted that the radius is usually set to 100 meters, and can be increased or decreased according to the actual urban situation. The information of all bus platforms within the range can be collected through the database of the bus management department, the identification board of the bus station or the bus query APP, so as to obtain the bus lines related to different platforms.

[0058] The number of passengers alighting at bus stations around the current rail transit station is counted based on a fixed time granularity T. According to the number of passengers entering the rail transit station at a discount in the time interval and the number of passengers alighting at the bus stations around the rail transit station in the time interval, the proportion of bus entries at different stations in different time intervals is calculated, an external flow database is established through MySQL, different station files are established and the proportion of bus entries in different time intervals is recorded, including the following steps:

[0059] Based on the fixed time granularity T, the number of passengers getting off at the bus station around the current rail transit station is counted, and the number of passengers getting off at the bus station obtained by all time granularities in the time interval t is integrated according to the time interval t obtained by the rail transit data collection module The number of passengers getting off at the bus station in the current time interval t is obtained through the gate equipment of the rail transit system The proportion of bus passengers getting off at different stations in different time intervals is calculated ;

[0060] An external flow database is established through MySQL, and different station files are established according to the station name in the external flow database, and the proportion of bus passengers getting off at different rail transit stations in different time intervals is recorded.

[0061] It should be noted that by recording the proportion of bus passengers getting off at different rail transit stations in different time intervals, subsequent fuzzy matching of the proportion of bus passengers getting off at different stations and the proportion of passengers getting on at different stations in different intervals can be facilitated to flexibly control and schedule the rail transit and subway.

[0062] Embodiment 2:

[0063] The fuzzy correlation matching module, based on the subway flow database and the external flow database, collects data, and fuzzy correlates the external flow and the subway flow in different time intervals to obtain the correlation of the external flow and the subway flow in different time intervals, specifically including the following steps:

[0064] Based on the subway flow database and the external flow database, the proportion of passengers getting on at different rail transit stations in different time intervals and the proportion of bus passengers getting off at different rail transit stations in different time intervals are extracted, and the proportion of passengers getting on at different rail transit stations in different time intervals and the proportion of bus passengers getting off at different rail transit stations in different time intervals are fuzzy correlated to obtain the correlation of the external flow and the subway flow in different time intervals, including the following steps:

[0065] According to the proportion of passengers getting on at the current time interval of the train in the subway flow database and the external flow database and the proportion of bus passengers getting off at different stations in different time intervals , based on the time interval, the minimum-maximum normalization is performed on and to obtain and ;

[0066] It should be noted that the normalization processing can eliminate the influence of different data scales, so that the value range is between [0, 1], which is convenient for subsequent fuzzy correlation.

[0067] the normalized boarding ratio and the bus entry ratio As fuzzy variables, each fuzzy variable is divided into three fuzzy subsets of "low", "medium", and "high", denoted as L, M, and H, respectively. The boarding ratio and the bus entry ratio are respectively subjected to triangular membership functions, and the low membership function , the medium membership function , and the high membership function of the boarding ratio are obtained, as well as the low membership function , the medium membership function , and the high membership function of the bus entry ratio, and fuzzy association rules are established ;

[0068] It should be noted that in the calculation of the triangular membership function, the low membership function is:

[0069] ;

[0070] The medium membership function is:

[0071] ;

[0072] The high membership function is:

[0073] ;

[0074] wherein is a parameter determined according to data distribution, and similarly, the membership function is defined for the bus entry ratio to determine the low, medium, and high membership functions. The establishment of fuzzy association rules requires actual experience and business knowledge. For example, if is L and is L, the association is L. The specific rules library is established based on the experience method and business knowledge by consulting current field experts according to the actual application environment.

[0075] For each rule , the membership degree of the rule premise is calculated by taking the minimum operation :

[0076] ;

[0077] wherein is the membership degree of the bus entry ratio belonging to the fuzzy subset , and is the fuzzy subset of the proportion of the number of passengers getting on the bus , , represent the fuzzy subsets of the proportion of the number of passengers getting on the bus and the number of passengers getting on the bus respectively;

[0078] The conclusion of all rules is obtained by maximum operation, and the associated fuzzy membership function is obtained where the membership degree of the rule conclusion is equal to the membership degree of the rule premise, that is , is the associated fuzzy subset, and n is the number of rules. Further de-fuzzification is performed by the barycenter method to obtain the specific associated value:

[0079] ;

[0080] wherein is the discrete value of the associated fuzzy subset, is the corresponding membership degree.

[0081] It should be noted that the final associated value of the external flow and the metro interchange flow in different time intervals , and the greater the value, the stronger the association;

[0082] The large-small interchange adjustment control module, based on the association of the external flow and the metro interchange flow in different time intervals, counts the real-time data of the external flow and combines the time interval to adjust and control the current metro line large-small interchange vehicle, including the following steps:

[0083] By obtaining the association of the external flow and the metro interchange flow in different time intervals , the real-time number of passengers getting off the bus at different stations s is obtained wherein represents the time interval in which the current time is located;

[0084] When > , the large-small interchange adjustment of the current station is determined, wherein is the passenger flow threshold value;

[0085] It should be noted that the passenger flow threshold value needs to be determined in combination with the historical average value of the same time interval of the number of passengers getting off the bus around the current station. If it exceeds the average value, it represents that the number of passengers is crowded and needs to be adjusted for the large-small interchange adjustment of the metro.

[0086] Different association threshold values , are set to determine the association degree of the current metro station:

[0087] When < , it represents that the correlation between the external traffic and the subway route traffic is low, and the large route and small route vehicles on the existing line are reduced;

[0088] When ≤ < , it represents that the correlation between the external traffic and the subway route traffic is at a medium level, the number of small route vehicles is increased, and the number of large route vehicles is kept unchanged;

[0089] When ≥ , it represents that the correlation between the external traffic and the subway route traffic is high, and the number of large and small route vehicles is increased.

[0090] It should be noted that, , The correlation data can be sorted from small to large, and the lower quartile, the median and the upper quartile are calculated, the lower quartile is set as , and the upper quartile is set as , and the specific vehicle adjustment result includes adjusting the departure time and train number of the large route and small route vehicles, which needs to be flexibly set in combination with the subway operation situation in the actual use environment, and the scheduling instructions are sent to the subway operation scheduling system, and the system adjusts and controls the large and small route vehicles of the current subway line according to the instructions, to ensure the implementation of the adjustment strategy.

[0091] In the embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the modules is only a logical function division, and actual implementation can have another division manner; the modules described as separated components can be or can not be physical separated, and the components displayed as modules can be or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. According to actual needs, some or all of the modules can be selected to achieve the purpose of the method of the embodiments.

[0092] The above embodiments are only used to illustrate the technical method of the present application and are not limited, although the technical method of the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present application can be modified or replaced equivalently without departing from the spirit and scope of the technical method of the present application.

Claims

1. An adaptive adjustment system for an intelligent command and control console based on multi-source information fusion, characterized in that: It includes a rail transit data acquisition module, an external traffic flow data acquisition module, a fuzzy correlation matching module, and a long / short route adjustment and control module; The rail transit data acquisition module shown collects current rail transit metro data, including metro line and station information, station travel intervals, station travel times, and information on major and minor routes. At the same time, it collects real-time metro passenger flow data and the number of people entering the metro through rail transit turnstiles to establish a metro flow database. The external traffic acquisition module collects information on bus routes involved in bus stops around subway stations, collects the number of passengers boarding at different bus stops and the number of passengers alighting at rail transit stations, calculates the proportion of passengers entering the station in different time intervals, and establishes an external traffic database. The fuzzy correlation matching module collects data from the subway traffic database and the external traffic database, performs fuzzy correlation between external traffic and subway traffic in different time intervals, and obtains the correlation between external traffic and subway traffic in different time intervals. The large and small route adjustment and control module adjusts and controls the vehicles on the current subway line based on the correlation between external traffic flow and subway route traffic flow in different time intervals, by statistically analyzing real-time external traffic flow data and combining it with time intervals.

2. The adaptive adjustment system for an intelligent command and control console based on multi-source information fusion as described in claim 1, characterized in that: The rail transit data acquisition module collects current rail transit subway data, including subway line and station information, station travel intervals, station travel times, and information on stations for both long and short routes. Simultaneously, it collects real-time subway passenger flow data and the number of people entering the subway through rail transit turnstiles, establishing a subway flow database. This includes the following steps: pass Establish a current urban rail transit subway traffic database, collect current urban rail transit line and station information, integrate rail transit station information, station travel interval, station travel time, and large and small loop station information, sort them according to line number and station number to obtain structured data tables, create a master file in the subway traffic database according to line number, and create a sub-file in the master file according to station number to record relevant integrated data, including the starting station, ending station, and stations passed through for large and small loops; The real-time passenger flow of the subway at each station is statistically analyzed by recording card swipes or QR code scans at the turnstiles of different rail transit stations. The card swipe records for entering and exiting the station are statistically analyzed according to a fixed time granularity T to calculate the total number of people entering and leaving the station within that time period. Simultaneously, the proportion of passengers actually boarding the subway is correlated with the actual number of passengers boarding the train based on the accumulated time granularity before entering the station. The specific steps are as follows: By connecting with the gate equipment of the rail transit system, the card swiping and QR code scanning records of each station gate are obtained. At the same time, passenger flow statistics equipment is set up at each station. Infrared sensors are used to count the number of passengers boarding each train when it enters the station, and the time of each train's entry, station number and the corresponding number of passengers boarding are recorded. The turnstile records are grouped according to a fixed time granularity T. Based on the current vehicle's entry time and the previous vehicle's exit time at the station, the time granularity between them is accumulated to obtain a time interval t. For each time interval t and station s, the number of people entering the station within that time interval is counted. At the same time, the number of passengers boarding train e within that time interval is obtained through infrared sensors. Calculate the proportion of passengers boarding the train within the current time interval. The proportion of passengers boarding at different stations in different sections is recorded in the subway traffic database sub-file.

3. The adaptive adjustment system for an intelligent command and control console based on multi-source information fusion according to claim 2, characterized in that: The external traffic data acquisition module collects information on bus routes around subway stations, the number of passengers boarding at different bus stops, and the number of passengers alighting at rail transit stations. It also calculates the proportion of passengers entering the station within different time intervals and establishes an external traffic database. The specific steps include: Using a geographic information system, a radius is drawn with the rail transit station as the center to collect information on bus stops around the current urban rail transit station, obtain the bus routes associated with different rail transit stations, and obtain the real-time number of passengers boarding the bus based on the number of card swipes at different bus stops by connecting to the urban public transportation system. The number of passengers getting off the bus and the arrival time are counted by cameras at the bus doors. Based on a fixed time granularity T, the number of people getting off at bus stops around the current rail transit station is statistically analyzed. According to the number of people entering the rail transit station with preferential transfer within the time interval and the number of people getting off at bus stops around the rail transit station within the time interval, the proportion of bus passengers entering the station at different stations within different time intervals is calculated. An external traffic database is established through MySQL to create files for different stations and record the proportion of bus passengers entering the station within different time intervals.

4. The adaptive adjustment system for an intelligent command and control console based on multi-source information fusion according to claim 3, characterized in that: The method involves statistically analyzing the number of passengers alighting at bus stops surrounding the current rail transit station based on a fixed time granularity T. It calculates the proportion of bus passengers entering different stations within different time intervals based on the number of passengers entering the rail transit station with discounted transfers and the number of passengers alighting at bus stops surrounding the rail transit station within the same time interval. An external traffic database is established using MySQL to create profiles for different stations and record the proportion of bus passengers entering the station within different time intervals. This includes the following steps: The number of passengers alighting at bus stops around the current rail transit station is statistically analyzed based on a fixed time granularity T. This is done by integrating the bus stop alighting data obtained from all time granularities within the time interval t obtained from the rail transit data acquisition module. The number of passengers entering the station with preferential transfer rates within the current time interval t is obtained through the turnstile equipment of the rail transit system. Calculate the proportion of passengers entering the bus station at different stations within different time intervals. ; An external traffic database is established using MySQL. Different station profiles are created in the external traffic database based on station names, and the proportion of bus passengers entering different rail transit stations within different time intervals is recorded.

5. The adaptive adjustment system for an intelligent command and control console based on multi-source information fusion according to claim 4, characterized in that: The fuzzy correlation matching module, based on data collected from the subway traffic database and the external traffic database, performs fuzzy correlation between external traffic and subway traffic in different time intervals to obtain the correlation between external traffic and subway route traffic in different time intervals. Specifically, it includes the following steps: Based on data collected from the subway traffic database and external traffic database, the proportion of passengers boarding and buses entering the station at different rail transit stations in different time intervals is extracted. Fuzzy correlation is then performed on the proportion of passengers boarding and buses entering the station at different rail transit stations in different time intervals to obtain the correlation between external traffic and subway traffic in different time intervals.

6. The adaptive adjustment system for an intelligent command and control console based on multi-source information fusion according to claim 5, characterized in that: The process involves collecting data from a subway traffic database and an external traffic database, extracting the proportion of passengers boarding trains and buses entering the station at different rail transit stations during different time intervals, and then performing a fuzzy correlation between these proportions to obtain the correlation between external traffic flow and subway traffic flow in different time intervals. This includes the following steps: Based on the proportion of passengers boarding the current train within the current time interval from both the subway traffic database and external traffic databases. And the proportion of passengers entering the bus station at different stations within different time intervals. Based on the time interval, the minimum-maximum normalization pair and Perform normalization to obtain and ; Normalized boarding passenger ratio Ratio of passengers entering the bus station As fuzzy variables, each fuzzy variable is divided into three fuzzy subsets: "low," "medium," and "high," denoted as L, M, and H, respectively, representing the proportion of passengers boarding the bus. and the proportion of passengers entering the bus station Perform triangular membership functions separately to obtain the low membership functions for the proportion of passengers boarding the bus. Membership functions High membership function And the low percentage of passengers entering bus stations (membership function) Membership functions High membership function And establish fuzzy association rules ; For each rule The membership degree of the rule premise is calculated by taking the smaller value. : ； in, The proportion of passengers entering the bus station belongs to a fuzzy subset. membership degree The proportion of passengers boarding the bus belongs to a fuzzy subset. membership degree , These are fuzzy subsets representing the proportions of people entering the bus station and boarding the bus, respectively. By synthesizing the conclusions of all rules through maximum operation, the fuzzy membership function of the correlation is obtained. The membership degree of the rule's conclusion is equal to the membership degree of the rule's premises, i.e. , For the fuzzy subset of correlations, where n is the number of rules, further defuzzification is performed using the centroid method to obtain specific correlation values: ； in, It is the discrete value of the relational fuzzy subset. It represents the corresponding membership degree.

7. The adaptive adjustment system for an intelligent command and control console based on multi-source information fusion according to claim 6, characterized in that: The large and small route adjustment and control module, based on the correlation between external traffic flow and subway traffic flow in different time intervals, statistically analyzes real-time external traffic flow data and combines it with time intervals to adjust and control the large and small route vehicles on the current subway line, including the following steps: By obtaining the correlation between external traffic flow and subway traffic flow in different time intervals Based on the real-time number of passengers getting off the bus at different stations s ,in This represents the time interval in which the current time is located; when > When this happens, a determination is made regarding the correlation between the current station and the metro lines of varying lengths. Human traffic threshold; Set different correlation thresholds , Determine the relevance of the current subway station: when < When this occurs, it indicates a low correlation between external traffic flow and subway traffic flow, thus reducing the number of long and short routes on existing lines; when ≤ < When the external traffic flow is at a moderate level, it indicates that the correlation between the external traffic flow and the subway traffic flow is at a moderate level. Therefore, the number of vehicles on the smaller routes should be increased while the number of vehicles on the larger routes should remain unchanged. when ≥ When this occurs, it indicates a high correlation between external traffic flow and subway traffic flow, while also increasing the number of vehicles on both large and small routes.

Images