An urban digital intelligence deduction system and method based on big data analysis

Abstract

The present invention discloses an urban digital intelligence deduction system and method based on big data analysis, belonging to the technical field of data analysis. The system includes an urban digital model management module, a data collection and input module, a correlation analysis module, and an urban traffic deduction calculation module; the urban digital model management module is used to establish a digital model of the city based on the land use and road planning of the city, and deploy the same road facility environment as the city in the digital model; the data collection and input module is used to collect urban traffic data and determine the types of travel modes of citizens on urban traffic roads; the correlation analysis module is used to establish a time management model to predict the total urban traffic flow at the next moment; the planned land deduction calculation module is used to simulate and deduce in the digital model according to the collected urban traffic data and the predicted total urban traffic flow at the next moment, and calculate the urban traffic congestion value at the next moment.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and specifically to an urban digital intelligence deduction system and method based on big data analysis. Background Art

[0002] Urban digital intelligence deduction is a method of simulating, predicting, and planning urban development by using advanced information technologies, especially artificial intelligence, big data analysis, virtual simulation technology, etc.; through urban digital intelligence deduction, urban planning and governance can be more scientifically guided, resource allocation can be optimized, urban management efficiency can be improved, and the diverse needs of citizens can be met; in life, the problem of urban traffic congestion has always attracted much attention, and in the existing technology, the analysis ability of urban traffic data is insufficient, and the identification and governance of traffic congestion points are not refined enough; it is difficult to monitor traffic information in real time, resulting in low urban traffic management ability. Summary of the Invention

[0003] The purpose of the present invention is to provide an urban digital intelligence deduction system and method based on big data analysis to solve the problems raised in the above background art.

[0004] To solve the above technical problems, the present invention provides the following technical solution: An urban digital intelligence deduction method based on big data analysis, the method comprising the following steps:

[0005] S10. Based on the land use and road planning of the city, establish a digital model of the city, and deploy the same road facility environment as the city in the digital model;

[0006] S20. Collect urban traffic data, and analyze the collected urban traffic data to determine the types of travel modes of citizens on urban traffic roads;

[0007] S30. Establish a time management model, analyze the correlation between the change in the number of people taking public transportation and the change in urban vehicle flow in urban traffic data in different time periods, and predict the total urban vehicle flow at the next moment;

[0008] S40. According to the collected urban traffic data and the predicted total urban vehicle flow at the next moment, simulate and deduce in the digital model, and calculate the urban traffic congestion value at the next moment.

[0009] Wherein, the types of travel modes include public transportation road travel and individual road travel; the public transportation road travel refers to the travel of public transportation vehicles that will affect urban traffic congestion; the individual road travel refers to the travel of non-public transportation vehicles that will affect urban traffic congestion.

[0010] Further, divide the city into N block areas; determine the total area S1, S2, ..., S of each block area N , the floor area s1, s2, ..., s of the traffic roads in each block area N and the number of traffic road intersections n1, n2, ..., n in each block area N ; divide the block areas in the digital model and simulate the road facility environment;

[0011] where N represents the number of divided block areas; i = 1, 2, ..., N; S i represents the total area of the corresponding i-th block area; s i represents the floor area of the traffic roads in the i-th block area; n i represents the number of traffic road intersections in the i-th block area;

[0012] By dividing the city into different block areas, the more detailed the divided block areas are, the more accurate the analysis of urban traffic data on personnel flow will be, thus improving the accuracy of automatic coordination of traffic light durations.

[0013] Further, the method steps of step S20 are as follows:

[0014] S201. Determine the travel modes of citizens on public transportation roads; according to the card swiping and traffic payment records of citizens, analyze the boarding and alighting data of traffic stations in each block area when citizens take public transportation, and obtain sets A and B; where T represents different days in the analyzed urban traffic data; t represents different timestamps within a day; represents the change of the boarding passenger flow of citizens taking public transportation in the i-th block area over time t under different days T; represents the change of the alighting passenger flow of citizens taking public transportation in the i-th block area over time t under different days T;

[0015] S202. Determine the travel modes of individual citizens on roads; according to road monitoring data, identify vehicles, monitor the traffic flow of urban traffic roads in each block area, regard non-public transportation vehicles as vehicles for individual citizens' road travel, and analyze the traffic flow change data of non-public transportation in each block area to obtain set C; where represents the change of the traffic flow of non-public transportation in the i-th block area over time t under different days T.

[0016] Further, the method steps of step S30 are as follows:

[0017] S301. Establish a time management model, adopt the RNN algorithm, and based on the public transportation road trips of citizens, analyze the relationship between the change in the number of people flow in urban public transportation and the change in the non-public transportation vehicle flow at the next moment; according to the calculation formula:

[0018] c t+1 =f(W cc c t +W cd (a t -b t )+ε);

[0019] Among them, c t+1 represents the predicted non-public transportation vehicle flow at the (t + 1)th moment; c t represents the current non-public transportation vehicle flow at the tth moment; a t represents the number of people getting on the public transportation by citizens at the current tth moment; b t represents the number of people getting off the public transportation by citizens at the current tth moment; W cc represents the weight for c t ; W cd represents the weight for a t -b t ; ε represents the bias;

[0020] Train the above calculation formula according to sets A, B, and C;

[0021] Since the travel modes of citizens on urban transportation roads are different, by collecting the change in the number of people flow on public transportation in real time, it is used to reflect the number of active people flow on urban transportation, so as to predict the urban transportation volume at the next moment; through the RNN algorithm, in-depth analysis of the time series data of urban transportation is carried out, improving the accuracy of the system's data analysis;

[0022] S302. Determine the public transportation vehicle flow in each sector area at the (t + 1)th moment according to the operation data of urban public transportation vehicles, predict the total vehicle flow in each sector area of the city at the (t + 1)th moment, according to the calculation formula:

[0023] H i,t+1 =c i,t+1 +g i,t+1 ;

[0024] Among them, c i,t+1 represents the predicted non-public transportation vehicle flow in the ith sector area at the (t + 1)th moment; g i,t+1 represents the public transportation vehicle flow in the ith sector area at the (t + 1)th moment; H i,t+1 represents the predicted total vehicle flow in the ith sector area at the (t + 1)th moment.

[0025] Further, the method steps of step S40 are as follows:

[0026] S401. Monitor the traffic flow at urban traffic road intersections; based on historical urban traffic road congestion data, when determining traffic road congestion, determine the maximum distance that vehicles move on the corresponding traffic light section under different green light display cycle durations Δt of the traffic lights at the traffic road intersections. Determine the vehicle queuing waiting distance L on each traffic light corresponding section when the traffic light is red. t ; Compare L t with to determine whether there is congestion on the traffic road section; when , it is determined that there is traffic road congestion on the current traffic light corresponding section; when , it is determined that the traffic on the current traffic light corresponding section is normal.

[0027] Among them, t represents the time stamp.

[0028] S402. Determine the number of congested road sections Y 1,t , Y 2,t ,..., Y N,t in each block area at the current t moment; calculate the traffic congestion value of each block area in the city at the next moment according to the calculation formula:

[0029]

[0030] Among them, Z i,t+1 represents the traffic congestion value of the i-th block area at the calculated t + 1 moment; Y i,t represents the number of congested road sections in the i-th block area at the t moment.

[0031] represents the evacuation ability of the road in the block area for vehicles. The larger the floor area of the traffic road and the more intersections, it indicates that the urban traffic network is more developed and the evacuation ability for vehicles is better. At the same time, the larger the total area of the corresponding block area, the worse the evacuation ability of the vehicles; H i,t+1 *Y i,t represents the traffic congestion degree. The more current congested road sections and the more total traffic flow, it indicates that the urban traffic is more congested; by calculating the traffic congestion values of each block area, it can better help traffic management personnel to allocate personnel in advance and improve the urban traffic management ability; at the same time, by analyzing the traffic congestion values of each block area, it can better assist personnel in planning and managing the urban traffic.

[0032] Among them, the calculated traffic congestion values of each block area are sent to traffic management personnel.

[0033] An urban digital intelligence deduction system based on big data analysis, which includes an urban digital model management module, a data collection and input module, a correlation analysis module, and an urban traffic deduction calculation module;

[0034] The urban digital model management module is used to establish a digital model of the city based on the land use and road planning of the city, and deploy the same road facility environment as the city in the digital model; the data collection and input module is used to collect urban traffic data and determine the types of travel modes of citizens on urban traffic roads; the correlation analysis module is used to establish a time management model to predict the total urban traffic flow at the next moment; the planned land deduction calculation module is used to simulate and deduce in the digital model according to the collected urban traffic data and the predicted total urban traffic flow at the next moment, and calculate the urban traffic congestion value at the next moment;

[0035] Among them, the types of travel modes include public transportation road travel and individual road travel; public transportation road travel refers to the travel of public transportation vehicles that will affect urban traffic congestion; individual road travel refers to the travel of non-public transportation vehicles that will affect urban traffic congestion.

[0036] Furthermore, the urban digital model management module includes a plate area division management unit, an information data determination unit, and a data input management unit;

[0037] The plate area division management unit is used to divide the city into different plate areas;

[0038] The information data determination unit is used to determine the total area of each plate area, the floor area of traffic roads, and the number of traffic road intersections;

[0039] The data input management unit is used to divide the plate area in the digital model and simulate the road facility environment.

[0040] Furthermore, the data collection and input module includes a public transportation data collection unit and an individual travel data collection unit;

[0041] The public transportation data collection unit is used to analyze the boarding and alighting data of traffic stations in each plate area when citizens take public transportation according to the card swiping and traffic payment records of citizens, and determine the public transportation road travel mode of citizens;

[0042] The individual travel data collection unit is used to identify vehicles according to road monitoring data, monitor the traffic flow of urban traffic roads in each plate area, regard non-public transportation vehicles as citizen individual road travel vehicles, analyze the traffic flow change data of non-public transportation in each plate area, and determine the citizen individual road travel mode.

[0043] Further, the correlation analysis module includes a model analysis and training unit and a total vehicle flow prediction unit;

[0044] The model analysis and training unit is used to establish a time management model, adopt the RNN algorithm, analyze the relationship between the change in the number of people in urban public transportation and the change in non-public transportation vehicle flow at the next moment based on the public transportation road trips of citizens, and train the calculation formula;

[0045] The total vehicle flow prediction unit is used to predict the total vehicle flow in each urban area at the next moment.

[0046] Further, the urban traffic deduction calculation module includes a congested section determination unit, a traffic congestion value calculation unit, and a data sending unit;

[0047] The congested section determination unit is used to determine the number of congested sections in each urban area at the current moment;

[0048] The traffic congestion value calculation unit is used to calculate the traffic congestion value in each urban area at the next moment;

[0049] The data sending unit is used to send the calculated traffic congestion values of each urban area to traffic management personnel.

[0050] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: A urban digital intelligence deduction system and method based on big data analysis are provided. By analyzing and deducing urban traffic data, the traffic congestion values of each urban area are calculated, so as to improve the allocation for traffic management personnel and enhance the urban traffic supervision ability; The personnel flow in the city is monitored in real time, which helps urban planners understand the hot areas of urban activities, and thus better plan urban space and allocate public resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0052] Figure 1 is a schematic structural diagram of a urban digital intelligence deduction system based on big data analysis of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0054] Please refer to Figure 1 , the present invention provides a technical solution: a method for urban digital intelligence deduction based on big data analysis, the method comprising the following steps:

[0055] S10. Based on the land use and road planning of the city, establish a digital model of the city, and deploy the same road facility environment as the city in the digital model;

[0056] S20. Collect urban traffic data, and analyze the collected urban traffic data to determine the types of travel modes of citizens on urban traffic roads;

[0057] S30. Establish a time management model, analyze the correlation between the change in the number of people taking public transportation and the change in urban vehicle flow in urban traffic data in different time periods, and predict the total urban vehicle flow at the next moment;

[0058] S40. According to the collected urban traffic data and the predicted total urban vehicle flow at the next moment, simulate and deduce in the digital model, and calculate the urban traffic congestion value at the next moment;

[0059] Among them, the types of travel modes include public transportation road travel and individual road travel; the public transportation road travel refers to the travel of public transportation vehicles that will affect urban traffic congestion; the individual road travel refers to the travel of non-public transportation vehicles that will affect urban traffic congestion.

[0060] Divide the city into N block areas; determine the total area S1, S2,..., S N of each block area, the floor area s1, s2,..., s N of the traffic roads in each block area, and the number of traffic road intersections n1, n2,..., n N in each block area; divide the block areas in the digital model and simulate the road facility environment;

[0061] Among them, N represents the number of divided block areas; i = 1, 2,..., N; S i represents the total area of the corresponding i-th block area; s i represents the floor area of the traffic roads in the i-th block area; n irepresents the number of traffic road intersections in the \(i\)-th block area.

[0062] The method steps of step S20 are as follows:

[0063] S201. Determine the public transportation road travel mode of citizens; according to the card swiping and transportation payment records of citizens, analyze the boarding and alighting data of traffic stations in each block area when citizens take public transportation, and obtain set \(A\) and set \(B\); where, \(T\) represents different days in the analyzed urban traffic data; \(t\) represents different time stamps within each day; represents the change situation of the boarding passenger flow of citizens taking public transportation in the \(i\)-th block area over time \(t\) under different days \(T\); represents the change situation of the alighting passenger flow of citizens taking public transportation in the \(i\)-th block area over time \(t\) under different days \(T\);

[0064] S202. Determine the individual road travel mode of citizens; according to the road monitoring data, identify vehicles, monitor the traffic flow of urban traffic roads in each block area, regard non-public transportation vehicles as individual road travel vehicles of citizens, and analyze the traffic flow change data of non-public transportation in each block area to obtain set \(C\); where, represents the change situation of the traffic flow of non-public transportation in the \(i\)-th block area over time \(t\) under different days \(T\).

[0065] The method steps of step S30 are as follows:

[0066] S301. Establish a time management model, adopt the RNN algorithm, and analyze the relationship formula between the change situation of the passenger flow in urban public transportation and the change of the traffic flow of non-public transportation at the next moment based on the public transportation road travel of citizens; according to the calculation formula:

[0067] c t+1 = f(W cc c t + W cd (a t - b t ) + ε);

[0068] where, c t+1 represents the predicted traffic flow of non-public transportation at the \(t + 1\) moment; c t represents the current traffic flow of non-public transportation at the \(t\) moment; a t represents the current boarding passenger flow of citizens taking public transportation; b t represents the current alighting passenger flow of citizens taking public transportation; W cc represents the weight for c t ; W cdIndicates for a t -b t as the weight; ε represents the bias;

[0069] Train the above calculation formula according to sets A, B, and C;

[0070] S302. Determine the public transportation vehicle flow in each block area at time t + 1 based on the operation data of urban public transportation vehicles, predict the total vehicle flow in each block area of the city at time t + 1, according to the calculation formula:

[0071] H i,t+1 = c i,t+1 + g i,t+1 ;

[0072] where c i,t+1 represents the non-public transportation vehicle flow in the i-th block area at predicted time t + 1; g i,t+1 represents the public transportation vehicle flow in the i-th block area at time t + 1; H i,t+1 is the predicted total vehicle flow in the i-th block area at time t + 1.

[0073] The method steps of step S40 are as follows:

[0074] S401. Monitor the vehicle flow at urban traffic road intersections; based on historical urban traffic road congestion data, determine the maximum distance that vehicles move on the corresponding traffic light section under different green light display cycle durations Δt when the traffic road is congested at the traffic road intersection, Determine the vehicle queuing waiting distance L on each traffic light corresponding section when the traffic light is red t ; Compare L t with to judge whether there is congestion on the traffic road section; when , judge that there is traffic road congestion on the current traffic light corresponding section; when , judge that the traffic road on the current traffic light corresponding section is normal;

[0075] where t represents the timestamp;

[0076] S402. Determine the number of congested road sections Y 1,t , Y 2,t ,..., Y N,t in each block area at the current time t; calculate the traffic congestion value of each block area of the city at the next moment, according to the calculation formula:

[0077]

[0078] where Z i,t+1Represents the traffic congestion value of the i-th block area at the calculated time t+1; Y i,t Represents the number of congested road sections in the i-th block area at time t;

[0079] Among them, the calculated traffic congestion values of each block area are sent to traffic management personnel.

[0080] An urban digital intelligence deduction system based on big data analysis, which includes an urban digital model management module, a data collection and input module, a correlation analysis module, and an urban traffic deduction calculation module;

[0081] The urban digital model management module is used to establish a digital model of the city based on the land use and road planning of the city, and deploy the same road facility environment as the city in the digital model; the data collection and input module is used to collect urban traffic data and determine the types of travel modes of citizens on urban traffic roads; the correlation analysis module is used to establish a time management model to predict the total urban traffic flow at the next moment; the planned land deduction calculation module is used to simulate and deduce in the digital model according to the collected urban traffic data and the predicted total urban traffic flow at the next moment, and calculate the urban traffic congestion value at the next moment;

[0082] Among them, the types of travel modes include public transportation road travel and individual road travel; public transportation road travel refers to the travel of public transportation vehicles that will affect urban traffic congestion; individual road travel refers to the travel of non-public transportation vehicles that will affect urban traffic congestion.

[0083] The urban digital model management module includes a block area division management unit, an information data determination unit, and a data input management unit;

[0084] The block area division management unit is used to divide the city into different block areas;

[0085] The information data determination unit is used to determine the total area of each block area, the floor area of traffic roads, and the number of traffic road intersections;

[0086] The data input management unit is used to divide the block areas in the digital model and simulate the road facility environment.

[0087] The data collection and input module includes a public transportation data collection unit and an individual travel data collection unit;

[0088] The public transportation data collection unit is used to analyze the boarding and alighting data of traffic stations in each block area when citizens take public transportation according to the citizens' card swiping and traffic payment records, and determine the public transportation road travel mode of citizens;

[0089] The individual travel data collection unit is used to identify vehicles based on road monitoring data, monitor the traffic flow of urban traffic roads in each plate area, regard non-public transportation vehicles as citizens' individual road travel vehicles, analyze the traffic flow change data of non-public transportation in each plate area, and determine the individual road travel modes of citizens.

[0090] The correlation analysis module includes a model analysis and training unit and a total traffic flow prediction unit;

[0091] The model analysis and training unit is used to establish a time management model, adopt the RNN algorithm, analyze the relationship between the change in the number of people in urban public transportation and the change in non-public transportation traffic flow at the next moment based on citizens' public transportation road travel, and train the calculation formula;

[0092] The total traffic flow prediction unit is used to predict the total traffic flow in each plate area of the city at the next moment.

[0093] The urban traffic deduction calculation module includes a congested section determination unit, a traffic congestion value calculation unit, and a data sending unit;

[0094] The congested section determination unit is used to determine the number of congested sections in each plate area at the current moment;

[0095] The traffic congestion value calculation unit is used to calculate the traffic congestion value in each plate area of the city at the next moment;

[0096] The data sending unit is used to send the calculated traffic congestion value of each plate area to traffic management personnel.

[0097] In this embodiment:

[0098] This system is specifically an intelligent deduction system for urban traffic data; in this system, based on the land use and road planning of the city, a digital model of the city is established, the same road facility environment as the city is deployed in the digital model, and the city is divided into 10 plate areas;

[0099] Determine the total area S1, S2,..., S 10 of each plate area, the occupied area s1, s2,..., s 10 of the traffic roads in each plate area, and the number of traffic road intersections n1, n2,..., n 10 in each plate area; divide the plate areas in the digital model and simulate the road facility environment;

[0100] Collect urban traffic data, analyze the collected urban traffic data to determine the public transportation road travel modes of citizens, and based on the card - swiping and transportation payment records of citizens, analyze the boarding and alighting data of traffic stations in each block area when citizens take public transportation to obtain set A and set B; determine the individual road travel modes of citizens, identify vehicles according to road monitoring data, monitor the traffic flow of urban traffic roads in each block area, regard non - public transportation vehicles as individual road travel vehicles of citizens, and analyze the traffic flow change data of non - public transportation in each block area to obtain set C;

[0101] Establish a time management model, adopt the RNN algorithm, and based on the public transportation road travel of citizens, analyze the relationship formula between the change in the number of people in urban public transportation and the change in the traffic flow of non - public transportation vehicles at the next moment; according to the calculation formula:

[0102] c t+1 =f(W cc c t +W cd (a t -b t )+ε);

[0103] According to sets A, B, and C, train the above - mentioned calculation formula; respectively determine the values of W cc 、W cd and ε;

[0104] According to the operation data of urban public transportation vehicles, determine the traffic flow of public transportation in each block area at time t + 1, predict the total traffic flow in each block area of the city at time t + 1, according to the calculation formula:

[0105] H i,t+1 =c i,t+1 +g i,t+1 ;

[0106] Monitor the traffic flow at urban traffic road intersections; based on historical urban traffic road congestion data, determine that when the traffic road is congested, for traffic lights at urban traffic road intersections, under different green - light display cycle durations Δt, the maximum distance that vehicles move on the corresponding traffic - light sections Determine the queuing distance L t of vehicles on each section corresponding to the traffic lights when the traffic light is red, judge whether there is congestion on the traffic road section, and determine the number of congested sections Y 1,t 、Y 2,t 、...、Y 10,t in each block area at the current time t; calculate the traffic congestion value of each block area of the city at the next moment, according to the calculation formula:

[0107]

[0108] Send the calculated traffic congestion values of each section area to the traffic management personnel.

[0109] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0110] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A city digital intelligence deduction method based on big data analysis, characterized by: The method comprises the following steps: S10. Based on the city’s land use and road planning, a digital model of the city is established, and the same road facilities environment as the city is deployed in the digital model; S20, collecting urban traffic data, and analyzing the collected urban traffic data to determine the travel mode type of citizens on urban traffic roads; S30, establishing a time management model, analyzing the correlation between changes in the flow of people taking public transportation and changes in the flow of vehicles in the city in different time periods, and predicting the total flow of vehicles in the city at the next moment; S40, based on the collected urban traffic data and the predicted total urban traffic volume at the next moment, simulate and deduce in the digital model to calculate the urban traffic congestion value at the next moment; The travel mode types include public transportation road travel and individual road travel; the public transportation road travel refers to public transportation travel that will affect urban traffic congestion; the individual road travel refers to non-public transportation travel that will affect urban traffic congestion; Divide the city into N plate areas; determine the total area of ​​each plate area S1, S2, ..., S N , the area occupied by the traffic roads in each block area is s1, s2, ..., s N and the number of traffic road intersections in each block area n1, n2, ..., n N ; Divide the plate area in the digital model and simulate the road facility environment; Where N represents the number of divided plate areas; i = 1, 2, ..., N; S i represents the total area of ​​the corresponding i-th plate region; s i represents the area occupied by the traffic roads in the ith block area; n i represents the number of traffic road intersections in the i-th block area; The method steps of step S40 are: S401, monitoring the traffic flow at the urban traffic road intersection; based on the historical urban traffic road congestion data, determining the maximum distance that vehicles move on the corresponding traffic light section under different green light display cycle lengths Δt of the traffic lights at the traffic road intersection when the traffic road is congested Determine the waiting distance L of vehicles on the road sections corresponding to each traffic light when the traffic light is red t ; L t and Compare and judge whether there is congestion on the traffic road section; When , it is judged that there is traffic congestion on the road section corresponding to the current traffic light; when When the traffic on the road section corresponding to the current traffic light is judged to be normal; Wherein, t represents the timestamp; S402: Determine the number Y of congested road sections in each block area at the current time t 1,t , Y 2,t , ..., Y N,t ; Calculate the traffic congestion value of each block area in the city at the next moment, according to the calculation formula: Among them, Z i,t+1 represents the traffic congestion value of the i-th plate area at time t+1; Y i,t H represents the number of congested sections in the i-th block area at time t; i,t+1 It represents the predicted total traffic volume of the ith plate area at time t+1; Among them, the calculated traffic congestion value of each block area is sent to the traffic management personnel.

2. According to the method of city digital intelligence deduction based on big data analysis according to claim 1, it is characterized by: The method steps of step S20 are: S201, determine the public transportation road travel mode of citizens; according to the citizens' card swiping and transportation payment records, analyze the boarding and alighting data of the citizens at the transportation stations in each block area when they take public transportation, and obtain set A and set B; wherein, T represents different days in the analyzed urban traffic data; t represents different timestamps within each day; It represents the change of the passenger flow of citizens taking public transportation in the i-th block area with time t on different days T; It represents the change of the flow of people getting off public transportation in the i-th block area with time t on different days T; S202, determine the individual road travel mode of citizens; identify vehicles based on road monitoring data, monitor the traffic volume of urban traffic roads in each block area, regard non-public transportation vehicles as individual road travel vehicles of citizens, analyze the traffic volume change data of non-public transportation in each block area, and obtain set C; where, It represents the change of non-public transportation traffic volume in the i-th block area with time t on different days T.

3. The method for urban digital intelligence deduction based on big data analysis according to claim 2 is characterized by: The method steps of step S30 are: S301, establish a time management model, adopt RNN algorithm, based on citizens' public transportation road travel, analyze the relationship between the change of passenger flow in urban public transportation and the change of non-public transportation vehicle flow at the next moment; according to the calculation formula: c t+1 =f(W cc c t +W cd (a t -b t )+ε); Among them, c t+1 represents the predicted non-public transportation traffic flow at time t+1; c t represents the traffic volume of non-public transportation at the current time t; a t represents the flow of citizens boarding public transportation at the current time t; b t represents the flow of people getting off public transportation at the current time t; W cc For c t The weight of cd For a t -b t The weight of ; ε represents paranoia; According to the sets A, B and C, the above calculation formula is trained; S302, based on the operation data of urban public transportation vehicles, determine the public transportation vehicle flow of each block area at time t+1, and predict the total vehicle flow of each block area of ​​the city at time t+1, according to the calculation formula: H i,t+1 =c i,t+1 +g i,t+1 ; Among them, c i,t+1 represents the predicted non-public transportation traffic volume in the ith block area at time t+1; g i,t+1 Represents the public transportation traffic volume in the i-th block area at time t+1.

4. A city digital intelligence deduction system based on big data analysis, using the city digital intelligence deduction method based on big data analysis as claimed in claim 1, characterized in that: The system includes a city digital model management module, a data collection and input module, a correlation analysis module, and a city traffic simulation and calculation module; The city digital model management module is used to establish a digital model of the city based on the city's land use and road planning, and deploy the same road facilities environment as the city in the digital model; the data collection and input module is used to collect urban traffic data and determine the type of travel mode of citizens on urban traffic roads; the correlation analysis module is used to establish a time management model and predict the total urban vehicle flow at the next moment; the planned land use deduction and calculation module is used to simulate and deduce in the digital model based on the collected urban traffic data and the predicted total urban vehicle flow at the next moment, and calculate the urban traffic congestion value at the next moment; Among them, the travel mode types include public transportation road travel and individual road travel; the public transportation road travel refers to public transportation travel that will affect urban traffic congestion; the individual road travel refers to non-public transportation travel that will affect urban traffic congestion.

5. The city digital intelligence deduction system based on big data analysis according to claim 4 is characterized by: The city digital model management module includes a plate area division management unit, an information data determination unit and a data entry management unit; The block area division management unit is used to divide the city into different block areas; The information data determination unit is used to determine the total area of ​​each block area, the area occupied by the traffic roads and the number of traffic road intersections; The data entry management unit is used to divide the plate area in the digital model and simulate the road facility environment.

6. The city digital intelligence deduction system based on big data analysis according to claim 5 is characterized by: The data collection and entry module includes a public transportation data collection unit and an individual travel data collection unit; The public transportation data collection unit is used to analyze the boarding and alighting data of the citizens at the transportation stations in each block area when the citizens take public transportation according to the citizens' card swiping and transportation payment records, and determine the citizens' public transportation road travel mode; The individual travel data collection unit is used to identify vehicles based on road monitoring data, monitor the traffic volume of urban traffic roads in each block area, regard non-public transportation vehicles as individual road travel vehicles of citizens, analyze the traffic volume change data of non-public transportation in each block area, and determine the individual road travel mode of citizens.

7. The city digital intelligence deduction system based on big data analysis according to claim 6 is characterized by: The correlation analysis module includes a model analysis training unit and a total vehicle flow prediction unit; The model analysis and training unit is used to establish a time management model, using an RNN algorithm, based on citizens' public transportation road travel, to analyze the relationship between the change in passenger flow in urban public transportation vehicles and the change in non-public transportation vehicle flow at the next moment, and to train the calculation formula; The total vehicle flow prediction unit is used to predict the total vehicle flow of each block area in the city at the next moment.

8. The city digital intelligence deduction system based on big data analysis according to claim 7 is characterized by: The urban traffic deduction calculation module includes a congested road section determination unit, a traffic congestion value calculation unit and a data sending unit; The congested road section determination unit is used to determine the number of congested road sections in each block area at the current moment; The traffic congestion value calculation unit is used to calculate the traffic congestion value of each block area in the city at the next moment; The data sending unit is used to send the calculated traffic congestion value of each block area to the traffic management personnel.

Images