Smart city operation decision-making method and system based on big data and AI big model

Abstract

The invention discloses a smart city operation decision-making method and system based on big data and an AI big model, relates to the technical field of city smart management, and solves the technical problem that road resources cannot be efficiently utilized due to the lack of deep analysis and dynamic response to real-time traffic data. According to the invention, a city is scientifically divided into management and control areas, a to-be-regulated area is accurately screened out based on comparison of historical traffic flow data and a preset value, and the time length of the signal lamp is dynamically regulated and controlled in combination with multi-dimensional parameters such as a circulation speed and an increase rate through gradual detailed analysis from the to-be-regulated area to the to-be-regulated area and a to-be-regulated time period. Compared with a traditional fixed signal lamp timing scheme, the traffic flow change can be responded in real time, the vehicle waiting time is shortened, the intersection traffic capacity is improved, traffic congestion is relieved, the traffic data value is fully mined based on big data analysis, and a scientific basis is provided for traffic operation decision making through deep processing and analysis of traffic flow data.

Description

Technical Field

[0001] The present invention relates to the technical field of urban intelligent management, and specifically to a smart city operation decision-making method and system based on big data and AI large models. Background Art

[0002] With the acceleration of the urbanization process, the urban traffic flow is increasing day by day, and problems such as traffic congestion and low traffic efficiency are becoming more and more serious.

[0003] According to the patent application with the publication number CN118333430A, a smart city operation decision-making method and system based on big data and AI large models are disclosed. The method includes: inputting the obtained multi-source data set into a generative adversarial network for data enhancement to obtain a target data set; inputting the target data set into a Bayesian network for data fusion to obtain fused data; inputting the fused data into a proximal policy optimization algorithm for decision-making strategy analysis to obtain multiple decision-making strategy data sets and inputting them into a multi-objective optimization algorithm for strategy optimization to obtain multiple optimized strategy data sets, and generating a city operation plan according to the multiple optimized strategy data sets; constructing a visualization chart for the city operation plan to obtain visualization chart data, and transmitting the visualization icon data to a preset data display terminal.

[0004] However, traditional smart city traffic operation decision-making methods mostly rely on fixed signal timing plans and empirical traffic management strategies, lacking in-depth analysis and dynamic response to real-time traffic data. In the prior art, the division of traffic control areas is often too rough to accurately identify key areas of traffic congestion; it is also difficult to scientifically adjust the signal light duration according to the real-time changes and trends of traffic flow, resulting in inefficient utilization of road resources. The level of intelligence and refinement of urban traffic management urgently needs to be improved. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides a smart city operation decision-making method and system based on big data and AI large models, which solves the problem of inefficient utilization of road resources caused by the lack of in-depth analysis and dynamic response to real-time traffic data.

[0006] To achieve the above objectives, the present invention is realized through the following technical solutions: A smart city operation decision-making method based on big data and AI large models, which specifically includes the following steps: Divide the control areas of the city according to traffic flow data, and screen out the control areas greater than the preset value and record them as the areas to be regulated; Determine the areas to be adjusted according to the traffic flow data of the areas to be regulated, classify their traffic time period information to obtain classified time period information, and at the same time compare their total traffic volume with the traffic volume threshold to obtain adjustment time period information; Calculate the average vehicle delay corresponding to different traffic intersections in the area to be regulated based on the obtained regulation time period information, select the one with the largest value to determine the target intersection, and calculate the corresponding circulation speed and increase rate at the same time; According to the traffic circulation speed and increase rate, calculate the remaining required time, add it to the current signal time, compare the sum with the preset value to determine whether adjustment is needed. If adjustment is needed, calculate the new duration in combination with the increase rate, and compare it with the preset value again to generate the duration adjustment information.

[0007] As a further solution of the present invention, the specific method for obtaining the area to be regulated is as follows: Divide the city to obtain the controlled areas, label them as i, and i = 1, 2,..., j, where j represents the number of corresponding controlled areas. At the same time, obtain the historical data of the controlled areas, and obtain the traffic flow data corresponding to the controlled area i in the historical data. Compare it with the preset value, and screen out the controlled areas greater than the preset value and mark them as the areas to be regulated.

[0008] As a further solution of the present invention, the specific method for obtaining the classified time period information is as follows: Obtain all the areas to be regulated, take one group as an example and record it as the target object, obtain all the traffic intersections of the target object, and at the same time obtain the traffic flow data of the traffic intersections. Then determine the area to be adjusted according to the traffic flow data, and then obtain the traffic time period information corresponding to the area to be adjusted, and classify it in combination with the traffic flow data corresponding to different traffic time period information to obtain the classified time period information.

[0009] As a further solution of the present invention, the specific method for obtaining the regulation time period information is as follows: Perform secondary classification according to the traffic flow data corresponding to the classified time period information, calculate the total traffic volume corresponding to the classified time period information, compare it with the traffic volume threshold, mark the classified time period with the total traffic volume greater than the traffic volume threshold as the time period to be adjusted, and generate the regulation time period information; And so on, perform the same processing on all the areas to be regulated to generate the corresponding regulation time period information.

[0010] As a further solution of the present invention, the specific method for determining the target intersection is as follows: Obtain the regulation time period information, and at the same time obtain the traffic intersections corresponding to the regulation time period information, label them as a, and a = 1, 2, 3, 4, and obtain the traffic volume corresponding to the traffic intersection a. Calculate the average vehicle delay corresponding to the traffic intersection a. According to the formula Calculate to obtain the average vehicle delay Da, where m is the total number of observed vehicles, t i is the actual time when the o-th vehicle passes the stop line, t0 is the theoretical time to pass the stop line, and select the traffic intersection a with the largest average vehicle delay as the standard and record it as the target intersection.

[0011] As a further solution of the present invention, the specific method for calculating the circulation speed and increase rate corresponding to the target intersection is as follows: Calculate the circulation speed of the target intersection, obtain the circulation volume corresponding to the target intersection within time T, and according to the formula calculate the circulation speed G corresponding to the target intersection, where L is the circulation volume, is the influence factor, and the specific value is set by the operator; Calculate the increase rate of the target intersection, obtain the increase amount corresponding to the target intersection within time T1, and according to the formula calculate the increase rate F corresponding to the target intersection, where Z is the increase amount, is the influence factor.

[0012] As a further solution of the present invention, the specific method for generating the duration adjustment information is as follows: First, obtain the circulation volume and remaining volume within the signal light duration, calculate the remaining required time according to the formula in combination with the circulation speed, then sum it with the signal light duration to obtain the total signal duration, compare the total signal duration with the preset value. If it is less than or equal to the preset value, directly generate the duration adjustment information accordingly; if it is greater than the preset value, generate a secondary adjustment signal and further analyze it.

[0013] As a further solution of the present invention, the specific method for analyzing the secondary adjustment signal is as follows: Analyze the secondary adjustment signal to obtain the increase rate, calculate the duration to be adjusted according to the formula, and compare it with the preset value: if the duration to be adjusted is greater than the preset value, generate the duration adjustment information based on the preset value; if it is less than the preset value, generate the duration adjustment information based on the duration to be adjusted.

[0014] The smart city operation decision-making system based on big data and AI large models includes a data acquisition unit, a regional analysis unit, a duration adaptive adjustment unit, and a decision information output unit; The data acquisition unit is used to acquire the traffic flow data of different regions of the city and transmit it to the regional analysis unit.

[0015] The regional analysis unit is used to divide different regions according to the acquired traffic flow data to obtain the regions to be regulated, determine the adjustment time period based on the historical data of the regions to be regulated, generate adjustment time period information, and calculate the circulation speed and increase rate corresponding to different traffic intersections in the regions to be regulated. Then, transmit the two to the duration adaptive adjustment unit; The duration adaptive adjustment unit is used to adjust and analyze the signal light duration of the traffic intersection according to the obtained flow velocity and increase rate, calculate the remaining required time based on the corresponding traffic volume in the traffic intersection signal light in combination with the flow velocity, sum it with the signal light duration and compare its magnitude with the preset value to generate duration adjustment information or a secondary adjustment signal; Analyze the secondary adjustment signal, calculate the duration to be adjusted according to the increase rate, compare it with the preset value, generate duration adjustment information, and transmit it to the decision information output unit at the same time; The decision information output unit is used to display the obtained duration adjustment information to the corresponding operator.

[0016] The present invention provides a smart city operation decision-making method and system based on big data and AI large models. Compared with the prior art, it has the following beneficial effects: By scientifically dividing the control area of the city in the present invention and comparing with the preset value based on the historical traffic flow data, the area to be regulated is accurately screened. Compared with the traditional extensive area division, it can more accurately locate the traffic congestion hotspots, concentrate traffic management resources on key areas, and improve management efficiency.

[0017] The present invention gradually refines the analysis from the area to be regulated to the area to be adjusted and the time period to be adjusted, and dynamically regulates the signal light duration by combining multi-dimensional parameters such as flow velocity and increase rate. Compared with the traditional fixed signal light timing scheme, it can respond to traffic flow changes in real time, effectively reduce the vehicle waiting time, improve the intersection passing capacity, and relieve traffic congestion.

[0018] Based on big data analysis, the present invention fully excavates the value of traffic data, provides a scientific basis for traffic operation decision-making through in-depth processing and analysis of traffic flow data. Compared with the traditional decision-making method relying on experience, it realizes the transformation from experience-driven to data-driven, from static management to dynamic optimization, significantly improves the intelligent level and accuracy of smart city traffic operation decision-making, and promotes the efficient and sustainable operation of the urban traffic system. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flowchart of the method steps of the present invention; Figure 2 It is a block diagram of the system principle of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described 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.

[0021] Embodiment 1: Please refer to Figure 1 , this application provides a smart city operation decision-making method based on big data and AI large models. The method specifically includes the following steps: Step S1: Collect traffic flow data in different regions of the city, divide the city into different regions, and at the same time obtain the historical data corresponding to different regions. Determine the regions to be regulated according to the historical data, and the specific determination method is as follows: Divide the city to obtain control regions, numbered as i, where i = 1, 2,..., j, and j represents the number of corresponding control regions. At the same time, obtain the historical data of the control regions, and obtain the traffic flow data corresponding to the control region i in the historical data. Here, the traffic flow data represents the vehicle flow corresponding to time T. Compare the obtained traffic flow data with a preset value, and screen out the control regions greater than the preset value, and mark them as regions to be regulated.

[0022] For example, after analysis, it is found that the average vehicle flow during the off-peak period in each control region of this city is 300 vehicles per hour, and the standard deviation is 50 vehicles per hour. Considering traffic fluctuations and management requirements, the preset value during the off-peak period is set to 400 vehicles per hour; the average vehicle flow during the morning and evening peak periods is 800 vehicles per hour, and the standard deviation is 100 vehicles per hour. The preset value during the peak period is set to 1000 vehicles per hour. In a certain analysis, the vehicle flows in the control regions numbered 5, 12, and 23 during the evening peak period reach 1100 vehicles per hour, 1050 vehicles per hour, and 1200 vehicles per hour respectively, all exceeding the evening peak preset value of 1000 vehicles per hour. Therefore, these three regions are marked as regions to be regulated.

[0023] Step S2: Obtain all regions to be regulated, and at the same time determine the areas to be adjusted corresponding to the regions to be regulated. Combine the historical data corresponding to the areas to be adjusted to determine the adjustment time period, and generate corresponding adjustment time period information. The specific processing method is as follows: Obtain all the areas to be regulated, and take one group as an example and denote it as the target object. Obtain all the traffic intersections of the target object, and at the same time obtain the traffic flow data of the traffic intersections. Then determine the areas to be adjusted according to the traffic flow data, and the processing method here is the same as that in step S1. Specifically, the specific values of the preset values are different. Then obtain the traffic period information corresponding to the areas to be adjusted, and classify them in combination with the traffic flow data corresponding to different traffic period information to obtain classified period information. At the same time, perform secondary classification according to the traffic flow data corresponding to the classified period information. Specifically, calculate the total traffic volume corresponding to the classified period information and compare it with the traffic volume threshold, and the specific value of the traffic volume threshold is set by the operator. Mark the classified periods with a total traffic volume greater than the traffic volume threshold as the periods to be adjusted, and generate adjustment period information; And so on, perform the same processing on all the areas to be regulated to generate the corresponding adjustment period information.

[0024] For example, if the target object is the core business district of a city, the preset value for the off-peak period of the surrounding traffic intersections is set to 500 vehicles per hour, and the preset value for the peak period is set to 1200 vehicles per hour. Compare the traffic flow data of each traffic intersection with the corresponding preset value, and screen out the traffic intersections with a traffic flow greater than the preset value and mark them as the areas to be adjusted. For example, in the area to be regulated numbered 5, it is found that the traffic volumes of traffic intersections A, B, and C during the evening peak period are 1300 vehicles per hour, 1400 vehicles per hour, and 1250 vehicles per hour respectively, all exceeding the evening peak preset value of 1200 vehicles per hour. Determine these three intersections as the areas to be adjusted, collect the traffic flow data of each period within a certain period (such as one week) in the areas to be adjusted, and according to the change law of the traffic flow, combined with the conventional morning peak (7:00 - 9:00), noon peak (11:30 - 13:30), evening peak (17:00 - 19:00) and off-peak period division criteria, conduct a primary classification of the traffic period information to obtain classified period information. For example, for traffic intersection A in the area to be adjusted, divide the periods of each day into four categories: morning peak, noon peak, evening peak, and off-peak, and record the traffic flow data corresponding to each category.

[0025] Calculate the total traffic flow corresponding to each classified time period information, that is, the total number of vehicles passing through the intersection during that time period. Operators set a traffic flow threshold based on the traffic carrying capacity of the area, historical traffic flow data, and traffic management objectives. For example, for the area to be adjusted in the commercial district, the traffic flow threshold is set at 800 vehicles per time period. Compare the total traffic flow of each classified time period with the traffic flow threshold, mark the classified time periods with a total traffic flow greater than the traffic flow threshold as time periods to be adjusted, and generate detailed adjustment time period information, including the specific time range of the time period to be adjusted, the total traffic flow value, etc. For example, at traffic intersection A, during the evening peak period (17:00 - 19:00), the total traffic flow is 1100 vehicles, which is greater than the traffic flow threshold of 800 vehicles. Mark this time period as a time period to be adjusted.

[0026] Step S3: Obtain the adjustment time period information. At the same time, obtain the traffic intersections corresponding to the adjustment time period information, label them as a, and a = 1, 2, 3, 4. Here, a crossroads is taken as an example for analysis. Obtain the traffic flow corresponding to traffic intersection a, and sort them in descending order according to the traffic flow. Then calculate the average vehicle delay corresponding to traffic intersection a according to the formula Calculate the average vehicle delay, where m is the total number of observed vehicles, Da is the average vehicle delay, t i is the actual time when the o-th vehicle passes the stop line, t0 is the theoretical time when the vehicle passes the stop line at the free flow speed assuming no signal lights, and select the traffic intersection a with the largest average vehicle delay as the target intersection. At the same time, obtain the signal light duration corresponding to the target intersection. Here, the signal light duration includes the red light duration and the green light duration, and calculate the traffic flow speed and increase rate corresponding to the target intersection; Calculate the traffic flow speed of the target intersection, obtain the traffic flow corresponding to the target intersection within time T. Here, the traffic flow represents the number of vehicles passing through during the green light duration. The specific time T represents the green light duration, and calculate according to the formula Calculate the traffic flow speed G corresponding to the target intersection, which refers to the number of vehicles passing through a specific lane of a traffic intersection per unit time, with the unit of "vehicles / minute". Where L is the traffic flow, is the influence factor, and the specific value is set by the operator; Calculate the increase rate of the target intersection, obtain the increase amount corresponding to the target intersection within time T1. Here, the increase amount represents the increased traffic flow during the red light duration, and time T1 represents the red light duration, and calculate according to the formula Calculate the increase rate F corresponding to the target intersection, which reflects the change trend of traffic flow over time, that is, the growth rate of traffic flow per unit time. Where Z is the increase amount, is the influence factor.

[0027] Step S4: Conduct a regulatory analysis of the signal light duration based on the obtained flow velocity and increase rate, obtain the corresponding traffic volume within the signal light duration, and obtain the corresponding remaining volume. Calculate the remaining required time in combination with the corresponding flow velocity according to the formula remaining required time = (remaining volume ÷ flow velocity) × c. Assume that the current signal light duration of the south approach of a certain intersection is 60 seconds, the flow velocity is 10 vehicles per minute, the remaining volume is 8 vehicles, and the influence factor c is set to 1.1. Then the remaining required time = (8 ÷ 10) × 1.1 × 60 = 52.8 seconds. Calculate the remaining required time, where c is the influence factor and the specific value is set by the operator. Sum the obtained remaining required time and the signal light duration to obtain the total signal duration. At the same time, compare the total signal duration with a preset value, and the specific value of the preset value is set by the operator; Sum the remaining required time and the current signal light duration to obtain the total signal duration. In the above example, the total signal duration = 60 + 52.8 = 112.8 seconds, and compare the total signal duration with the preset value set by the operator. If the preset value is 100 seconds, since 112.8 seconds > 100 seconds, it is determined that the total signal duration is unreasonable and a secondary adjustment signal is generated; if the total signal duration is less than the preset value, it means the duration is reasonable, and adjust according to this total signal duration and generate a duration adjustment message.

[0028] If the total signal duration is greater than the preset value, it means the total signal duration is unreasonable and a secondary adjustment signal is generated. On the contrary, if the total signal duration is less than the preset value, it means the total signal duration is reasonable, and adjust according to the total signal duration and generate a duration adjustment message; Analyze the generated secondary adjustment signal to obtain the increase rate. Calculate the duration to be adjusted according to the formula duration to be adjusted = (remaining required time × increase rate) + signal light duration. At the same time, compare the obtained duration to be adjusted with the preset value. If it is greater than the preset value, adjust according to the preset value and generate a duration adjustment message. On the contrary, if it is less than the preset value, adjust according to the duration to be adjusted and generate a duration adjustment message.

[0029] When the total signal duration is unreasonable, analyze the secondary adjustment signal to obtain the increase rate. Calculate the duration to be adjusted according to the formula duration to be adjusted = (remaining required time × increase rate) + signal light duration. For example, the remaining required time is 52.8 seconds, the increase rate is 0.3% per second, and the signal light duration is 60 seconds. Then the duration to be adjusted = (52.8 × 0.003 × 60) + 60 = 69.504 seconds. Compare the duration to be adjusted with the preset value. If the duration to be adjusted is greater than the preset value, adjust according to the preset value and generate a duration adjustment message; if it is less than the preset value, adjust according to the duration to be adjusted. Assume the preset value is 70 seconds, 69.504 seconds < 70 seconds, and finally use 69.504 seconds as the adjustment duration of the signal light for the south approach of this intersection.

[0030] Example 2: Please refer to Figure 2 , this application provides a smart city operation decision-making system based on big data and AI large models, including a data acquisition unit, a regional analysis unit, a duration adaptive adjustment unit, and a decision information output unit, and combined with Figure 2 it can be known that the above functional units are unidirectionally electrically connected to each other.

[0031] Data acquisition unit, which is used to acquire traffic flow data in different regions of the city and transmit it to the regional analysis unit.

[0032] Regional analysis unit, which is used to divide different regions according to the acquired traffic flow data to obtain regions to be regulated, determine the adjustment time period based on the historical data of the regions to be regulated, generate adjustment time period information, and calculate the flow velocity and increase rate corresponding to different traffic intersections in the regions to be regulated. Then, both are transmitted to the duration adaptive adjustment unit, and the processing method here is the same as that of step S3 in Embodiment 1; Duration adaptive adjustment unit, which is used to adjust and analyze the signal light duration of traffic intersections according to the obtained flow velocity and increase rate, calculate the remaining required time according to the traffic volume corresponding to the signal lights at traffic intersections in combination with the flow velocity, sum it with the signal light duration, and compare its size with the preset value to generate duration adjustment information or a secondary adjustment signal; Analyze the secondary adjustment signal, calculate the adjustment duration according to the increase rate, compare it with the preset value, generate duration adjustment information, and transmit it to the decision information output unit at the same time. The specific processing method is the same as that of step S4 in Embodiment 1; Decision information output unit, which is used to display the acquired duration adjustment information to the corresponding operator.

[0033] At the same time, the content not described in detail in this specification belongs to the prior art well-known to those skilled in the art.

[0034] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for urban intelligent operation decision-making based on big data and AI large models, characterized in that, The method specifically includes the following steps: Divide the control areas of the city according to the traffic flow data, and screen the control areas greater than the preset value and record them as the areas to be regulated; Determine the areas to be adjusted according to the traffic flow data of the areas to be regulated, classify their traffic time information to obtain classified time information, and at the same time compare their total traffic volume with the traffic volume threshold to obtain the adjusted time information; Based on the obtained adjusted time information, calculate the average vehicle delay corresponding to different traffic intersections in the areas to be regulated, select the one with the largest value to determine the target intersection, and at the same time calculate its corresponding circulation speed and increase rate; According to the traffic circulation speed and increase rate, calculate the remaining required time, add it to the current signal time and compare it with the preset value to judge whether adjustment is needed. If so, calculate the new duration in combination with the increase rate, and compare it with the preset value again to generate duration adjustment information.

2. The smart city operation decision-making method based on big data and AI large models according to claim 1, wherein The specific way to obtain the areas to be regulated is as follows: Divide the city to obtain control areas, label them as i, and i = 1, 2,..., j, where j represents the corresponding number of control areas. At the same time, obtain the historical data of the control areas, and obtain the traffic flow data corresponding to the control area i in the historical data, compare it with the preset value, and screen the control areas greater than the preset value and mark them as the areas to be regulated.

3. The smart city operation decision-making method based on big data and AI large models according to claim 1, characterized in that The specific way to obtain the classified time information is as follows: Obtain all the areas to be regulated, take one group as an example and record it as the target object, obtain all the traffic intersections of the target object, and at the same time obtain the traffic flow data of the traffic intersections. Then determine the areas to be adjusted according to the traffic flow data, and then obtain the traffic time information corresponding to the areas to be adjusted, and classify them in combination with the traffic flow data corresponding to different traffic time information to obtain the classified time information.

4. The smart city operation decision-making method based on big data and AI large models according to claim 1, wherein, The specific way to obtain the adjusted time information is as follows: Perform secondary classification according to the traffic flow data corresponding to the classified time information, calculate the total traffic volume corresponding to the classified time information, and compare it with the traffic volume threshold. Mark the classified time periods with a total traffic volume greater than the traffic volume threshold as the time periods to be adjusted, and generate the adjusted time information; And so on, perform the same processing on all the areas to be regulated to generate the corresponding adjusted time information.

5. The smart city operation decision-making method based on big data and AI large models according to claim 1, wherein, The specific way to determine the target intersection is as follows: Obtain the adjustment period information, and at the same time obtain the traffic intersections corresponding to the adjustment period information, label them as a, and a = 1, 2, 3, 4, and obtain the traffic flow corresponding to traffic intersection a, calculate the average vehicle delay corresponding to traffic intersection a, according to the formula Calculate the average vehicle delay Da, where m is the total number of observed vehicles, t i is the actual time for the o-th vehicle to pass the stop line, t0 is the theoretical time to pass the stop line, and select the traffic intersection a with the largest average vehicle delay as the standard and label it as the target intersection.

6. The method for making smart city operation decisions based on big data and AI large models according to claim 1, characterized in that, The specific way to calculate its corresponding circulation speed and increase rate is as follows: Calculate the circulation speed of the target intersection, obtain the circulation volume corresponding to the target intersection within time T, and according to the formula calculate the circulation speed G corresponding to the target intersection, where L is the circulation volume, is the influence factor, and the specific value is set by the operator; Calculate the increased rate for the target intersection, obtain the increase corresponding to the target intersection within time T1, and according to the formula calculate to obtain the increased rate F corresponding to the target intersection, where Z is the increase is the influencing factor.

7. The method for making urban operation decisions based on big data and AI large models according to claim 1, wherein The specific way to generate the duration adjustment information is as follows: First, obtain the traffic volume and remaining volume within the signal light duration, calculate the remaining required time according to the formula in combination with the circulation speed, then sum it with the signal light duration to obtain the total signal duration, compare the total signal duration with the preset value. If it is less than or equal to the preset value, directly generate the duration adjustment information accordingly; if it is greater than the preset value, generate a secondary adjustment signal and further analyze it.

8. The method for making urban intelligent operation decisions based on big data and AI large models according to claim 7, wherein, The specific way to analyze the secondary adjustment signal is as follows: Analyze the secondary adjustment signal to obtain the increase rate, calculate the duration to be adjusted according to the formula, and compare it with the preset value: if the duration to be adjusted is greater than the preset value, generate the duration adjustment information based on the preset value; If it is less than the preset value, generate the duration adjustment information based on the duration to be adjusted.

9. A smart city operation decision-making system based on big data and AI large models, which is used to execute the smart city operation decision-making method described in any one of claims 1-8, characterized in that, It includes a data acquisition unit, a regional analysis unit, a duration adaptive adjustment unit, and a decision information output unit; A data acquisition unit, which is used to acquire traffic flow data of different regions in a city and transmit it to the regional analysis unit; A regional analysis unit, which is used to divide different regions according to the acquired traffic flow data to obtain regions to be regulated, determine the time periods to be adjusted based on the historical data of the regions to be regulated, generate adjustment time period information, calculate the flow velocity and increase rate corresponding to different traffic intersections in the regions to be regulated, and then transmit the two to the duration adaptive adjustment unit; A duration adaptive adjustment unit, which is used to adjust and analyze the signal light duration of traffic intersections according to the obtained flow velocity and increase rate, calculate the remaining required time based on the traffic volume corresponding to the signal lights at traffic intersections in combination with the flow velocity, sum it with the signal light duration and compare its magnitude with the preset value to generate duration adjustment information or a secondary adjustment signal; Analyze the secondary adjustment signal, calculate the adjustment duration according to the increase rate, compare it with the preset value, generate duration adjustment information, and transmit it to the decision information output unit at the same time; A decision information output unit, which is used to display the acquired duration adjustment information to the corresponding operator.

Images