A big data-based urban traffic operation management system and method

Abstract

The application provides a kind of city traffic operation management system and method based on big data, by obtaining initial traffic data of city traffic from each database, and the initial traffic data is standardized and integrated, and multidimensional traffic data is obtained, the integration of various data sources is realized, the content of traffic data is enriched, the problem of information island is solved, by based on the multidimensional traffic data, combined with management requirements, build multiple city traffic management models, establish various management models, realize the arrangement of each type of traffic data, provide effective data information for subsequent decision-making, by visualizing the city traffic management model, it is convenient for decision-makers to intuitively understand the traffic operation, according to traffic demand, based on visual display data, combined with artificial intelligence, get traffic decision, realize the precise acquisition of traffic decision, promote green traffic construction and industry governance.

Description

Technical Field

[0001] This invention relates to the field of urban transportation technology, and in particular to an urban transportation operation management system and method based on big data. Background Technology

[0002] With the acceleration of urbanization, traffic congestion and inefficiency have become serious challenges for many cities. The rise of big data technology has provided new solutions for smart city transportation. By collecting, analyzing and applying massive amounts of traffic data, big data can not only help traffic management departments make scientific decisions, but also significantly improve residents' travel experience.

[0003] In urban traffic operation management, traffic data may come from government departments, private enterprises, IoT devices, social media, etc. The integration of this multi-source data brings more comprehensive analysis capabilities, but how to effectively integrate it is a challenge. How to conduct effective analysis based on the integrated multi-dimensional data to help traffic management departments make accurate decisions, promote green transportation construction and industry governance is also an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a big data-based urban traffic operation management system and method to solve the problems mentioned in the background art.

[0005] A big data-based urban traffic operation management system includes:

[0006] The data integration module is used to obtain initial traffic data from various databases on urban traffic, and to standardize and integrate the initial traffic data to obtain multi-dimensional traffic data.

[0007] The model building module is used to construct multiple urban traffic management models based on the multi-dimensional traffic data and in combination with management needs.

[0008] The visual display module is used to visualize the urban traffic management model.

[0009] The traffic decision-making module is used to make traffic decisions based on traffic demand, visualized data, and artificial intelligence.

[0010] Preferably, the data integration module includes:

[0011] The data acquisition unit is used to retrieve initial traffic data from various databases based on a unified API interface;

[0012] The data storage unit is used to distribute the initial traffic data according to the data source to obtain the distributed storage result.

[0013] The data integration unit is used to standardize and integrate the initial traffic data based on multi-data collaborative information and distributed storage results to obtain multi-dimensional traffic data.

[0014] Preferably, the model building module includes:

[0015] The data retrieval unit is used to determine model attributes based on management needs and retrieve target data related to the model attributes from multidimensional traffic data;

[0016] The model building unit is used to construct the model structure based on the model attributes, embed the target data into the model structure, and obtain the urban traffic management model.

[0017] Preferably, the model building module further includes:

[0018] The channel establishment unit is used to establish a real-time interactive channel between the urban traffic management model and target data.

[0019] The real-time update unit is used to update the urban traffic management model in real time based on the update results of the target data through the real-time interaction channel.

[0020] Preferably, the visual display module includes:

[0021] The model analysis unit is used to determine the visual map based on the traffic management scope of the urban traffic management model and to determine the marker points based on the model attributes of the urban traffic management model.

[0022] The heat map creation unit is used to create heat maps for urban traffic management models based on visual maps and marker points;

[0023] The display unit is used to perform data statistics on the heat map and mark and display the statistical results on the heat map.

[0024] Preferably, the traffic decision module includes:

[0025] The demand determination unit is used to determine basic traffic condition requirements and target decision requirements based on traffic demand.

[0026] The weight determination unit is used to determine the participating urban traffic management models based on basic traffic condition requirements, and to determine the model weight of each urban traffic management model.

[0027] The fusion unit is used to perform spatiotemporal model fusion of participating urban traffic management models according to their model weights based on the model attributes of the participating urban traffic management models, so as to obtain basic traffic condition information.

[0028] The association determination unit is used to extract multiple key factors from the basic traffic condition information, and determine the periodic association characteristics between the multiple key factors based on time characteristics, and determine the causal association characteristics between the multiple key factors based on the target decision requirements.

[0029] The model training unit is used to determine the target fusion features based on the periodic correlation features and causal correlation features, and to train the traffic decision model based on the target fusion features and the target decision requirements.

[0030] An intermediate decision-making unit is used to input current traffic data into the traffic decision-making model to obtain an initial traffic decision, and to intelligently intervene in the variable factors in the initial traffic decision to obtain multiple intermediate decisions.

[0031] The decision-making unit is used to determine the trend of public sentiment and the rules for predicting the effect of decisions based on historical data, thereby determining the decision effect score for each intermediate decision, and selecting the intermediate decision with the highest decision effect score as the final traffic decision.

[0032] Preferably, the decision-making unit includes:

[0033] The retrieval unit is used to retrieve key information from the intermediate decision according to the scoring indicators, and obtain key decision information under each scoring indicator.

[0034] The prediction unit is used to determine the effect prediction of key decision information based on the decision effect prediction rules, and to determine the public's sentiment trend rating of the effect prediction based on the trend of public sentiment.

[0035] The scoring unit is used to score the emotional trajectory based on all key decision information, and to obtain the decision effect score corresponding to the intermediate decision.

[0036] Preferably, the data integration unit includes:

[0037] The standardization unit is used to determine the data standard format based on multi-data collaborative information, standardize the data in the distributed storage results based on the data standard format to obtain standard traffic data, and perform semantic extraction analysis on the standard traffic data to obtain traffic environment features.

[0038] The classification unit is used to classify the distributed storage results based on multi-data collaborative information to obtain storage data groups that can be located and integrated.

[0039] The positioning and transformation unit is used to obtain the coordinate system type of each data group in the stored data group, determine the standard coordinate system type, and perform coordinate system transformation on other coordinate system types according to translation and rotation based on the standard coordinate system type, so as to realize the reference alignment of the stored data group and obtain the reference data group.

[0040] The compensation unit is used to acquire the spatial coordinates and sensor features of the reference data set, perform type difference compensation on the reference data set based on the differences in sensor types, perform difference compensation on the reference data set and the environment based on traffic environment features, and obtain the standard data set based on the type difference compensation and the environment difference compensation.

[0041] The calibration unit is used to automatically calibrate the standard data set based on an adaptive calibration algorithm to obtain the target data set;

[0042] A hardware synchronization unit is used to obtain the cable transmission differences and crystal oscillator drift characteristics in the target data group, and to perform hardware synchronization error compensation on the target data group based on the cable transmission differences and crystal oscillator drift characteristics to obtain an intermediate synchronized data group.

[0043] A timestamp synchronization unit is used to obtain the target synchronization data group by aligning the timestamps of the intermediate synchronization data group.

[0044] The integration unit is used to integrate data based on the location and time characteristics of the target synchronized data group to obtain multi-dimensional traffic data.

[0045] Preferably, the integration unit includes:

[0046] The location integration unit is used to integrate the target synchronization data group according to its location characteristics to obtain multi-dimensional location data.

[0047] The time integration unit is used to integrate the multi-dimensional location data according to time characteristics to obtain multi-dimensional traffic data.

[0048] A big data-based urban traffic operation management method includes:

[0049] S1: Obtain initial traffic data from various databases, and standardize and integrate the initial traffic data to obtain multi-dimensional traffic data;

[0050] S2: Based on the aforementioned multi-dimensional traffic data and combined with management needs, construct multiple urban traffic management models;

[0051] S3: Visualize the urban traffic management model;

[0052] S4: Based on traffic demand, traffic decisions are made using visualized data and artificial intelligence.

[0053] Compared with the prior art, the present invention has achieved the following beneficial effects:

[0054] By acquiring initial urban traffic data from various databases and standardizing and integrating the data format, multi-dimensional traffic data is obtained. This integrates various data sources, enriches the content of traffic data, and solves the problem of information silos. Based on this multi-dimensional traffic data and combined with management needs, multiple urban traffic management models are constructed, various management models are established, and various types of traffic data are organized to provide effective data information for subsequent decision-making. By visualizing the urban traffic management models, decision-makers can intuitively understand the traffic operation. Based on traffic demand, traffic decisions are made using the visualized data and artificial intelligence, achieving precise acquisition of traffic decisions and promoting green transportation construction and industry governance.

[0055] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in this application.

[0056] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0057] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0058] Figure 1 This is a structural diagram of a big data-based urban traffic operation management system according to an embodiment of the present invention;

[0059] Figure 2 This is a structural diagram of the data integration module described in this embodiment of the invention;

[0060] Figure 3 This is a flowchart of a big data-based urban traffic operation management method according to an embodiment of the present invention. Detailed Implementation

[0061] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0062] Example 1:

[0063] This invention provides a big data-based urban traffic operation management system, such as... Figure 1 As shown, it includes:

[0064] The data integration module is used to obtain initial traffic data from various databases on urban traffic, and to standardize and integrate the initial traffic data to obtain multi-dimensional traffic data.

[0065] The model building module is used to construct multiple urban traffic management models based on the multi-dimensional traffic data and in combination with management needs.

[0066] The visual display module is used to visualize the urban traffic management model.

[0067] The traffic decision-making module is used to make traffic decisions based on traffic demand, visualized data, and artificial intelligence.

[0068] In this embodiment, the databases include government departments, private enterprises, IoT devices, social media, weather data, etc., and the privacy-related parts of this traffic data can be disclosed with authorization.

[0069] In this embodiment, the management requirements include, for example, the management of pedestrian flow, vehicle flow, routes, stations, etc., and the corresponding urban traffic management models include pedestrian flow management models, vehicle flow management models, route management models, station management models, etc.

[0070] In this embodiment, traffic decisions include, for example, designing bus routes, suggesting modes of transportation, suggesting travel routes, and suggesting road construction designs.

[0071] The beneficial effects of the above design scheme are as follows: By acquiring initial urban traffic data from various databases and standardizing and integrating the data format of the initial traffic data, multi-dimensional traffic data is obtained, realizing the integration of various data sources, enriching the content of traffic data, and solving the problem of information silos. Based on the multi-dimensional traffic data and combined with management needs, multiple urban traffic management models are constructed, various management models are established, and various types of traffic data are organized, providing effective data information for subsequent decision-making. By visualizing the urban traffic management models, decision-makers can intuitively understand the traffic operation. Based on traffic demand, traffic decisions are obtained based on the visualized data and combined with artificial intelligence, achieving precise acquisition of traffic decisions and promoting green transportation construction and industry governance.

[0072] Example 2:

[0073] Based on Embodiment 1, this embodiment of the invention provides a big data-based urban traffic operation management system, such as... Figure 2 As shown, the data integration module includes:

[0074] The data acquisition unit is used to retrieve initial traffic data from various databases based on a unified API interface;

[0075] The data storage unit is used to distribute the initial traffic data according to the data source to obtain the distributed storage result.

[0076] The data integration unit is used to standardize and integrate the initial traffic data based on multi-data collaborative information and distributed storage results to obtain multi-dimensional traffic data.

[0077] In this embodiment, unified acquisition of multi-source data is achieved based on a unified API interface.

[0078] In this embodiment, the initial traffic data is distributed and stored according to the data source to improve storage efficiency and storage space.

[0079] In this embodiment, the multi-data collaboration information refers to the collaborative information required for the types of decisions that the urban traffic operation management system can make, such as data collaboration between government departments and private enterprises, and collaboration between educational data and meteorological data.

[0080] The beneficial effects of the above design scheme are as follows: Initial traffic data from various databases will be obtained through a unified API interface. The initial traffic data will be distributed and stored according to the data source to obtain distributed storage results. Based on multi-data collaborative information and combined with the distributed storage results, the initial traffic data will be standardized and integrated to obtain multi-dimensional traffic data. This will realize the integration of various data sources, enrich the content of traffic data, and solve the problem of information silos.

[0081] Example 3:

[0082] Based on Embodiment 1, this embodiment of the invention provides a big data-based urban traffic operation management system, wherein the model building module includes:

[0083] The data retrieval unit is used to determine model attributes based on management needs and retrieve target data related to the model attributes from multidimensional traffic data;

[0084] The model building unit is used to construct the model structure based on the model attributes, embed the target data into the model structure, and obtain the urban traffic management model.

[0085] In this embodiment, model attributes include pedestrian flow, vehicle flow, routes, stations, etc.

[0086] The beneficial effects of the above design scheme are as follows: by determining the model attributes based on management needs, retrieving target data related to the model attributes from multi-dimensional traffic data, constructing a model structure based on the model attributes, embedding the target data into the model structure, obtaining an urban traffic management model, realizing the organization of various types of traffic data, and providing effective data information for subsequent decision-making.

[0087] Example 4:

[0088] Based on Embodiment 3, this embodiment of the invention provides a big data-based urban traffic operation management system, wherein the model building module further includes:

[0089] The channel establishment unit is used to establish a real-time interactive channel between the urban traffic management model and target data.

[0090] The real-time update unit is used to update the urban traffic management model in real time based on the update results of the target data through the real-time interaction channel.

[0091] The beneficial effects of the above design scheme are: by establishing a real-time interaction channel between the urban traffic management model and the target data, the urban traffic management model is updated in real time based on the update results of the target data through the real-time interaction channel, thereby achieving real-time updates of the urban traffic management model, ensuring the timeliness of the urban traffic management model, and providing an accurate data foundation for traffic decision-making.

[0092] Example 5:

[0093] Based on Embodiment 1, this embodiment of the invention provides a big data-based urban traffic operation management system, wherein the visual display module includes:

[0094] The model analysis unit is used to determine the visual map based on the traffic management scope of the urban traffic management model and to determine the marker points based on the model attributes of the urban traffic management model.

[0095] The heat map creation unit is used to create heat maps for urban traffic management models based on visual maps and marker points;

[0096] The display unit is used to perform data statistics on the heat map and mark and display the statistical results on the heat map.

[0097] The beneficial effects of the above design scheme are as follows: by determining the traffic management scope based on the urban traffic management model, determining the marker points based on the model attributes of the urban traffic management model, establishing a heat map of the urban traffic management model based on the visual map and the marker points, performing data statistics on the heat map, and marking and displaying the statistical results on the heat map, the data-driven and visual display of the urban traffic management model is realized, helping managers to better understand and make decisions.

[0098] Example 6:

[0099] Based on Embodiment 1, this embodiment of the invention provides a unified urban traffic operation management system based on big data, wherein the traffic decision module includes:

[0100] The demand determination unit is used to determine basic traffic condition requirements and target decision requirements based on traffic demand.

[0101] The weight determination unit is used to determine the participating urban traffic management models based on basic traffic condition requirements, and to determine the model weight of each urban traffic management model.

[0102] The fusion unit is used to perform spatiotemporal model fusion of participating urban traffic management models according to their model weights based on the model attributes of the participating urban traffic management models, so as to obtain basic traffic condition information.

[0103] The association determination unit is used to extract multiple key factors from the basic traffic condition information, and determine the periodic association characteristics between the multiple key factors based on time characteristics, and determine the causal association characteristics between the multiple key factors based on the target decision requirements.

[0104] The model training unit is used to determine the target fusion features based on the periodic correlation features and causal correlation features, and to train the traffic decision model based on the target fusion features and the target decision requirements.

[0105] An intermediate decision-making unit is used to input current traffic data into the traffic decision-making model to obtain an initial traffic decision, and to intelligently intervene in the variable factors in the initial traffic decision to obtain multiple intermediate decisions.

[0106] The decision-making unit is used to determine the trend of public sentiment and the rules for predicting the effect of decisions based on historical data, thereby determining the decision effect score for each intermediate decision, and selecting the intermediate decision with the highest decision effect score as the final traffic decision.

[0107] In this embodiment, the basic traffic condition requirements include, for example, obtaining actual information on traffic flow and congestion, and obtaining actual information on the speed at which vehicles exit each route.

[0108] In this embodiment, the target decision requirements include, for example, path repair decisions, bus route design decisions, and target path design decisions for vehicles.

[0109] In this embodiment, the periodic correlation feature is, for example, the correlation feature between pedestrian flow and vehicle flow within 24 hours, and the causal correlation feature is, for example, determined according to the order of time, such as the increase in bus trips leading to a decrease in vehicle flow.

[0110] In this embodiment, the variable factor in bus route design decisions may be, for example, a change in local routes or a change in local stops.

[0111] In this embodiment, historical data is obtained from stored data.

[0112] The beneficial effects of the above design scheme are: by determining the basic traffic condition demand and target decision demand based on traffic demand, the management model is integrated and analyzed from the data level and the decision level to obtain the initial traffic decision, and the decision adjustment analysis is carried out based on the variable factors, taking into account the public sentiment to determine the final traffic decision, thus ensuring the correctness of the final traffic decision.

[0113] Example 7:

[0114] Based on Embodiment 6, this embodiment of the invention provides a big data-based urban traffic operation management system, wherein the decision-making unit includes:

[0115] The retrieval unit is used to retrieve key information from the intermediate decision according to the scoring indicators, and obtain key decision information under each scoring indicator.

[0116] The prediction unit is used to determine the effect prediction of key decision information based on the decision effect prediction rules, and to determine the public's sentiment trend rating of the effect prediction based on the trend of public sentiment.

[0117] The scoring unit is used to score the emotional trajectory based on all key decision information, and to obtain the decision effect score corresponding to the intermediate decision.

[0118] In this embodiment, the higher the emotion trend score, the higher the corresponding decision-making effect score.

[0119] The beneficial effects of the above design scheme are: by determining the trend of public sentiment and the rules for predicting decision-making effects based on historical data, a decision-making effect score is determined for each intermediate decision, and the intermediate decision with the highest decision-making effect score is selected as the final traffic decision. The final traffic decision is determined based on the predicted public satisfaction, thus ensuring the correctness of the traffic decision and improving public satisfaction with the traffic decision.

[0120] Example 8:

[0121] Based on Embodiment 2, this embodiment of the invention provides a big data-based urban traffic operation management system, wherein the data integration unit includes:

[0122] The standardization unit is used to determine the data standard format based on multi-data collaborative information, standardize the data in the distributed storage results based on the data standard format to obtain standard traffic data, and perform semantic extraction analysis on the standard traffic data to obtain traffic environment features.

[0123] The classification unit is used to classify the distributed storage results based on multi-data collaborative information to obtain storage data groups that can be located and integrated.

[0124] The positioning and transformation unit is used to obtain the coordinate system type of each data group in the stored data group, determine the standard coordinate system type, and perform coordinate system transformation on other coordinate system types according to translation and rotation based on the standard coordinate system type, so as to realize the reference alignment of the stored data group and obtain the reference data group.

[0125] The compensation unit is used to acquire the spatial coordinates and sensor features of the reference data set, perform type difference compensation on the reference data set based on the differences in sensor types, perform difference compensation on the reference data set and the environment based on traffic environment features, and obtain the standard data set based on the type difference compensation and the environment difference compensation.

[0126] The calibration unit is used to automatically calibrate the standard data set based on an adaptive calibration algorithm to obtain the target data set;

[0127] A hardware synchronization unit is used to obtain the cable transmission differences and crystal oscillator drift characteristics in the target data group, and to perform hardware synchronization error compensation on the target data group based on the cable transmission differences and crystal oscillator drift characteristics to obtain an intermediate synchronized data group.

[0128] A timestamp synchronization unit is used to obtain the target synchronization data group by aligning the timestamps of the intermediate synchronization data group.

[0129] The integration unit is used to integrate data based on the location and time characteristics of the target synchronized data group to obtain multi-dimensional traffic data.

[0130] In this embodiment, traffic environment characteristics include temperature, humidity, wind force, etc., which affect data collection.

[0131] The beneficial effects of the above design scheme are: by aligning traffic data in terms of location and time, and by using methods such as semantic analysis, deep learning, compensation calibration and hardware and software synchronization in the process, the spatiotemporal synchronization of traffic data is achieved, ensuring the accuracy of the obtained multi-dimensional location data and providing a basis for urban traffic decision-making.

[0132] Example 9:

[0133] Based on Embodiment 8, this embodiment of the invention provides a big data-based urban traffic operation management system, wherein the integration unit includes:

[0134] The location integration unit is used to integrate the target synchronization data group according to its location characteristics to obtain multi-dimensional location data.

[0135] The time integration unit is used to integrate the multi-dimensional location data according to time characteristics to obtain multi-dimensional traffic data.

[0136] The beneficial effects of the above design scheme are: by integrating the target synchronized data group according to location characteristics, multi-dimensional location data is obtained; by integrating the multi-dimensional location data according to time characteristics, multi-dimensional traffic data is obtained; thus, the integration of various data sources is realized, the content of traffic data is enriched, and the problem of information silos is solved.

[0137] Example 10:

[0138] A big data-based urban traffic operation management method, such as Figure 3 As shown, it includes:

[0139] S1: Obtain initial traffic data from various databases, and standardize and integrate the initial traffic data to obtain multi-dimensional traffic data;

[0140] S2: Based on the aforementioned multi-dimensional traffic data and combined with management needs, construct multiple urban traffic management models;

[0141] S3: Visualize the urban traffic management model;

[0142] S4: Based on traffic demand, traffic decisions are made using visualized data and artificial intelligence.

[0143] In this embodiment, the databases include government departments, private enterprises, IoT devices, social media, weather data, etc., and the privacy-related parts of this traffic data can be disclosed with authorization.

[0144] In this embodiment, the management requirements include, for example, the management of pedestrian flow, vehicle flow, routes, stations, etc., and the corresponding urban traffic management models include pedestrian flow management models, vehicle flow management models, route management models, station management models, etc.

[0145] In this embodiment, traffic decisions include, for example, designing bus routes, suggesting modes of transportation, suggesting travel routes, and suggesting road construction designs.

[0146] The beneficial effects of the above design scheme are as follows: By acquiring initial urban traffic data from various databases and standardizing and integrating the data format of the initial traffic data, multi-dimensional traffic data is obtained, realizing the integration of various data sources, enriching the content of traffic data, and solving the problem of information silos. Based on the multi-dimensional traffic data and combined with management needs, multiple urban traffic management models are constructed, various management models are established, and various types of traffic data are organized, providing effective data information for subsequent decision-making. By visualizing the urban traffic management models, decision-makers can intuitively understand the traffic operation. Based on traffic demand, traffic decisions are obtained based on the visualized data and combined with artificial intelligence, achieving precise acquisition of traffic decisions and promoting green transportation construction and industry governance.

[0147] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of this application and its equivalents, this invention also intends to include these modifications and variations.

Claims

1. A big data-based urban traffic operation management system, characterized in that, include: The data integration module is used to obtain initial traffic data from various databases on urban traffic, and to standardize and integrate the initial traffic data to obtain multi-dimensional traffic data. The model building module is used to construct multiple urban traffic management models based on the multi-dimensional traffic data and in combination with management needs. The visual display module is used to visualize the urban traffic management model. The traffic decision-making module is used to generate traffic decisions based on traffic demand, visualized data, and artificial intelligence, including: The demand determination unit is used to determine basic traffic condition requirements and target decision requirements based on traffic demand. The weight determination unit is used to determine the participating urban traffic management models based on basic traffic condition requirements, and to determine the model weight of each urban traffic management model. The fusion unit is used to perform spatiotemporal model fusion of participating urban traffic management models according to their model weights based on the model attributes of the participating urban traffic management models, so as to obtain basic traffic condition information. The association determination unit is used to extract multiple key factors from the basic traffic condition information, and determine the periodic association characteristics between the multiple key factors based on time characteristics, and determine the causal association characteristics between the multiple key factors based on the target decision requirements. The model training unit is used to determine the target fusion features based on the periodic correlation features and causal correlation features, and to train the traffic decision model based on the target fusion features and the target decision requirements. An intermediate decision-making unit is used to input current traffic data into the traffic decision-making model to obtain an initial traffic decision, and to intelligently intervene in the variable factors in the initial traffic decision to obtain multiple intermediate decisions. The decision-making unit is used to determine the trend of public sentiment and the rules for predicting the effect of decisions based on historical data, thereby determining the decision effect score for each intermediate decision, and selecting the intermediate decision with the highest decision effect score as the final traffic decision. 2.The big data-based urban traffic operation management system according to claim 1, wherein, The data integration module includes: The data acquisition unit is used to retrieve initial traffic data from various databases based on a unified API interface; The data storage unit is used to distribute the initial traffic data according to the data source to obtain the distributed storage result. The data integration unit is used to standardize and integrate the initial traffic data based on multi-data collaborative information and distributed storage results to obtain multi-dimensional traffic data. 3.The urban traffic operation management system based on big data according to claim 1, wherein, The model building module includes: The data retrieval unit is used to determine model attributes based on management needs and retrieve target data related to the model attributes from multidimensional traffic data; The model building unit is used to construct the model structure based on the model attributes, embed the target data into the model structure, and obtain the urban traffic management model.

4. The urban traffic operation management system based on big data according to claim 3, characterized in that, The model building module also includes: The channel establishment unit is used to establish a real-time interactive channel between the urban traffic management model and target data. The real-time update unit is used to update the urban traffic management model in real time based on the update results of the target data through the real-time interaction channel. 5.The urban traffic operation management system based on big data according to claim 1, wherein, The visual display module comprises: The model analysis unit is configured to determine a visual map based on a traffic management range of the urban traffic management model, and determine a marked point based on a model attribute of the urban traffic management model; The heat map establishment unit is configured to establish a heat map of the urban traffic management model based on the visual map and the marked point; The display unit is configured to perform data statistics on the heat map, and mark and display the statistics on the heat map. 6.The big data-based urban traffic operation management system according to claim 1, wherein, The decision unit comprises: The calling unit is configured to call key information of the intermediate decision according to the scoring indicators, to obtain key decision information under each scoring indicator; The prediction unit is configured to determine an effect prediction of the key decision information according to a decision effect prediction rule, and determine a public mood trend score of the public mood trend according to the effect prediction; The scoring unit is configured to determine a decision effect score corresponding to the intermediate decision based on the mood trend scores of all the key decision information. 7.The urban traffic operation management system based on big data according to claim 2, wherein, The data integration unit comprises: The standardization unit is configured to determine a data standard format based on the multi-data collaborative information, standardize the data in the distributed storage result based on the data standard format, obtain standard traffic data, and perform semantic extraction analysis on the standard traffic data to obtain traffic environment features; The classification unit is configured to classify the distributed storage result based on the multi-data collaborative information, to obtain a storage data group that can be positioned and integrated; The positioning conversion unit is configured to obtain a coordinate system type of each data group in the storage data group, determine a standard coordinate system type, convert the coordinate system of other coordinate system types according to translation and rotation based on the standard coordinate system type, realize reference alignment of the storage data group, and obtain a reference data group; The compensation unit is configured to obtain spatial coordinates and sensor features of the reference data group, compensate the reference data group based on the differences in sensor types, compensate the reference data group based on the traffic environment features, and obtain a standard data group based on the type difference compensation and the environment difference compensation; The calibration unit is configured to automatically calibrate the standard data group based on an adaptive calibration algorithm, to obtain a target data group; The hardware synchronization unit is configured to obtain cable transmission differences and crystal oscillator drift features in the target data group, compensate the target data group for hardware synchronization errors based on the cable transmission differences and the crystal oscillator drift features, and obtain an intermediate synchronization data group; The timestamp synchronization unit is configured to obtain timestamp alignment of the intermediate synchronization data group, to obtain a target synchronization data group; The integration unit is configured to integrate data based on position features and time features of the target synchronization data group, to obtain multi-dimensional traffic data. 8.The big data-based urban traffic operation management system according to claim 7, characterized in that, The integration unit comprises: The position integration unit is configured to perform position synchronization integration on the target synchronization data group according to the position features, to obtain multi-dimensional position data; The time integration unit is configured to perform time synchronization integration on the multi-dimensional position data according to the time features, to obtain multi-dimensional traffic data. 9.A method for urban traffic operation management based on big data, in particular for the urban traffic operation management system based on big data according to claim 1, characterized in that, The method comprises: S1: obtaining initial traffic data from urban traffic from each database, and performing data format standardization and integration on the initial traffic data to obtain multi-dimensional traffic data; S2: Based on the multi-dimensional traffic data, combined with management needs, a plurality of city traffic management models are constructed; S3: The city traffic management model is visually displayed; S4: According to the traffic demand, based on the visual display data, combined with artificial intelligence, the traffic decision is obtained.

Images