Three-dimensional traffic intelligent management and control method and system based on multi-dimensional data fusion

Abstract

The application provides a three-dimensional traffic intelligent management and control method and system based on multi-dimensional data fusion, relates to the technical field of traffic management and control, and obtains weather forecast information, road types, road slopes and road widths of to-be-analyzed road sections. Road traffic is analyzed according to precipitation forecast information, temperature forecast information, road types, road slopes and road widths, traffic flow threshold values of the to-be-analyzed road sections are obtained, high-frequency flow fitting of weather forecast time zones of the to-be-analyzed road sections is performed, traffic flow prediction values of the to-be-analyzed road sections are obtained, when the traffic flow prediction values of the to-be-analyzed road sections are greater than or equal to the traffic flow threshold values of the to-be-analyzed road sections, traffic congestion of the weather forecast time zones of the to-be-analyzed road sections is identified, and the traffic congestion is sent to a traffic intelligent management and control end. The technical problem that traffic flow threshold values are fixed and lack of flexibility in the prior art traffic management and control is solved. The technical effect that the traffic flow threshold values are dynamically adjusted, and the flexibility and accuracy of traffic intelligent management and control are improved is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of traffic control, in particular to a three-dimensional traffic intelligent control method and system based on multi-dimensional data fusion. BACKGROUND

[0002] With the acceleration of urbanization and the rapid growth of the number of motor vehicles, urban traffic management is facing the problem of improving road traffic capacity and relieving traffic congestion. To solve this problem, the traditional traffic management usually uses a preset fixed traffic flow threshold as the basis for monitoring and control. The fixed traffic flow threshold is usually set based on historical average flow or empirical data, which cannot adapt to the dynamic changes of traffic flow and lacks flexibility. In the face of weather changes or holiday peak flow, it is difficult to accurately judge the congestion situation. At the same time, the fixed threshold lacks the ability to predict future flow changes, resulting in lagging or inaccurate traffic control measures, which further exacerbates the congestion of the road.

[0003] The prior art traffic control has the technical problem that the traffic flow threshold is fixed and lacks flexibility, resulting in lagging or inaccurate control measures. SUMMARY

[0004] The present application provides a three-dimensional traffic intelligent control method and system based on multi-dimensional data fusion to solve the technical problem that the prior art traffic control has a fixed traffic flow threshold and lacks flexibility, resulting in lagging or inaccurate control measures.

[0005] In view of the above problems, the present application provides a three-dimensional traffic intelligent control method and system based on multi-dimensional data fusion.

[0006] In a first aspect of the present application, a three-dimensional traffic intelligent control method based on multi-dimensional data fusion is provided, which comprises: obtaining weather forecast information, wherein the weather forecast information includes precipitation forecast information and temperature forecast information; obtaining the road type, road slope and road width of the road section to be analyzed; performing road flow analysis according to the precipitation forecast information, the temperature forecast information, the road type, the road slope and the road width to obtain the traffic flow threshold of the road section to be analyzed; fitting the high-frequency flow of the weather forecast time zone of the road section to be analyzed to obtain the traffic flow prediction value of the road section to be analyzed; when the traffic flow prediction value of the road section to be analyzed is greater than or equal to the traffic flow threshold of the road section to be analyzed, identifying the traffic congestion of the weather forecast time zone of the road section to be analyzed and sending it to the traffic intelligent control end.

[0007] In a second aspect of the present application, a three-dimensional traffic intelligent management and control system based on multi-dimensional data fusion is provided, comprising: a weather information obtaining module, configured to obtain weather forecast information, wherein the weather forecast information comprises precipitation forecast information and temperature forecast information; a road section information obtaining module, configured to obtain road type, road slope and road width of a to-be-analyzed road section; a road traffic analysis module, configured to perform road traffic analysis according to the precipitation forecast information, the temperature forecast information, the road type, the road slope and the road width, and obtain a to-be-analyzed road section traffic flow threshold; a road traffic prediction value obtaining module, configured to perform high-frequency traffic fitting on the to-be-analyzed road section in a weather forecast time zone, and obtain a to-be-analyzed road section traffic flow prediction value; and a traffic flow judgment module, configured to perform traffic congestion identification on the weather forecast time zone of the to-be-analyzed road section when the to-be-analyzed road section traffic flow prediction value is greater than or equal to the to-be-analyzed road section traffic flow threshold, and send the weather forecast time zone to a traffic intelligent management and control end.

[0008] The one or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0009] The method provided by the embodiments of the present application obtains weather forecast information, wherein the weather forecast information comprises precipitation forecast information and temperature forecast information; obtains road type, road slope and road width of a to-be-analyzed road section; performs road traffic analysis according to the precipitation forecast information, the temperature forecast information, the road type, the road slope and the road width, and obtains a to-be-analyzed road section traffic flow threshold; performs high-frequency traffic fitting on the to-be-analyzed road section in a weather forecast time zone, and obtains a to-be-analyzed road section traffic flow prediction value; and performs traffic congestion identification on the weather forecast time zone of the to-be-analyzed road section when the to-be-analyzed road section traffic flow prediction value is greater than or equal to the to-be-analyzed road section traffic flow threshold, and sends the weather forecast time zone to a traffic intelligent management and control end. The technical effect of dynamically adjusting the traffic flow threshold, accurately predicting and controlling, and improving the flexibility and accuracy of traffic intelligent management and control is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0011] Figure 1 A flowchart of the three-dimensional traffic intelligent management and control method based on multi-dimensional data fusion provided by the present application is shown in the figure.

[0012] Figure 2A schematic diagram of the structure of the three-dimensional intelligent traffic control system based on multi-dimensional data fusion provided in this application.

[0013] Explanation of reference numerals in the attached diagram: Weather information acquisition module 11, road segment information acquisition module 12, road flow analysis module 13, road flow prediction value acquisition module 14, traffic flow judgment module 15. Detailed Implementation

[0014] This application provides a three-dimensional intelligent traffic management method and system based on multi-dimensional data fusion, which addresses the technical problem in existing traffic management technologies where traffic flow thresholds are fixed and lack flexibility, leading to lagging or inaccurate management measures. It achieves the technical effect of dynamically adjusting traffic flow thresholds, accurately predicting and controlling traffic, and improving the flexibility and accuracy of intelligent traffic management.

[0015] The technical solutions of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. It should also be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all of them.

[0016] Example 1, as Figure 1 As shown, this application provides a three-dimensional intelligent traffic management and control method based on multi-dimensional data fusion, the method comprising:

[0017] Obtain weather forecast information, which includes precipitation forecast information and temperature forecast information.

[0018] Specifically, weather forecast information for the three-dimensional traffic control area is obtained through multiple channels, including the meteorological bureau's official website, meteorological information centers, weather forecast apps, and television and radio broadcasts. This weather forecast includes precipitation and temperature forecasts. Precipitation forecasts indicate the amount of precipitation expected in the area over a specific period, reflecting the precipitation situation in the future. Precipitation has a significant impact on road traffic because it not only affects road friction, reducing vehicle speed, but can also lead to traffic safety hazards such as water accumulation and slippery roads, and in severe cases, can cause traffic accidents or road closures. Temperature forecasts indicate temperature changes over a future period, primarily affecting the durability of road materials and road surface friction. For example, in cold conditions, low temperatures may cause road surfaces to freeze, increasing the risk of skidding, while in high temperatures, some road materials may deform due to the heat, causing changes in traffic flow. Precipitation and temperature forecasts, as the foundation for multi-dimensional data fusion, can identify the potential impact of weather changes on road traffic, providing crucial environmental factor support for traffic flow analysis, thereby enabling more intelligent and precise traffic control.

[0019] Obtain the road type, road slope, and road width of the road segment to be analyzed.

[0020] Specifically, the road type, road gradient, and road width of the road segment to be analyzed are obtained by accessing traffic management systems, GIS geographic information systems, or map service platforms. Road type refers to the classification of different road designs and uses, including highways, urban roads, rural roads, and local roads. Different road types have different capacities, design standards, and traffic flow characteristics. For example, highways typically have multiple lanes, longer speed limits, and higher capacity, while urban roads may have lower efficiency due to narrow roads and numerous traffic lights. Road gradient refers to the degree of inclination of the road relative to the horizontal plane, which can be determined through topographic data or road design parameters. Gradient is a key factor affecting vehicle speed and acceleration / deceleration characteristics. Uphill sections cause vehicles to travel slower, especially under heavy loads, potentially reducing traffic flow, while downhill sections may cause vehicles to travel too fast, increasing the risk of traffic accidents and thus affecting traffic flow stability. Road width refers to the distance between lanes on both sides of the road surface, usually measured in meters. Road width directly affects the number of lanes and traffic flow capacity. Wide roads can accommodate more vehicles, thus improving traffic capacity, while narrow roads lead to traffic congestion, especially during peak hours. By acquiring road characteristic information such as road type, slope, and width of the road segment to be analyzed, the accuracy of traffic flow data can be further improved. Combined with weather forecast information, a comprehensive assessment of traffic flow can be achieved, providing accurate and reliable data support for intelligent traffic management.

[0021] According to the precipitation forecast information, the temperature forecast information, the road type, the road slope and the road width, road traffic analysis is performed to obtain a traffic flow threshold of the to-be-analyzed road section.

[0022] Specifically, by comprehensively analyzing the precipitation forecast information, the temperature forecast information, the road type, the road slope and the road width, the traffic flow of the to-be-analyzed road section is obtained. Optionally, by constructing a model, the precipitation forecast information, the temperature forecast information, the road type, the slope and the width are input, and the corresponding traffic flow threshold of the road section is output. The traffic flow threshold refers to the maximum traffic flow that the road can accommodate under certain conditions. Exceeding this threshold will lead to traffic congestion or traffic accidents. By obtaining the traffic flow threshold of the to-be-analyzed road section, a basis is provided for subsequent flow prediction and congestion judgment, ensuring that traffic control can accurately and timely respond, optimizing traffic flow management, and improving the efficiency and reliability of intelligent traffic control.

[0023] Further, according to the precipitation forecast information, the temperature forecast information, the road type, the road slope and the road width, road traffic analysis is performed to obtain a traffic flow threshold of the to-be-analyzed road section, including: according to the road type, matching a road traffic threshold configuration model; inputting the precipitation forecast information, the temperature forecast information, the road slope and the road width into the road traffic threshold configuration model, and outputting the traffic flow threshold of the to-be-analyzed road section.

[0024] Specifically, the road type is an important factor affecting traffic flow. Different types of roads have different design standards, number of lanes, traffic conditions and traffic capacity. According to the road type, a model matched therewith is selected from a preset road traffic threshold configuration model library. The road traffic threshold configuration model in the preset road traffic threshold configuration model library is trained and constructed using historical traffic flow data and corresponding road types and environmental conditions, and can reflect the traffic capacity of different road types under different conditions. Then, the precipitation forecast information, the temperature forecast information, the road slope and the road width are input into the matched road traffic threshold configuration model. The road traffic threshold configuration model, based on the input multi-dimensional data, combines the characteristics of the road type and the correlation rules in the historical data, and comprehensively considers the influence of various factors on traffic flow, and outputs a traffic flow threshold for the to-be-analyzed road section. By matching the road traffic threshold configuration model according to the road type, the influence of different data on traffic flow can be considered comprehensively, thereby providing more accurate flow prediction results and ensuring that traffic flow can be effectively managed.

[0025] Further, the road traffic threshold configuration model construction step includes: collecting precipitation record information, temperature record information, road record slope, road record width and road traffic identification information as constraints; training the road traffic threshold configuration model according to the precipitation record information, the temperature record information, the road record slope, the road record width and the road traffic identification information.

[0026] Specifically, when constructing the road traffic threshold configuration model, the road type is taken as a model constraint, and multiple key data are collected, including precipitation record information, temperature record information, road record slope, road record width and road traffic identification information. The collected data are cleaned and preprocessed to remove invalid values and outliers, and the data are standardized. The road traffic threshold configuration model is trained according to the processed precipitation record information, temperature record information, road record slope, road record width and road traffic identification information. In the training process, different features such as precipitation, temperature, slope and width are given different weights, and the road traffic threshold configuration model is trained by machine learning methods such as neural networks. Through repeated iteration and optimization, the model can accurately predict the traffic threshold according to historical data. After training, the final road traffic threshold configuration model is obtained, which can consider the influence of weather changes, road characteristics and historical traffic data, provide scientific decision support for intelligent traffic control, and ensure effective prediction and control of traffic flow.

[0027] The high-frequency traffic fitting of the weather forecast time zone of the to-be-analyzed road section is performed to obtain a traffic flow prediction value of the to-be-analyzed road section.

[0028] Specifically, the weather forecast time zone refers to a time period divided based on weather forecast data, and the weather conditions in these time periods have a direct impact on traffic flow. High-frequency traffic refers to high-frequency data of the to-be-analyzed road section obtained through traffic monitoring equipment such as traffic cameras, which records the vehicle passing situation of the road in different time periods, and is counted by hours or minutes. The high-frequency traffic fitting of the weather forecast time zone of the to-be-analyzed road section refers to fitting the traffic flow data in a unit time to obtain the traffic flow prediction value in that time period.

[0029] Further, the high-frequency traffic fitting of the weather forecast time zone of the to-be-analyzed road section is performed to obtain a traffic flow prediction value of the to-be-analyzed road section, including: obtaining a same period time zone traffic flow record value set and a same period time zone traffic flow record value set of the to-be-analyzed road section; performing mode analysis on the same period time zone traffic flow record value set and the same period time zone traffic flow record value set to obtain the traffic flow prediction value of the to-be-analyzed road section.

[0030] Specifically, first, traffic flow records corresponding to the weather forecast time zone are extracted from historical traffic flow data, and two data sets are constructed, including a same period traffic flow record value set and a same period traffic flow record value set, wherein the same period analysis is to compare the data of the current weather forecast time zone with the historical data of the same period in the past, and the same period traffic flow record value set refers to the comparison of the flow record data set of the current time period with the flow record data set of the same date and period in the past year or history, which can reflect the influence of seasonal changes, holidays, working days and other factors on traffic flow. The same period analysis is to compare the data of the current period with the data of the same period in the previous period, and the same period traffic flow record value set refers to the data set compared with the same period flow data of the previous period, for example, the previous week or the previous day. By obtaining these two data sets, traffic flow data under historical and approximate conditions can be provided, and the accuracy of traffic flow prediction can be enhanced. Then, mode analysis is performed on the same period traffic flow record value set and the same period traffic flow record value set to obtain the same period mode and the same period mode, and the same period mode and the same period mode are taken as the same period flow prediction value and the same period flow prediction value respectively to obtain the traffic flow prediction value of the analyzed road section. Mode analysis is a statistical analysis method, which obtains the prediction result by calculating the value with the highest frequency in a group of data. By obtaining and mode analyzing the same period traffic flow record value set and the same period traffic flow record value set, historical data and short-term fluctuation prediction can be effectively combined to obtain more accurate traffic flow prediction value of the analyzed road section, thereby optimizing traffic flow prediction and management and improving traffic control flexibility and effectiveness.

[0031] Further, the same period traffic flow record value set and the same period traffic flow record value set are mode analyzed to obtain the traffic flow prediction value of the analyzed road section, including: mode analyzing the same period traffic flow record value set to obtain a first traffic flow prediction value of the analyzed road section; mode analyzing the same period traffic flow record value set to obtain a second traffic flow prediction value of the analyzed road section; obtaining a same period prediction weight and a same period prediction weight; and according to the same period prediction weight and the same period prediction weight, weighted mean analysis is performed on the first traffic flow prediction value of the analyzed road section and the second traffic flow prediction value of the analyzed road section to obtain the traffic flow prediction value of the analyzed road section.

[0032] Specifically, the mode analysis is performed on the traffic flow record value set in the same time zone to obtain a first to-be-analyzed road section traffic flow prediction value, which reflects the traffic flow level of the time period in the historical data and can reflect seasonal, periodic or long-term traffic trends. Similar to the same period analysis, the mode calculation is performed on the traffic flow data in the same period to obtain a second to-be-analyzed road section traffic flow prediction value, which reflects the most likely value of the flow in the short term and can reflect the volatility of the flow in the recent period. Then, in order to combine the results of the same period prediction and the same period prediction, the same period prediction value and the same period prediction value are respectively assigned corresponding prediction weights, and the weight allocation can be set according to the historical data and the prediction accuracy to obtain the same period prediction weight and the same period prediction weight. Then, by weighted mean analysis, the first to-be-analyzed road section traffic flow prediction value and the second to-be-analyzed road section traffic flow prediction value are combined to obtain the final to-be-analyzed road section traffic flow prediction value. The calculation formula of the weighted mean is as follows: final prediction value=(first prediction value x same period prediction weight)+(second prediction value x same period prediction weight). Through the weighted mean, the data of two different time dimensions can be combined to obtain a more comprehensive, accurate and reliable traffic flow prediction value, ensuring that the traffic management is more intelligent and accurate.

[0033] Further, obtaining the same period prediction weight and the same period prediction weight comprises: obtaining a same period prediction accuracy record value set and a same period prediction accuracy record value set; calculating the mean value of the same period prediction accuracy record value set, and setting it as the same period prediction feature accuracy; calculating the mean value of the same period prediction accuracy record value set, and setting it as the same period prediction feature accuracy; adding the same period prediction feature accuracy and the same period prediction feature accuracy to obtain a feature accuracy addition value; calculating the ratio of the same period prediction feature accuracy and the feature accuracy addition value, and setting it as the same period prediction weight; calculating the ratio of the same period prediction feature accuracy and the feature accuracy addition value, and setting it as the same period prediction weight.

[0034] Specifically, by comparing the historical prediction results with the actual data, the accuracy record values of all the same period traffic flow prediction are collected to form a same period prediction accuracy record value set. Similarly, by comparing the actual flow data, the accuracy record values of the same period traffic flow prediction are collected to form a same period prediction accuracy record value set. The average value of all values in the same period prediction accuracy record value set is calculated to obtain a comprehensive accuracy, i.e. the same period prediction feature accuracy, which reflects the overall performance in long-term historical trend prediction. Similarly, the average value of all values in the same period prediction accuracy record value set is calculated to obtain a comprehensive accuracy, i.e. the same period prediction feature accuracy, which reflects the performance of short-term flow fluctuation prediction. Further, the same period prediction feature accuracy and the same period prediction feature accuracy are added to obtain a total feature accuracy addition value, which is used for weight normalization processing to ensure that the sum of the weights of the two prediction methods is 1. By dividing the same period prediction feature accuracy by the feature accuracy addition value, the relative weight of the same period prediction in the overall prediction is calculated. Similarly, by dividing the same period prediction feature accuracy by the feature accuracy addition value, the weight of the same period prediction is calculated. By obtaining the historical prediction accuracy data and calculating the weight, it is ensured that the prediction result can effectively reflect the influence of short-term fluctuations while considering the long-term trend, so that the flow prediction is more accurate and adaptive to actual change needs.

[0035] When the traffic flow prediction value of the to-be-analyzed road section is greater than or equal to the traffic flow threshold value of the to-be-analyzed road section, the traffic congestion is identified for the weather forecast time zone of the to-be-analyzed road section, and the traffic congestion is sent to the traffic intelligent management and control end.

[0036] Specifically, the traffic flow prediction value of the to-be-analyzed road section is compared with the traffic flow threshold value. When the traffic flow prediction value is greater than or equal to the traffic flow threshold value, it indicates that the traffic of the road section in the specific weather forecast time zone may reach or exceed the carrying capacity of the road, and there is a risk of traffic congestion. Conversely, it indicates that the traffic of the to-be-analyzed road section is relatively smooth, and the risk of traffic congestion is low. Once it is judged that there is a risk of traffic congestion, the weather forecast time zone of the to-be-analyzed road section is marked with traffic congestion, and it is immediately sent to the management and control end to ensure that measures are taken in time. The traffic congestion mark is a standardized representation method for marking the congestion state of a road section in a specific time zone. The traffic mark can be presented in the form of numbers, colors, icons or words. For example, red is used to mark a serious congestion state, yellow is used to mark a high traffic flow but not serious congestion, and green represents smoothness. The time point when the traffic flow prediction value exceeds the threshold value and the corresponding road section are recorded. According to different exceeding degrees, such as slight exceeding and significant exceeding, different congestion severity levels are marked. After receiving the congestion mark, the intelligent management and control end integrates it with other real-time data of the current road network to generate a traffic management and control strategy, realizes accurate traffic diversion and congestion relief, and improves the traffic efficiency of the entire road network.

[0037] In the second embodiment, based on the same inventive concept as the three-dimensional traffic intelligent management and control method based on multi-dimensional data fusion in the foregoing embodiments, as shown in the following table, the present application provides a three-dimensional traffic intelligent management and control system based on multi-dimensional data fusion, wherein the system comprises: Figure 2

[0038] The weather information obtaining module 11 is configured to obtain weather forecast information, wherein the weather forecast information comprises precipitation forecast information and temperature forecast information; the road section information obtaining module 12 is configured to obtain the road type, road slope and road width of the to-be-analyzed road section; the road flow analysis module 13 is configured to perform road flow analysis according to the precipitation forecast information, the temperature forecast information, the road type, the road slope and the road width to obtain the traffic flow threshold value of the to-be-analyzed road section; the road flow prediction value obtaining module 14 is configured to perform high-frequency flow fitting on the to-be-analyzed road section in the weather forecast time zone to obtain the traffic flow prediction value of the to-be-analyzed road section; and the traffic flow judgment module 15 is configured to perform traffic congestion marking on the weather forecast time zone of the to-be-analyzed road section when the traffic flow prediction value of the to-be-analyzed road section is greater than or equal to the traffic flow threshold value of the to-be-analyzed road section, and send the traffic congestion mark to the traffic intelligent management and control end.

[0039] Further, the road flow analysis module 13 comprises: matching a road flow threshold value configuration model according to the road type; inputting the precipitation forecast information, the temperature forecast information, the road slope and the road width into the road flow threshold value configuration model to output the traffic flow threshold value of the to-be-analyzed road section.​

[0040] Further, the road traffic analysis module 13 further comprises: collecting precipitation record information, temperature record information, road record slope, road record width and road traffic identification information as constraints; training the road traffic threshold configuration model according to the precipitation record information, the temperature record information, the road record slope, the road record width and the road traffic identification information.

[0041] Further, the road traffic analysis module 14 comprises: obtaining a same-period time zone traffic flow record value set and a cycle-period time zone traffic flow record value set of the weather forecast time zone of the to-be-analyzed road section; performing mode analysis on the same-period time zone traffic flow record value set and the cycle-period time zone traffic flow record value set to obtain a traffic flow prediction value of the to-be-analyzed road section.

[0042] Further, the road traffic analysis module 14 further comprises: performing mode analysis on the same-period time zone traffic flow record value set to obtain a first to-be-analyzed road section traffic flow prediction value; performing mode analysis on the cycle-period time zone traffic flow record value set to obtain a second to-be-analyzed road section traffic flow prediction value; obtaining a same-period prediction weight and a cycle-period prediction weight; and performing weighted mean analysis on the first to-be-analyzed road section traffic flow prediction value and the second to-be-analyzed road section traffic flow prediction value according to the same-period prediction weight and the cycle-period prediction weight to obtain the traffic flow prediction value of the to-be-analyzed road section.

[0043] Further, the road traffic analysis module 14 further comprises: obtaining a same-period prediction accuracy record value set and a cycle-period prediction accuracy record value set; calculating a mean value of the same-period prediction accuracy record value set as a same-period prediction feature accuracy; calculating a mean value of the cycle-period prediction accuracy record value set as a cycle-period prediction feature accuracy; summing the same-period prediction feature accuracy and the cycle-period prediction feature accuracy to obtain a feature accuracy sum value; calculating a ratio of the same-period prediction feature accuracy to the feature accuracy sum value as the same-period prediction weight; and calculating a ratio of the cycle-period prediction feature accuracy to the feature accuracy sum value as the cycle-period prediction weight.

[0044] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0045] The specification and drawings are, of course, subject to various interpretations and should not be viewed in any limiting sense. It will be understood that various modifications and changes can be made to the application disclosed without departing from the scope thereof. Accordingly, you are to understand that there is no intention, either express or implied, that any of the described embodiments of the application is more efficient or effective than any of the other possible embodiments. It is therefore intended to cover in the appended claims all such changes and modifications that fall within the scope of the application.

Claims

1. A three-dimensional traffic intelligent management and control method based on multi-dimensional data fusion, characterized in that, The method comprises the following steps: obtaining weather forecast information, wherein the weather forecast information comprises precipitation forecast information and temperature forecast information; obtaining the road type, road slope and road width of the road section to be analyzed; performing road flow analysis according to the precipitation forecast information, the temperature forecast information, the road type, the road slope and the road width to obtain the traffic flow threshold of the road section to be analyzed; performing high-frequency flow fitting on the weather forecast time zone of the road section to be analyzed to obtain the traffic flow prediction value of the road section to be analyzed; when the traffic flow prediction value of the road section to be analyzed is greater than or equal to the traffic flow threshold of the road section to be analyzed, identifying traffic congestion in the weather forecast time zone of the road section to be analyzed and sending the same to a traffic intelligent management and control end; obtaining the traffic flow threshold of the road section to be analyzed by performing road flow analysis according to the precipitation forecast information, the temperature forecast information, the road type, the road slope and the road width, comprising: matching a road flow threshold configuration model according to the road type; inputting the precipitation forecast information, the temperature forecast information, the road slope and the road width into the road flow threshold configuration model to output the traffic flow threshold of the road section to be analyzed; the road flow threshold configuration model construction step comprises: collecting precipitation record information, temperature record information, road record slope, road record width and road flow identification information with road type as a constraint; training the road flow threshold configuration model according to the precipitation record information, the temperature record information, the road record slope, the road record width and the road flow identification information; performing high-frequency flow fitting on the weather forecast time zone of the road section to be analyzed to obtain the traffic flow prediction value of the road section to be analyzed, comprising: obtaining a same-period time zone traffic flow record value set and a ring-period time zone traffic flow record value set of the weather forecast time zone of the road section to be analyzed; performing mode analysis on the same-period time zone traffic flow record value set and the ring-period time zone traffic flow record value set to obtain the traffic flow prediction value of the road section to be analyzed; specifically comprising: performing mode analysis on the same-period time zone traffic flow record value set to obtain a first traffic flow prediction value of the road section to be analyzed; performing mode analysis on the ring-period time zone traffic flow record value set to obtain a second traffic flow prediction value of the road section to be analyzed; obtaining a same-period prediction weight and a ring-period prediction weight; performing weighted mean analysis on the first traffic flow prediction value of the road section to be analyzed and the second traffic flow prediction value of the road section to be analyzed according to the same-period prediction weight and the ring-period prediction weight to obtain the traffic flow prediction value of the road section to be analyzed.

2. The multi-dimensional data fusion based three-dimensional traffic intelligent management and control method according to claim 1, characterized in that, obtaining a same-period prediction weight and a ring-period prediction weight, comprising: obtaining a same-period prediction accuracy record value set and a ring-period prediction accuracy record value set; obtaining the mean value of the same-period prediction accuracy record value set as a same-period prediction feature accuracy; obtaining the mean value of the ring-period prediction accuracy record value set as a ring-period prediction feature accuracy; adding the same-period prediction feature accuracy and the ring-period prediction feature accuracy to obtain a feature accuracy addition value; A ratio of the same-period prediction feature accuracy and the feature accuracy sum value is calculated and set as the same-period prediction weight; A ratio of the same-period prediction feature accuracy and the feature accuracy sum value is calculated and set as the same-period prediction weight.

3. The three-dimensional traffic intelligent management and control system based on multi-dimensional data fusion, characterized in that, The three-dimensional traffic intelligent management and control system based on multi-dimensional data fusion is used to implement the steps of the method in any one of claims 1 to 2, and comprises: a weather information obtaining module configured to obtain weather forecast information, wherein the weather forecast information comprises precipitation forecast information and temperature forecast information; a road section information obtaining module configured to obtain road types, road slopes and road widths of a to-be-analyzed road section; a road traffic analysis module configured to perform road traffic analysis according to the precipitation forecast information, the temperature forecast information, the road types, the road slopes and the road widths, and obtain a to-be-analyzed road section traffic flow threshold value; a road traffic prediction value obtaining module configured to perform high-frequency flow fitting on the to-be-analyzed road section in a weather forecast time zone, and obtain a to-be-analyzed road section traffic flow prediction value; a traffic flow judgment module configured to perform traffic congestion identification on the weather forecast time zone of the to-be-analyzed road section when the to-be-analyzed road section traffic flow prediction value is greater than or equal to the to-be-analyzed road section traffic flow threshold value, and send the weather forecast time zone to a traffic intelligent management and control end.

4. The multi-dimensional data fusion based three-dimensional traffic intelligent management and control system of claim 3, wherein, The road traffic analysis module comprises: a road traffic threshold value configuration model is matched according to the road types; the precipitation forecast information, the temperature forecast information, the road slopes and the road widths are input into the road traffic threshold value configuration model, and the to-be-analyzed road section traffic flow threshold value is output.

Images