A method and system for predicting tomorrow's traffic operation

Abstract

The present invention belongs to the field of traffic technology, and specifically provides a method and system for predicting tomorrow's traffic operations, wherein the method includes: creating traffic index data for each road section through traffic index information; weighting and associating the congestion factor that causes traffic congestion with the traffic index data; analyzing real data and predicted data, and optimizing and updating the weight value of the corresponding congestion factor according to the size of the congestion difference to obtain a traffic index prediction model; and predicting tomorrow's traffic conditions based on the traffic index prediction model. The prediction results and recommended measures are output through the analysis of underlying historical data, and then the real-time real data and the predicted data are compared and verified in different aspects, the prediction model is continuously optimized, the weight factor of the historical data is updated, and historical related data that is greatly affected by accidental factors and no longer conforms to the actual situation is eliminated. Based on the continuously self-correcting model system, the accuracy of data prediction and the precision of resource allocation can be improved, which helps to reduce the degree of traffic congestion.

Description

Technical Field

[0001] The present invention relates to the field of traffic technology, and more specifically, to a method and system for predicting tomorrow's traffic operation. Background Art

[0002] With the current burgeoning socioeconomic landscape, road traffic has become an essential part of people's daily lives. Whether driving a car or taking public transportation, traffic congestion is a common occurrence. Current technologies, leveraging advanced technologies like terminal devices and satellites, are already capable of collecting a wide range of traffic data. This back-end process of big data collection, analysis, calculation, and decision-making support lays the foundation for today's smart transportation.

[0003] But at the same time, traffic congestion still occurs every day. It is common to see that Road A is extremely congested, but after passing a certain congestion point, the traffic becomes extremely smooth. It is also seen that due to the unintelligent traffic decisions, some roads are empty but no cars pass through, while some roads are extremely congested but no cars can pass through. Summary of the Invention

[0004] The present invention addresses the technical problem in the prior art that traffic congestion cannot be predicted in advance.

[0005] The present invention provides a method for predicting tomorrow's traffic operation, comprising the following steps:

[0006] S1, creating traffic index data for each road section using traffic index information;

[0007] S2, weighting the congestion factor causing traffic congestion and the traffic index data;

[0008] S3, analyzing the actual and predicted traffic congestion data for a specific road section during a specific time period, optimizing and updating the weight of the corresponding congestion factor based on the difference in congestion, and obtaining a traffic index prediction model;

[0009] S4, based on the traffic index prediction model, predicts tomorrow's traffic conditions.

[0010] Preferably, the S1 specifically includes: aggregating the historical corresponding road section information, time information, and congestion factor information into traffic index data.

[0011] Preferably, the S2 specifically includes:

[0012] Correlating the violation data affecting road traffic with the traffic index data in step S1 based on the location and time of the violation;

[0013] Associating the traffic event data with the traffic index data of step S1 based on location, occurrence time, and estimated duration;

[0014] The number of vehicles passing through is extracted according to the set road range and time range, and the vehicle passing data is associated with the traffic index data of step S1.

[0015] Preferably, the congestion factors in S2 specifically include: illegal events, traffic events, holidays, vehicle passing data, weather data and resource allocation.

[0016] Preferably, the S2 specifically includes:

[0017] According to the influence of congestion factors on traffic congestion in different time periods and different road sections, weight values ​​are assigned in direct proportion.

[0018] Preferably, the S3 specifically includes:

[0019] When the difference between the actual data and the predicted data is no greater than a threshold, it is further determined whether congestion is predicted; if congestion is predicted, the weight value of the repetitive congestion factor of the specific time period of the specific road section is reduced; if congestion is predicted, the weight value of the repetitive congestion factor of the specific time period of the specific road section is increased;

[0020] When the difference between the actual data and the predicted data is greater than the threshold, it means that a new accidental congestion factor has appeared, and it is further judged whether the congestion is predicted to worsen. If the congestion is predicted to ease, the weight value of the accidental congestion factor in the specific time period of the specific road section is weakened. If the congestion is predicted to worsen, the weight value of the non-accidental congestion factor in the specific time period of the specific road section is increased, and the influence of the accidental congestion factor is eliminated.

[0021] Preferably, the S3 specifically includes: based on the weight values ​​of different congestion factors, matching time and events to calculate prediction data, and automatically matching optimizable traffic points based on the prediction data to obtain a traffic index prediction model.

[0022] The present invention also provides a tomorrow traffic operation prediction system, which is used to implement the tomorrow traffic operation prediction method, including:

[0023] The historical data module is used to create traffic index data for each road section based on traffic index information;

[0024] A weight association module is used to associate the congestion factor causing traffic congestion with traffic index data by weight;

[0025] The prediction model building module is used to analyze the actual and predicted data of traffic congestion in a specific time period on a specific road section, optimize and update the weight value of the corresponding congestion factor according to the size of the congestion difference, and obtain the traffic index prediction model;

[0026] The prediction module is used to predict tomorrow's traffic conditions based on the traffic index prediction model.

[0027] The present invention also provides an electronic device comprising a memory and a processor, wherein the processor is configured to implement the steps of a method for predicting tomorrow's traffic operation when executing a computer management program stored in the memory.

[0028] The present invention also provides a computer-readable storage medium on which a computer management program is stored. When the computer management program is executed by a processor, the steps of the tomorrow traffic operation prediction method are implemented.

[0029] Beneficial effects: The present invention provides a method and system for predicting tomorrow's traffic operation, wherein the method includes: creating traffic index data for each road section through traffic index information; weighting and associating the congestion factor that causes traffic congestion with the traffic index data; analyzing the actual data and predicted data of traffic congestion in a specific time period of a specific road section, optimizing and updating the weight value of the corresponding congestion factor according to the size of the congestion difference, and obtaining a traffic index prediction model; predicting tomorrow's traffic conditions based on the traffic index prediction model. Output the prediction results and recommended measures through the analysis of the underlying historical data, and then compare and verify the real-time real data with the predicted data in different aspects, continuously optimize the prediction model, update the weight factor of the historical data, and eliminate the historical related data that is greatly affected by accidental factors and no longer conforms to the actual situation. Based on the continuously self-correcting model system, it can improve the accuracy of data prediction and the accuracy of resource allocation, and help reduce the degree of traffic congestion. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A flow chart of a method for predicting tomorrow's traffic operation provided by the present invention;

[0031] Figure 2 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0032] Figure 3 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0033] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following examples are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0034] Figure 1 The present invention provides a method for predicting tomorrow's traffic operation, comprising the following steps:

[0035] S1. Create traffic index data for each road section using traffic index information. This includes historically corresponding road section information, time information, and congestion factor information, which are aggregated into traffic index data. Specifically, the congestion situation, time period, and congestion factor of each road section, especially during congested periods, are recorded to form a traffic index database.

[0036] S2, weighting the congestion factor causing traffic congestion and the traffic index data;

[0037] S3, analyze the actual data and predicted data of traffic congestion in a specific time period of a specific road section, optimize and update the weight value of the corresponding congestion factor according to the size of the congestion difference, and obtain a traffic index prediction model; there are many factors that cause congestion, and the congestion factors of different road sections and different time periods are also different. Therefore, it is necessary to assign a weight value to the congestion factor of traffic congestion in a specific time period of a specific road section, and the congestion factor with a greater impact has a higher weight value.

[0038] S4, based on the traffic index prediction model, predicts tomorrow's traffic conditions.

[0039] The present invention is mainly used to predict tomorrow's data. Through computer analysis and decision-making, it provides road prediction data to decision makers, which helps relevant workers in the transportation industry to make advance preparations based on the prediction data and reduce the frequency and severity of road traffic congestion as much as possible.

[0040] The preferred solution, S2, specifically includes: associating the violation data that affects road traffic with the traffic index data in step S1 based on the location and time of the violation; associating the traffic event data with the traffic index data in step S1 based on the location, time of occurrence, and expected duration; extracting the number of passing vehicles data based on the set road range and time range, and associating the passing vehicle data with the traffic index data in step S1. Therefore, the congestion factor specifically includes: illegal events, traffic events, holidays, passing vehicle data, weather data, and resource allocation. Other congestion factors are also associated with the traffic index data in step S1 according to the above S2 process. When the congestion factors are associated, corresponding weight values ​​can be assigned.

[0041] A further approach assigns weights proportional to the impact of congestion factors on traffic congestion at different time periods and road sections. Finally, the weighted sum is used to determine the degree of traffic congestion at a specific time period on a specific road section.

[0042] In a preferred solution, when the difference between the actual data and the predicted data is not greater than a threshold, it is further determined whether congestion is predicted; if congestion is predicted, the weight value of the repetitive congestion factor of the specific time period of the specific road section is reduced; if congestion is predicted, the weight value of the repetitive congestion factor of the specific time period of the specific road section is increased;

[0043] When the difference between real-world data and predicted data exceeds a threshold, it indicates the emergence of a new accidental congestion factor, and further consideration is given to predicting worsening congestion. If congestion is predicted to ease, the weight of the accidental congestion factor for that specific road section and time period is reduced. If congestion is predicted to worsen, the weight of the non-accidental congestion factor for that specific road section and time period is increased, eliminating the impact of the accidental congestion factor. Real-time data is compared and verified with predicted data in various aspects, continuously optimizing the prediction model and updating the weighting factors of historical data. Historical data that is significantly affected by accidental factors or no longer reflects actual conditions is eliminated. This continuously self-correcting model system improves the accuracy of data predictions and resource allocation, helping to reduce traffic congestion.

[0044] The preferred solution, S3, specifically includes: based on the weight values ​​of different congestion factors, matching time and events to calculate prediction data, and automatically matching optimizable traffic points based on the prediction data to obtain a traffic index prediction model.

[0045] The specific principle process of a method for predicting tomorrow's traffic operation according to an embodiment of the present invention is as follows:

[0046] Step 1: First, create a historical traffic index database for the road section using traffic index information. Traffic index information includes: original road information, time information, and index information;

[0047] Step 2: Extract the violation data that affects road traffic congestion and associate the violation data with the traffic index in step 1 based on the location and time of the violation;

[0048] Step 3: Correlate traffic incident data with the traffic index from step 1 based on location, occurrence time, and estimated duration;

[0049] Step 4: Extracting the number of vehicles passing according to the set road range and time range, and associating the number of vehicles passing with the traffic index data in step 1;

[0050] Step 5: Collect resource allocation data and associate it with relevant transportation areas;

[0051] Step 6: Analyze the predicted data and the actual data.

[0052] If the judgment is accurate and traffic is normal: the congestion factor with a larger weight should be reduced compared with the congestion factor;

[0053] Accurate judgment and traffic congestion: focus on repetitive congestion factors;

[0054] Determine anomalies and traffic easing: Focus on factors that do not appear in the new data;

[0055] Determine anomalies and increase traffic congestion: focus on new data and emerging factors.

[0056] At the same time, it is necessary to eliminate congestion factors that have not occurred for a long time. Such congestion factors are weakening factors, or reduce the weight of the weakening factor.

[0057] Horizontally compare the final traffic indexes of different congestion factors at the same location, and continuously optimize the weights of congestion factors for different traffic areas to continuously update and optimize the traffic index database.

[0058] Step 7: Based on the latest historical traffic index data warehouse in step 6, first determine the holiday factor, then incorporate the data of the same weekdays in recent months and the recent days, and assign correlation weight values ​​based on the current latest congestion factors. Then perform computer calculations, extract historical useful measures, and output tomorrow's forecast data.

[0059] In a specific implementation scenario, suppose a road traffic condition has an input index a and a predicted index b, along with congestion factors B, C, and D. Analysis shows that a > b (the prediction is abnormal and congestion is worsening). Congestion factor D is a new factor, but it has a limited impact time period. Therefore, its weight is reset to a lower level based on history. Based on the latest data warehouse, tomorrow's forecast will focus on the same period and recent data. Traffic indices (o, p, q...) with similar conditions to tomorrow's weather, events, and dates will be searched for in the base number. Tomorrow's traffic conditions will be calculated based on different weights.

[0060] An embodiment of the present invention further provides a tomorrow traffic operation prediction system, which is used to implement a tomorrow traffic operation prediction method, including:

[0061] The historical data module is used to create traffic index data for each road section based on traffic index information;

[0062] A weight association module is used to associate the congestion factor causing traffic congestion with traffic index data by weight;

[0063] The prediction model building module is used to analyze the actual and predicted data of traffic congestion in a specific time period on a specific road section, optimize and update the weight value of the corresponding congestion factor according to the size of the congestion difference, and obtain the traffic index prediction model;

[0064] The prediction module is used to predict tomorrow's traffic conditions based on the traffic index prediction model.

[0065] See also Figure 2 Schematic diagram of an embodiment of an electronic device provided by an embodiment of the present invention. Figure 2 As shown, an embodiment of the present invention provides an electronic device, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320. When the processor 1320 executes the computer program 1311, the following steps are implemented: S1, creating traffic index data for each road segment based on traffic index information;

[0066] S2, weighting the congestion factor causing traffic congestion and the traffic index data;

[0067] S3, analyzing the actual and predicted traffic congestion data for a specific road section during a specific time period, optimizing and updating the weight of the corresponding congestion factor based on the difference in congestion, and obtaining a traffic index prediction model;

[0068] S4, based on the traffic index prediction model, predicts tomorrow's traffic conditions.

[0069] See also Figure 3 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Figure 3 As shown, this embodiment provides a computer-readable storage medium 1400 on which a computer program 1411 is stored. When the computer program 1411 is executed by a processor, the following steps are implemented: S1, creating traffic index data for each road segment using traffic index information;

[0070] S2, weighting the congestion factor causing traffic congestion and the traffic index data;

[0071] S3, analyzing the actual and predicted traffic congestion data for a specific road section during a specific time period, optimizing and updating the weight of the corresponding congestion factor based on the difference in congestion, and obtaining a traffic index prediction model;

[0072] S4, based on the traffic index prediction model, predicts tomorrow's traffic conditions.

[0073] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0074] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0078] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0079] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for predicting tomorrow's traffic operation, characterized in that: The following steps are involved: S1, creating traffic index data for each road section using traffic index information; S2, weighting the congestion factor causing traffic congestion and the traffic index data; S3: Analyze the actual and predicted traffic congestion data for a specific road section during a specific time period, optimize and update the weight of the corresponding congestion factor based on the difference in congestion, and obtain a traffic index prediction model; specifically, it includes: When the difference between the actual data and the predicted data is no greater than a threshold, it is further determined whether congestion is predicted; if congestion is predicted, the weight value of the repetitive congestion factor of the specific time period of the specific road section is reduced; if congestion is predicted, the weight value of the repetitive congestion factor of the specific time period of the specific road section is increased; When the difference between the actual data and the predicted data is greater than a threshold, it indicates that a new accidental congestion factor has appeared, and a further judgment is made on whether the congestion is predicted to worsen. If the congestion is predicted to ease, the weight value of the accidental congestion factor for the specific time period of the specific road section is weakened. If the congestion is predicted to worsen, the weight value of the non-accidental congestion factor for the specific time period of the specific road section is increased, and the influence of the accidental congestion factor is eliminated. Based on the weight values ​​of different congestion factors, time and events are matched to calculate the predicted data. Based on the predicted data, the traffic index prediction model is automatically matched to the optimized traffic points; S4, based on the traffic index prediction model, predicts tomorrow's traffic conditions.

2. The method for predicting tomorrow's traffic operation according to claim 1, characterized in that: Said S1 specifically includes: aggregating the corresponding road section information, time information, and index information in history into traffic index data.

3. The method for predicting tomorrow's traffic operation according to claim 1, characterized in that: The S2 specifically includes: Correlating the violation data affecting road traffic with the traffic index data in step S1 based on the location and time of the violation; Associating the traffic event data with the traffic index data of step S1 based on location, occurrence time, and estimated duration; The number of vehicles passing the road is extracted according to the set road range and time range, and the number of vehicles passing the road is associated with the traffic index data of step S1.

4. The method for predicting tomorrow's traffic operation according to claim 1, characterized in that: The congestion factors in S2 specifically include: illegal events, traffic events, holidays, passing vehicle data, weather data and resource allocation.

5. The method for predicting tomorrow's traffic operation according to claim 4, characterized in that: The S2 specifically includes: According to the influence of congestion factors on traffic congestion in different time periods and different road sections, weight values ​​are assigned in direct proportion.

6. A tomorrow traffic operation prediction system, characterized in that: The system is used to implement the method for predicting tomorrow's traffic operation according to any one of claims 1 to 5, comprising: The historical data module is used to create traffic index data for each road section based on traffic index information; A weight association module is used to associate the congestion factor causing traffic congestion with traffic index data by weight; The prediction model building module is used to analyze the actual and predicted data of traffic congestion in a specific time period on a specific road section, optimize and update the weight value of the corresponding congestion factor according to the size of the congestion difference, and obtain the traffic index prediction model; The prediction module is used to predict tomorrow's traffic conditions based on the traffic index prediction model.

7. An electronic device, characterized in that: It comprises a memory and a processor, and the processor is used to implement the steps of the tomorrow traffic operation prediction method as described in any one of claims 1 to 5 when executing the computer management program stored in the memory.

8. A computer-readable storage medium, characterized in that A computer management program is stored thereon, and when the computer management program is executed by a processor, the steps of the tomorrow traffic operation prediction method according to any one of claims 1 to 5 are implemented.

Images