Multi-source data fusion intelligent network connection traffic state monitoring method and system

Abstract

The invention discloses an intelligent network connection traffic state monitoring method and system based on multi-source data fusion, and particularly relates to the technical field of intelligent traffic, and the method comprises the steps: obtaining the speed data of M data sources in an nth topological road section in a T time period, and carrying out the preprocessing of the speed data, so as to obtain a data quality coefficient of the nth topological road section; the data quality coefficient of the nth topological road section is analyzed, whether M data sources meet requirements or not is judged, if not, a data optimization instruction is generated, and if yes, a state analysis instruction is generated; according to the method, the data quality coefficient is calculated by analyzing the speed data of the M data sources, so that the accuracy and the reliability of the input data can be ensured. And when the data source does not meet the requirement, a data optimization instruction is generated, so that the influence of low-quality data on the system is avoided. Through the real-time detection and optimization mechanism of the data quality, the interference of data noise or missing is reduced, and the accuracy of the fusion model is improved.

Description

Technical Field

[0001] The present invention relates to the field of smart transportation technology, and more specifically, to a method and system for monitoring the state of intelligent networked traffic with multi-source data fusion. Background Art

[0002] Traditional traffic monitoring methods mainly rely on a single data source, such as traffic cameras, ground sensors or GPS devices. These methods have certain limitations in data collection accuracy, real-time performance and coverage, and cannot fully reflect the traffic status.

[0003] In the prior art, for example, a Chinese patent application with publication number CN103838772A discloses a multi-source traffic data fusion method, which includes: obtaining traffic information data from three data sources: mobile phones, floating vehicles, and traffic video images; performing pixel-level fusion on the traffic information data to remove unqualified information in the traffic information data; performing feature-level fusion on the traffic information data of each data source to generate traffic status information of the road section from three different data sources; performing decision-level fusion on the traffic status information of the road section from three different data sources to generate consistent traffic status description information of the road section; and outputting the traffic status description information of the road section. Although the above method obtains traffic information data from multiple data sources, performs three-level fusion, and generates the final traffic status of the road section, it can more accurately determine the traffic conditions of the road surface, but research and application of the above method and the prior art have found that the above method and the prior art have at least the following partial defects:

[0004] 1. Data standardization and time alignment algorithms are not used, which makes it difficult to ensure the uniform format and time sequence of different source data;

[0005] 2. Pixel-level fusion is suitable for homogeneous or highly related visual data (such as multiple frames of continuous images) because it is based on pixel-by-pixel information superposition and analysis. However, for heterogeneous data (such as visible light images and thermal imaging images or data collected by different sensors), direct pixel-level fusion may lead to information distortion or redundant processing, thereby reducing the effectiveness and reliability of data fusion. When monitoring complex traffic conditions, this distortion may affect the real-time performance and accuracy of the system.

[0006] To this end, the present invention provides a method and system for monitoring the status of intelligent connected traffic with multi-source data fusion. Summary of the invention

[0007] In order to overcome the above-mentioned defects of the prior art, the present invention provides a method and system for monitoring the state of intelligent connected traffic with multi-source data fusion to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] In a first aspect, the present invention provides a method for monitoring the state of intelligent networked traffic by fusion of multi-source data, comprising:

[0010] In a time period of T, speed data of M data sources in the nth topological section are obtained, and the speed data are preprocessed to obtain a data quality coefficient of the nth topological section;

[0011] Analyze the data quality coefficient of the nth topological section to determine whether the M data sources meet the requirements. If not, generate a data optimization instruction. If yes, generate a state analysis instruction.

[0012] receiving a data optimization instruction, optimizing the data quality coefficient of the nth topological section to obtain a speed optimization coefficient, and converting the data optimization instruction into a state analysis instruction;

[0013] Receive a state analysis instruction, obtain road characteristic data of the nth topological road section, generate a road full load coefficient within a time period T according to the road characteristic data, and input the generated road full load coefficient into a pre-generated state prediction model to obtain a road full load coefficient within a time period T+a;

[0014] The road full load coefficient of the nth topological road section in the T+a time period is extracted, and the nth topological road section is matched with the traffic status warning information according to the road full load coefficient to obtain the corresponding status warning information.

[0015] Furthermore, the method of preprocessing the speed data to obtain the data quality coefficient of the nth topological road section includes:

[0016] Step a1: Synchronize the speed data of M data sources into the same time period T to obtain speed calibration data;

[0017] Step a2: performing standardization calculation on the speed calibration data to obtain speed standard data;

[0018] The calculation formula of the speed standard data is:

[0019]

[0020] Where, Vb m Represents the speed standard data of the mth data source; V m represents the speed of the mth data source, Represents the average speed of M data sources;

[0021] Step a3: Fuse M speed standard data and calculate the data quality coefficient of the nth topological section. The calculation formula is:

[0022]

[0023] Where Vx n Represents the data quality coefficient of the nth topological segment, β m is the corresponding weight factor.

[0024] Further, a quality coefficient threshold is preset, and the quality coefficient threshold includes Zx1 and Zx2, wherein Zx1>ZX2; the data quality coefficient is compared with the preset quality coefficient threshold;

[0025] If Vx n >Zx1 or Vx n <Zx2, then generate data optimization instructions;

[0026] If Zx1≥Vx n ≥Zx2, a status analysis instruction is generated.

[0027] Furthermore, the method of optimizing the data quality coefficient of the nth topological section to obtain the speed optimization coefficient includes:

[0028] Step b1: Obtain the data quality coefficient VL of the nth topological section, and construct a coefficient time domain diagram with time as the horizontal axis and the data quality coefficient as the vertical axis;

[0029] Step b2: dividing the coefficient time domain graph into equal parts according to time periods to obtain a real-time fluctuation coefficient set, wherein the real-time fluctuation coefficient set includes R real-time coefficient fluctuation graphs, where R is an integer greater than zero;

[0030] Step b3: extracting the rth real-time coefficient fluctuation graph in the real-time fluctuation coefficient set, where r is a positive integer greater than zero, and the initial value of r is 1;

[0031] Step b4: extract the set of standard coefficient fluctuation graphs of the same time period, calculate the similarity between the real-time coefficient fluctuation graph and the standard coefficient fluctuation graph, if the similarity between the real-time coefficient fluctuation graph and the standard coefficient fluctuation graph is greater than or equal to the preset similarity threshold, mark the real-time coefficient fluctuation graph as a normal coefficient waveform, and jump to step b5; if the similarity between the real-time coefficient fluctuation graph and the standard coefficient fluctuation graph is less than the preset similarity threshold, directly jump to step b5;

[0032] Step b5: set r=r+1 and jump back to step b3;

[0033] Step b6: Repeat the above steps b3 to b5 until r=R, then end the loop and obtain multiple normal coefficient waveforms;

[0034] Step b7: Extract the similarity corresponding to each normal coefficient waveform, and use the data quality coefficient corresponding to the normal coefficient waveform with the greatest similarity as the speed optimization coefficient.

[0035] Further, the road characteristic data includes the length of the road section, the total width of the lane, the total number of actual vehicles and the maximum density of vehicles;

[0036] The method for generating the road full load factor within the T time period according to the road characteristic data includes:

[0037] The road section length, lane width, actual number of vehicles and maximum vehicle density in the road feature data are marked as Ld n 、Wz n , Cm n and Cs n ;

[0038] The length of the road section, the total width of the lane, the actual total number of vehicles and the maximum vehicle density are formalized and the road full load coefficient is calculated. The calculation formula is:

[0039]

[0040] Where Dlm n Indicates the road load factor of the nth topological road segment, Ld n represents the length of the nth topological segment, Wz n Indicates the total lane width of the nth topological road segment, Cm n represents the maximum vehicle density of the nth topological road segment, Cs n represents the actual number of vehicles on the nth topological road segment, and ln(·) represents the logarithmic function with e as the base.

[0041] Furthermore, the method for generating the state prediction model includes:

[0042] Step c1: Obtain the road load coefficient time series set of the nth topological road section;

[0043] Step c2: preset time step B, sliding step K and sliding window length C; convert the historical road load coefficients in the road load coefficient time series set into multiple training samples using the sliding window method, use the training samples as the input of the state prediction model, and predict the road load coefficient after time step B as the output. The road load coefficient of each training sample is used as the prediction target, and the prediction accuracy is used as the training target to train the state prediction model; generate a state prediction model for predicting the road load coefficient in the T+a time period based on the historical road load coefficients in the road load coefficient time series set; wherein the state prediction model is an RNN neural network model.

[0044] Furthermore, the method for obtaining the road load factor time series set includes:

[0045] The road load coefficient of the nth topological road section during the historical traffic status monitoring process is extracted and marked as the historical road load coefficient. The extracted historical road load coefficient is used to construct a road load coefficient time series set. The road load coefficient time series set includes i historical road load coefficients. The time intervals for obtaining the i historical road load coefficients are equal, and the i historical road load coefficients correspond to a time period.

[0046] Furthermore, the method for obtaining traffic status warning information includes:

[0047] Step e1: Obtain the road load factor of N topological road sections in the time period T+a, and obtain speed data;

[0048] Step e2: combining the road load factor and speed data into a feature vector, and inputting the feature vector into a pre-built traffic warning model to obtain traffic status warning information.

[0049] Furthermore, the traffic warning model is obtained according to warning training data, wherein the warning training data includes warning feature data and its corresponding traffic status warning information; the warning feature data includes road full load coefficient and speed data;

[0050] The method for acquiring the traffic status warning information in the warning training data includes:

[0051] Step d1: extracting the road load factor of the nth topological road section in the time period T+a; and simultaneously obtaining the speed data of the nth topological road section in the time period T+a;

[0052] Step d2: setting H road load factor intervals, and setting H traffic status warning information corresponding to the H road load factor intervals; each of the road load factor intervals is bound if and only if there is one traffic status warning information associated with it;

[0053] Step d3: comparing the road full load coefficient of the nth topological road section with each road full load coefficient interval, and obtaining the road full load coefficient interval into which the road full load coefficient of the nth topological road section falls;

[0054] Step d4: according to the road full load coefficient interval into which the road full load coefficient of the nth topological road section falls, the road full load coefficient of the nth topological road section is divided into corresponding traffic state warning information; and n=n+1 is set, and the process is returned to step d1;

[0055] Step d5: repeating the above steps d1 to d4 until the cycle ends when n=N, so that each road full load coefficient is divided into H traffic status warning information in sequence;

[0056] Step d6: Adjust the traffic status warning information according to the speed data of the N topological road sections.

[0057] Furthermore, the method for adjusting traffic status warning information according to speed data of N topological road sections includes:

[0058] Preset a speed threshold, and compare the speed data of each topological road section with the preset speed threshold;

[0059] When the speed data is greater than or equal to the preset speed threshold, the corresponding road load factor is reduced by one level and adjusted to the next road load factor interval;

[0060] When the speed data is less than the preset speed threshold, the corresponding road load factor will be increased by one level and adjusted to the previous road load factor range.

[0061] Furthermore, the generation method of the traffic warning model includes:

[0062] Each set of warning feature data is combined into a feature vector, and the elements of all feature vectors are used as inputs of a machine learning model. The machine learning model uses the traffic status warning information predicted by each set of warning feature data as output, and uses the actual traffic status warning information corresponding to each set of warning feature data as a prediction target, and uses minimizing the sum of the prediction accuracies of all predicted traffic status warning information as a training target; the machine learning model is trained until the sum of the prediction accuracies converges, and the training is stopped; the trained machine learning model is used as a traffic warning model, and the machine learning model is a deep neural network model or a deep belief network model.

[0063] In a second aspect, the present invention provides a multi-source data fusion intelligent networked traffic status monitoring system, which is used to implement the multi-source data fusion intelligent networked traffic status monitoring method, including:

[0064] A data preprocessing module is used to obtain speed data of M data sources in the nth topological road section within a T time period, and preprocess the speed data to obtain a data quality coefficient of the nth topological road section;

[0065] A judgment module is used to analyze the data quality coefficient of the nth topological section to determine whether the M data sources meet the requirements. If not, a data optimization instruction is generated; if yes, a state analysis instruction is generated;

[0066] An optimization module, for receiving a data optimization instruction, optimizing the data quality coefficient of the nth topological road section to obtain a speed optimization coefficient, and converting the data optimization instruction into a state analysis instruction;

[0067] An analysis module is used to receive a state analysis instruction, obtain road characteristic data of the nth topological road section, generate a road full load coefficient within a time period T according to the road characteristic data, and input the generated road full load coefficient into a pre-generated state prediction model to obtain the road full load coefficient within a time period T+a;

[0068] The matching module is used to extract the road load coefficient of the nth topological road section in the T+a time period, match the nth topological road section with the traffic status warning information according to the road load coefficient, and obtain the corresponding status warning information.

[0069] Technical effects and advantages of the present invention:

[0070] 1. The present invention helps to ensure the accuracy and reliability of input data by analyzing the speed data of M data sources and calculating the data quality coefficient. When the data source does not meet the requirements, a data optimization instruction is generated to avoid the impact of low-quality data on the system. Through the real-time detection and optimization mechanism of data quality, the interference of data noise or missing is reduced, and the accuracy of the fusion model is improved. The robustness and adaptability of the system are enhanced to adapt to data fluctuations in different traffic scenarios, while reducing the monitoring false alarm rate caused by data anomalies and improving the stability of traffic status prediction.

[0071] 2. The present invention enables the system to flexibly adjust the operation process according to the data situation through conversion between data optimization instructions and state analysis instructions, ensuring that state analysis and prediction are based on high-quality data, thereby improving the execution efficiency of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 This is a flow chart of the intelligent networked traffic status monitoring method using multi-source data fusion in Example 1;

[0073] Figure 2 This is a flow chart of a method for acquiring traffic status warning information in warning training data of Example 1;

[0074] Figure 3 This is a schematic diagram of the structure of the intelligent networked traffic status monitoring system with multi-source data fusion according to Example 2;

[0075] Figure 4 This is a schematic diagram of an electronic device according to Example 3. DETAILED DESCRIPTION

[0076] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0078] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and a similar second unit may be referred to as a first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0079] Example 1

[0080] See also Figure 1 As shown, this embodiment discloses a method for monitoring the state of intelligent networked traffic by fusion of multi-source data, the method comprising:

[0081] Step 1: In a time period of T, obtain speed data from M data sources in the nth topological section, and preprocess the speed data to obtain a data quality coefficient of the nth topological section.

[0082] It should be noted that: T and M are both integers greater than zero, n=1, 2, ..., N, where N is the total number of topological sections.

[0083] It should be understood that: the topological road segment represents the division of the target city traffic network into N topological road segments according to the division rules, and the division rules include geographical location, road attributes and traffic flow direction, etc., which are specifically determined by those skilled in the art according to actual conditions and are not limited to this. The data sources include but are not limited to road sensors, GPS, collected mind data, traffic cameras, checkpoint data, floating car data, OSM system and POI system, etc. Since the quality of speed information obtained from different data sources is inconsistent, it is easy to cause data delay, so it is necessary to pre-process the speed data to improve the quality of the data.

[0084] It should be noted that: the speed data is the average speed of the vehicle on the nth topological road section. The T time period is a time span preset by a person skilled in the art according to data collection requirements. For example, the preset time span includes Y, where Y is an integer greater than zero. Further examples are given as follows: assuming that the time interval is 00:00-00:30, and the preset time span is 5 minutes, the speed data within the preset time span includes speed values ​​between 00:00-00:05, speed values ​​between 00:05-00:10, speed values ​​between 00:10-00:15, ..., speed values ​​between 00:25-00:30.

[0085] In implementation, the method of preprocessing the speed data to obtain the data quality coefficient of the nth topological road section includes:

[0086] Step a1: Synchronize the speed data of M data sources into the same time period T to obtain speed calibration data.

[0087] It should be noted that the speed data is time-stamped in advance to ensure that the speed data from different sources are consistent in time.

[0088] Step a2: Standardize and calculate the speed calibration data to obtain speed standard data; the calculation formula of the speed standard data is:

[0089]

[0090] Where, Vb m Represents the speed standard data of the mth data source; V m represents the speed of the mth data source, Indicates the average speed of M data sources.

[0091] Step a3: Fuse M speed standard data and calculate the data quality coefficient of the nth topological section. The calculation formula is:

[0092]

[0093] Where Vxn represents the data quality coefficient of the nth topological section, β m is the corresponding weight factor, β m is a constant greater than zero, and the weight factors are set by those skilled in the art based on experience.

[0094] Step 2: Analyze the data quality coefficient of the nth topological section to determine whether the M data sources meet the requirements. If not, generate a data optimization instruction; if yes, generate a state analysis instruction.

[0095] A quality coefficient threshold is preset, and the quality coefficient threshold includes Zx1 and Zx2, wherein Zx1>Zx2; and the data quality coefficient is compared with the preset quality coefficient threshold.

[0096] If Vx n >Zx1 or Vx n <Zx2, a data optimization instruction is generated, indicating that the data quality coefficient of the nth topological path does not meet the data requirements and the speed data needs to be further optimized.

[0097] If Zx1≥Vx n ≥Zx2, a state analysis instruction is generated, indicating that the data quality coefficient of the nth topological path meets the data requirements.

[0098] It should be noted that the preset quality coefficient threshold is determined by those skilled in the art based on actual needs and a large amount of experimental data. This step obtains a unified and accurate data quality coefficient through multi-source data fusion and preprocessing, effectively solving the problem of inconsistent multi-source data quality in the intelligent transportation system. These data can not only reflect the traffic conditions of a certain road section in a specific time period, but also provide data support for the next step of traffic prediction, dynamic signal control and congestion management.

[0099] Step 3: Receive data optimization instructions, optimize the data quality coefficient of the nth topological road section to obtain a speed optimization coefficient, and convert the data optimization instructions into state analysis instructions to improve the accuracy of the analysis of the traffic state of the nth topological road section.

[0100] In implementation, the method of optimizing the data quality coefficient of the nth topological section to obtain the speed optimization coefficient includes:

[0101] Step b1: Obtain the data quality coefficient Vx of the nth topological segment n , with time as the horizontal axis and data quality coefficient as the vertical axis, a coefficient time domain diagram is constructed;

[0102] Step b2: dividing the coefficient time domain graph into equal parts according to time periods to obtain a real-time fluctuation coefficient set, wherein the real-time fluctuation coefficient set includes R real-time coefficient fluctuation graphs, where R is an integer greater than zero;

[0103] Step b3: extracting the rth real-time coefficient fluctuation graph in the real-time fluctuation coefficient set, where r is a positive integer greater than zero, and the initial value of r is 1;

[0104] Step b4: extract the set of standard coefficient fluctuation graphs of the same time period, calculate the similarity between the real-time coefficient fluctuation graph and the standard coefficient fluctuation graph, if the similarity between the real-time coefficient fluctuation graph and the standard coefficient fluctuation graph is greater than or equal to the preset similarity threshold, mark the real-time coefficient fluctuation graph as a normal coefficient waveform, and jump to step b5; if the similarity between the real-time coefficient fluctuation graph and the standard coefficient fluctuation graph is less than the preset similarity threshold, jump directly to step b5 without marking;

[0105] It should be noted that a set of standard coefficient fluctuation graphs for multiple time periods are pre-stored in the system database, and each time period is associated with a standard coefficient fluctuation graph, which reflects the coefficient fluctuation of the nth topological section when there is no abnormality in the speed data preprocessing of M data sources.

[0106] Step b5: set r=r+1 and jump back to step b3;

[0107] Step b6: Repeat the above steps b3 to b5 until r=R, then end the loop and obtain multiple normal coefficient waveforms;

[0108] Step b7: Extract the similarity corresponding to each normal coefficient waveform, and use the data quality coefficient corresponding to the normal coefficient waveform with the greatest similarity as the speed optimization coefficient.

[0109] It should be noted that: the similarity algorithm includes cosine similarity algorithm or Euclidean distance algorithm, etc.; the real-time coefficient fluctuation map and the standard coefficient fluctuation map need to be preprocessed before comparison, and the preprocessing includes image enhancement, image denoising and image segmentation.

[0110] Step 4: Receive the state analysis instruction, obtain the road characteristic data of the nth topological road section, generate the road load coefficient within the T time period based on the road characteristic data, and input the generated road load coefficient into the pre-generated state prediction model to obtain the road load coefficient within the T+a time period.

[0111] The road characteristic data include road section length, total lane width, actual total number of vehicles and maximum vehicle density.

[0112] It should be noted that the road section length and total lane width are obtained by real-time measurement along the road using GPS equipment, and the actual total number of vehicles and the maximum vehicle density are completed through automatic recognition and data extraction by the camera. The above method of obtaining the road section length, total lane width, actual total number of vehicles and maximum vehicle density is only an example, and any other method in the prior art (such as LiDAR, drone aerial photography, GIS system, etc.) can be used to collect road feature data. The collection method of road feature data is flexible and diverse, and the specific selection can be adjusted and optimized according to the application scenario requirements and accuracy requirements.

[0113] In implementation, the method of generating the road full load coefficient within the T time period according to the road characteristic data includes:

[0114] The road section length, lane width, actual number of vehicles and maximum vehicle density in the road feature data are marked as Ld n 、Wz n , Cm n and Cs n .

[0115] The length of the road section, the total width of the lane, the actual total number of vehicles and the maximum vehicle density are formalized and the road full load coefficient is calculated. The calculation formula is:

[0116]

[0117] Where Dlm n Indicates the road load factor of the nth topological road segment, Ld n represents the length of the nth topological segment, Wz n Indicates the total lane width of the nth topological road segment, Cm n represents the maximum vehicle density of the nth topological road segment, Cs n represents the actual number of vehicles on the nth topological road segment, and ln(·) represents the logarithmic function with e as the base.

[0118] It should be noted that the larger the value of the road load coefficient is, the more congested the topological road section is.

[0119] In implementation, the method for generating the state prediction model includes:

[0120] Step c1: Obtain the road load coefficient time series set of the nth topological road section;

[0121] The method for obtaining the road load factor time series set includes:

[0122] The road load coefficient during the historical traffic status monitoring process of the nth topological road section is extracted from the system database and marked as the historical road load coefficient. The extracted historical road load coefficients are used to construct a road load coefficient time series set. The road load coefficient time series set includes i historical road load coefficients. The time intervals for obtaining the i historical road load coefficients are equal, and the i historical road load coefficients correspond to a time period.

[0123] Step c2: preset the time step B, sliding step K and sliding window length C according to the actual experience of the staff; convert the historical road load coefficients in the road load coefficient time series set into multiple training samples using the sliding window method, use the training samples as the input of the state prediction model, predict the road load coefficient after the time step B as the output, use the road load coefficient of each training sample as the prediction target, and train the state prediction model with the prediction accuracy as the training target; generate a state prediction model for predicting the road load coefficient in the T+a time period based on the historical road load coefficients in the road load coefficient time series set; wherein the state prediction model is an RNN neural network model; by using the road load coefficient time series set, predict the road load coefficient of the nth topological section in the T+a time period, thereby realizing the prediction of the road load coefficient of the nth topological section in the T+a time period based on the road load coefficient in the T time period.

[0124] It should be noted that the road full load coefficient time series set is divided into sliding windows of equal size, the road full load coefficient in each window is taken as a sample, and the road full load coefficient in the window T+a time period is taken as a digital label. It should be noted that one sample corresponds to one digital label, and one sample and the corresponding digital label constitute a set of full load training data, and multiple sets of full load training data constitute a coefficient training set;

[0125] As a further example, assume that the road load factor time series set A contains 10 sets of historical road load factors, A = {A1, A2, A3, A4, A5, ..., A 10}, A a For the a-th group of historical road load coefficients, use a sliding window to construct multiple training samples, set the prediction time step B to 1, the sliding window length H to 5, and the sliding step C to 1, then each generated training sample contains 5 consecutive historical road load coefficients, and the next road load coefficient of the 5 consecutive historical road load coefficients is used as the prediction target; for example:

[0126] {A1, A2, A3, A4, A5} is used as the full-load training data, and the corresponding prediction target is A6;

[0127] {A2, A3, A4, A5, A6} is the full-load training data, and the corresponding prediction target is A7;

[0128] By analogy, the state prediction model for predicting the road load factor of the nth topological road section in the T+a time period is trained.

[0129] By collecting road feature data and analyzing the obtained road load factor, the pre-built state prediction model is used to predict the road load factor of the nth topological road section in the T+a time period. This process can not only improve the prediction accuracy and traffic flow management level, but also support managers to formulate and implement traffic control plans in a timely manner.

[0130] Step 5: Extract the road load coefficient of the nth topological road section in the T+a time period, match the nth topological road section with the traffic status warning information according to the road load coefficient, and obtain the corresponding traffic status warning information.

[0131] In implementation, the method for obtaining traffic status warning information includes:

[0132] Step e1: Obtain the road load factor of N topological road sections in the time period T+a, and obtain speed data;

[0133] Step e2: combining the road load factor and speed data into a feature vector, and inputting the feature vector into a pre-built traffic warning model to obtain traffic status warning information.

[0134] The traffic warning model is obtained based on warning training data, and the warning training data includes warning feature data and its corresponding traffic status warning information; the warning feature data includes road load factor and speed data.

[0135] See also Figure 2 As shown, in a specific implementation, the method for acquiring the traffic status warning information in the warning training data includes:

[0136] Step d1: extracting the road load factor of the nth topological road section in the time period T+a; and simultaneously obtaining the speed data of the nth topological road section in the time period T+a;

[0137] Step d2: Set H road load factor intervals, and set H traffic status warning information corresponding to the H road load factor intervals; each of the road load factor intervals is bound to it if and only if there is one traffic status warning information associated with it.

[0138] It should be noted that the H road load factor intervals are arranged in a step-by-step order from large to small, and correspondingly, the H traffic status warning information are also arranged in the same order.

[0139] Step d3: comparing the road full load coefficient of the nth topological road section with each road full load coefficient interval, and obtaining the road full load coefficient interval into which the road full load coefficient of the nth topological road section falls;

[0140] Step d4: according to the road full load coefficient interval into which the road full load coefficient of the nth topological road section falls, the road full load coefficient of the nth topological road section is divided into corresponding traffic state warning information; and n=n+1 is set, and the process is returned to step d1;

[0141] Step d5: repeating the above steps d1 to d4 until the cycle ends when n=N, so that each road full load coefficient is divided into H traffic status warning information in sequence;

[0142] Step d6: Adjust H traffic status warning information according to the speed data of N topological road sections.

[0143] In a preferred embodiment, the method for adjusting H traffic status warning information according to speed data of N topological road sections includes:

[0144] Preset a speed threshold, and compare the speed data of each topological road section with the preset speed threshold;

[0145] When the speed data is greater than or equal to the preset speed threshold, the corresponding road load factor is reduced by one level and adjusted to the next road load factor interval;

[0146] When the speed data is less than the preset speed threshold, the corresponding road load factor will be increased by one level and adjusted to the previous road load factor range.

[0147] It should be noted that by dynamically comparing speed data with the preset speed threshold, the road load factor can be adjusted in real time, which helps to improve the accuracy and flexibility of traffic status warnings. Traffic status warning information is updated in a timely manner as vehicle speed changes to avoid misjudgments caused by static evaluation. This adjustment mechanism can also more accurately reflect traffic flow conditions, provide timely and effective decision-making support for traffic control departments, optimize traffic flow management, reduce congestion risks, and improve road traffic efficiency.

[0148] In implementation, the generation method of the traffic warning model includes:

[0149] Each set of warning feature data is combined into a feature vector, and the elements of all feature vectors are used as inputs of a machine learning model. The machine learning model uses the traffic status warning information predicted by each set of warning feature data as output, uses the actual traffic status warning information corresponding to each set of warning feature data as a prediction target, and uses minimizing the sum of the prediction accuracies of all predicted traffic status warning information as a training target; wherein the calculation formula for prediction accuracy is: d v =(c v -p v ) 2 , where V is the number of each set of warning feature data, d v is the prediction accuracy, c v is the predicted traffic status warning information corresponding to the vth group of warning feature data, p v The actual traffic status warning information corresponding to the vth group of warning feature data; the machine learning model is trained until the sum of the prediction accuracies reaches convergence and the training is stopped; the trained machine learning model is used as a traffic warning model, and the machine learning model is a deep neural network model or a deep belief network model.

[0150] This embodiment helps ensure the accuracy and reliability of input data by analyzing the speed data of M data sources and calculating the data quality coefficient. When the data source does not meet the requirements, a data optimization instruction is generated to avoid the impact of low-quality data on the system. Through the real-time detection and optimization mechanism of data quality, the interference of data noise or missing is reduced, and the accuracy of the fusion model is improved. The robustness and adaptability of the system are enhanced to adapt to data fluctuations in different traffic scenarios, while reducing the monitoring false alarm rate caused by data anomalies and improving the stability of traffic status prediction.

[0151] This embodiment enables the system to flexibly adjust the operation process according to the data situation through conversion between data optimization instructions and state analysis instructions, ensuring that state analysis and prediction are based on high-quality data, thereby improving the execution efficiency of the system.

[0152] The formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The weight factors in the formula and the preset thresholds in the analysis process are set by technicians in this field according to actual conditions or obtained by simulating a large amount of data; the size of the weight factor is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the weight factor depends on the amount of sample data and the corresponding processing coefficient initially set by technicians in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0153] Example 2

[0154] See also Figure 3 As shown, this embodiment provides an intelligent networked traffic status monitoring system with multi-source data fusion, the system is applied to a cloud server, and the system includes: a data preprocessing module, a judgment module, an optimization module, an analysis module and a matching module, and the above modules are connected by wired and / or wireless means to realize data transmission between each other;

[0155] A data preprocessing module is used to obtain speed data of M data sources in the nth topological road section within a T time period, and preprocess the speed data to obtain a data quality coefficient of the nth topological road section;

[0156] A judgment module is used to analyze the data quality coefficient of the nth topological section to determine whether the M data sources meet the requirements. If not, a data optimization instruction is generated; if yes, a state analysis instruction is generated;

[0157] An optimization module, for receiving a data optimization instruction, optimizing the data quality coefficient of the nth topological road section to obtain a speed optimization coefficient, and converting the data optimization instruction into a state analysis instruction;

[0158] An analysis module is used to receive a state analysis instruction, obtain road characteristic data of the nth topological road section, generate a road full load coefficient within a time period T according to the road characteristic data, and input the generated road full load coefficient into a pre-generated state prediction model to obtain the road full load coefficient within a time period T+a;

[0159] The matching module is used to extract the road load coefficient of the nth topological road section in the T+a time period, match the nth topological road section with the traffic status warning information according to the road load coefficient, and obtain the corresponding status warning information.

[0160] Example 3

[0161] Figure 4 This is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 4 As shown, the electronic device of this embodiment includes: a processor 11 ( Figure 4 Only one processor is shown), a memory 12, and a computer program 13 stored in the memory 12 and executable on the processor 11. When the processor 11 executes the computer program 13, the steps in the embodiment of the intelligent networked traffic state monitoring method for multi-source data fusion are implemented, for example Figure 1 Alternatively, when the processor 11 executes the computer program 13, the functions of each module / unit in the above-mentioned system embodiments are realized, for example Figure 3 The functions of each module are shown.

[0162] Exemplarily, the computer program 13 may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 11 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 13 in the terminal device.

[0163] Those skilled in the art will understand that Figure 4 It is only an example of an electronic device and does not constitute a limitation on the electronic device. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc. The processor 11 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0164] The memory 12 may be an internal storage unit of the terminal device, such as a hard disk or memory of the terminal device. The memory 12 may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the terminal device. Further, the memory 12 may also include both an internal storage unit of the terminal device and an external storage device. The memory 12 is used to store the computer program and other programs and data required by the terminal device. The memory 12 may also be used to temporarily store data that has been output or is to be output.

[0165] Example 4

[0166] This embodiment provides a computer-readable storage medium storing instructions. When the instructions are executed on a computer, the computer executes the intelligent connected traffic status monitoring method of multi-source data fusion of embodiment 1.

[0167] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0168] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A multi-source data fusion intelligent network traffic status monitoring method, characterized in that: include: In a time period of T, speed data of M data sources in the nth topological section are obtained, and the speed data are preprocessed to obtain a data quality coefficient of the nth topological section; Analyze the data quality coefficient of the nth topological section to determine whether the M data sources meet the requirements. If not, generate a data optimization instruction. If yes, generate a state analysis instruction. receiving a data optimization instruction, optimizing the data quality coefficient of the nth topological section to obtain a speed optimization coefficient, and converting the data optimization instruction into a state analysis instruction; Receive a state analysis instruction, obtain road characteristic data of the nth topological road section, generate a road full load coefficient within a time period T according to the road characteristic data, and input the generated road full load coefficient into a pre-generated state prediction model to obtain a road full load coefficient within a time period T+a; The road full load coefficient of the nth topological road section in the T+a time period is extracted, and the nth topological road section is matched with the traffic status warning information according to the road full load coefficient to obtain the corresponding status warning information.

2. The intelligent networked traffic status monitoring method based on multi-source data fusion according to claim 1 is characterized in that: The method of preprocessing the speed data to obtain the data quality coefficient of the nth topological road section includes: Step a1: Synchronize the speed data of M data sources into the same time period T to obtain speed calibration data; Step a2: performing standardization calculation on the speed calibration data to obtain speed standard data; The calculation formula of the speed standard data is: Where Vb m Represents the speed standard data of the mth data source; V m represents the speed of the mth data source, Represents the average speed of M data sources; Step a3: Fuse M speed standard data and calculate the data quality coefficient of the nth topological section. The calculation formula is: Where Vx n Represents the data quality coefficient of the nth topological segment, β m is the corresponding weight factor.

3. The intelligent networked traffic status monitoring method based on multi-source data fusion according to claim 2 is characterized in that: Preset a quality coefficient threshold, the quality coefficient threshold includes Zx1 and Zx2, where Zx1>Zx2; compare the data quality coefficient with the preset quality coefficient threshold; If Vx n > Zx1 or Vx n < Zx2, then generate a data optimization instruction; If Zx1≥Vx n ≥Zx2, a status analysis instruction is generated.

4. The intelligent networked traffic status monitoring method based on multi-source data fusion according to claim 3 is characterized in that: The method of optimizing the data quality coefficient of the nth topological section to obtain the speed optimization coefficient includes: Step b1: Obtain the data quality coefficient VL of the nth topological section, and construct a coefficient time domain diagram with time as the horizontal axis and the data quality coefficient as the vertical axis; Step b2: dividing the coefficient time domain graph into equal parts according to time periods to obtain a real-time fluctuation coefficient set, wherein the real-time fluctuation coefficient set includes R real-time coefficient fluctuation graphs, where R is an integer greater than zero; Step b3: extracting the rth real-time coefficient fluctuation graph in the real-time fluctuation coefficient set, where r is a positive integer greater than zero, and the initial value of r is 1; Step b4: extract the set of standard coefficient fluctuation graphs of the same time period, calculate the similarity between the real-time coefficient fluctuation graph and the standard coefficient fluctuation graph, if the similarity between the real-time coefficient fluctuation graph and the standard coefficient fluctuation graph is greater than or equal to the preset similarity threshold, mark the real-time coefficient fluctuation graph as a normal coefficient waveform, and jump to step b5; if the similarity between the real-time coefficient fluctuation graph and the standard coefficient fluctuation graph is less than the preset similarity threshold, directly jump to step b5; Step b5: set r=r+1 and jump back to step b3; Step b6: Repeat the above steps b3 to b5 until r=R, then end the loop and obtain multiple normal coefficient waveforms; Step b7: Extract the similarity corresponding to each normal coefficient waveform, and use the data quality coefficient corresponding to the normal coefficient waveform with the greatest similarity as the speed optimization coefficient.

5. The intelligent networked traffic status monitoring method based on multi-source data fusion according to claim 4 is characterized in that: The road characteristic data include road section length, total lane width, actual total number of vehicles and maximum vehicle density; The method for generating the road full load factor within the T time period according to the road characteristic data includes: The road section length, lane width, actual number of vehicles and maximum vehicle density in the road feature data are marked as Ld n 、Wz n , Cm n and Cs n ; The length of the road section, the total width of the lane, the actual total number of vehicles and the maximum vehicle density are formalized and the road full load coefficient is calculated. The calculation formula is: Where Dlm n Indicates the road load factor of the nth topological road segment, Ld n represents the length of the nth topological segment, Wz n Indicates the total lane width of the nth topological road segment, Cm n represents the maximum vehicle density of the nth topological road segment, Cs n represents the actual number of vehicles on the nth topological road segment, and ln(·) represents the logarithmic function with e as the base.

6. The intelligent networked traffic status monitoring method based on multi-source data fusion according to claim 5 is characterized in that: The method for generating the state prediction model comprises: Step c1: Obtain the road load coefficient time series set of the nth topological road section; Step c2: preset time step B, sliding step K and sliding window length C; convert the historical road load coefficients in the road load coefficient time series set into multiple training samples using the sliding window method, use the training samples as the input of the state prediction model, and predict the road load coefficient after time step B as the output. The road load coefficient of each training sample is used as the prediction target, and the prediction accuracy is used as the training target to train the state prediction model; generate a state prediction model for predicting the road load coefficient in the T+a time period based on the historical road load coefficients in the road load coefficient time series set; wherein the state prediction model is an RNN neural network model.

7. The method for monitoring the state of intelligent networked traffic by multi-source data fusion according to claim 6 is characterized in that: Methods for obtaining a road load factor time series set include: The road load coefficient of the nth topological road section during the historical traffic status monitoring process is extracted and marked as the historical road load coefficient. The extracted historical road load coefficient is used to construct a road load coefficient time series set. The road load coefficient time series set includes i historical road load coefficients. The time intervals for obtaining the i historical road load coefficients are equal, and the i historical road load coefficients correspond to a time period.

8. The method for monitoring the state of intelligent networked traffic by multi-source data fusion according to claim 7 is characterized in that: Methods for obtaining traffic status warning information include: Step e1: Obtain the road load factor of N topological road sections in the time period T+a, and obtain speed data; Step e2: combining the road load factor and speed data into a feature vector, and inputting the feature vector into a pre-built traffic warning model to obtain traffic status warning information.

9. The method for monitoring the state of intelligent networked traffic by multi-source data fusion according to claim 8, characterized in that: The traffic warning model is obtained based on warning training data, and the warning training data includes warning feature data and its corresponding traffic status warning information; The warning characteristic data include road load factor and speed data; The method for acquiring the traffic status warning information in the warning training data includes: Step d1: extracting the road load factor of the nth topological road section in the time period T+a; and simultaneously obtaining the speed data of the nth topological road section in the time period T+a; Step d2: setting H road load factor intervals, and setting H traffic status warning information corresponding to the H road load factor intervals; each of the road load factor intervals is bound if and only if there is one traffic status warning information associated with it; Step d3: comparing the road full load coefficient of the nth topological road section with each road full load coefficient interval, and obtaining the road full load coefficient interval into which the road full load coefficient of the nth topological road section falls; Step d4: according to the road full load coefficient interval into which the road full load coefficient of the nth topological road section falls, the road full load coefficient of the nth topological road section is divided into corresponding traffic state warning information; and n=n+1 is set, and the process is returned to step d1; Step d5: repeating the above steps d1 to d4 until the cycle ends when n=N, so that each road full load coefficient is divided into H traffic status warning information in sequence; Step d6: adjusting the traffic status warning information according to the speed data of the N topological road sections; The method for adjusting traffic status warning information according to speed data of N topological road sections includes: Preset a speed threshold, and compare the speed data of each topological road section with the preset speed threshold; When the speed data is greater than or equal to the preset speed threshold, the corresponding road load factor is reduced by one level and adjusted to the next road load factor interval; When the speed data is less than the preset speed threshold, the corresponding road load factor will be increased by one level and adjusted to the previous road load factor range.

10. A multi-source data fusion intelligent networked traffic status monitoring system, used to implement the multi-source data fusion intelligent networked traffic status monitoring method according to any one of claims 1 to 9, characterized in that: include: A data preprocessing module is used to obtain speed data of M data sources in the nth topological road section within a T time period, and preprocess the speed data to obtain a data quality coefficient of the nth topological road section; A judgment module is used to analyze the data quality coefficient of the nth topological section to determine whether the M data sources meet the requirements. If not, a data optimization instruction is generated; if yes, a state analysis instruction is generated; An optimization module, for receiving a data optimization instruction, optimizing the data quality coefficient of the nth topological road section to obtain a speed optimization coefficient, and converting the data optimization instruction into a state analysis instruction; An analysis module is used to receive a state analysis instruction, obtain road characteristic data of the nth topological road section, generate a road full load coefficient within a time period T according to the road characteristic data, and input the generated road full load coefficient into a pre-generated state prediction model to obtain the road full load coefficient within a time period T+a; The matching module is used to extract the road load coefficient of the nth topological road section in the T+a time period, match the nth topological road section with the traffic status warning information according to the road load coefficient, and obtain the corresponding status warning information.

Images