Urban road travel time noise data processing method and system
By setting up data sensors on urban roads, adjusting the acquisition frequency of noise data based on driving data, and generating spatial and temporal characteristics of noise points, the problem of unreasonable noise data acquisition caused by different traffic flow in the prior art is solved, and a more comprehensive and efficient acquisition and analysis of noise data is achieved.
Patent Information
- Application Number
- CN202510155687.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-12
- Publication Date
- 2025-05-30
AI Technical Summary
In the analysis of urban road noise, the collection frequency is unreasonable due to different traffic flows, which leads to insufficient comprehensive data when the traffic flow is large, and wastes energy when the traffic flow is small, affecting the actual analysis of noise data.
The driving data of urban roads is collected through data sensors, the collection frequency of noise data is analyzed based on the driving data, and the collection frequency is adjusted according to the traffic flow and traffic jams, the spatial and temporal characteristics of noise points are generated, and the noise prediction table of urban roads is integrated to generate.
It improves the completeness and comprehensiveness of noise data collection, can adjust the collection frequency in real time according to traffic flow and traffic jams, and accurately locate the time and place of noise occurrence, which is conducive to timely taking noise control measures.
Smart Images

Figure CN120071610A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of noise data processing, relates to the technology of processing urban road travel time noise data, and specifically is a method and system for processing urban road travel time noise data. Background Art
[0002] Urban road noise data refers to the sound level information generated by traffic flow in the urban environment; such data is crucial for understanding the impact of traffic on the environment, planning quieter urban areas, and designing effective noise reduction measures; noise data processing can help planners identify potential high-noise areas and avoid building noise-sensitive buildings in these areas; through the analysis of noise data, the layout of quiet spaces such as urban green spaces and parks can be optimized to provide more leisure places for citizens; by processing noise data, the noise levels in different regions and time periods can be evaluated, and the traffic flow and noise levels in different road sections and time periods can be understood; it provides a data basis for traffic management and formulating and implementing noise control measures.
[0003] The prior art (a patent for invention with the application number: 201610980291.4) discloses a method for processing urban road travel time noise data, and the method includes: collecting the original travel time data within the time window of the section to be discriminated and calculating its standard deviation; using a box plot to perform data preprocessing on the original travel time data within the time window of the section to be discriminated; evaluating the probability of excessive data rejection in combination with the travel time characteristics and updating the range of the normal data interval; evaluating the probability that the noise data is not rejected in combination with the travel time characteristics and updating the range of the normal data interval; rejecting the travel time noise data; the prior art combines the characteristics of urban road travel time and uses the basic principle of the box plot to reject the noise data caused by abnormal driving behaviors of drivers; however, during the process of urban road noise analysis, the traffic flow is different in different time periods. If the same acquisition frequency is used to collect the driving data, it will lead to incomplete data collection when the traffic flow is large and waste energy when the traffic flow is small; it is not conducive to the actual analysis of noise data.
[0004] The present invention provides a method and system for processing urban road travel time noise data to solve the above technical problems. Summary of the Invention
[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; for this purpose, the present invention proposes a method and system for processing urban road travel time noise data, which is used to solve the technical problem that during the process of urban road noise analysis in the prior art, the traffic flow is different in different time periods. If the same acquisition frequency is used to collect the driving data, it will lead to incomplete data collection when the traffic flow is large and waste energy when the traffic flow is small; it is not conducive to the actual analysis of noise data.
[0006] To achieve the above object, a first aspect of the present invention provides a method and system for processing travel time noise data of urban roads, including:
[0007] Step S1: Collect driving data of urban roads through data sensors; wherein, the data sensors are set according to urban roads;
[0008] Step S2: Analyze the acquisition frequency of noise data based on the driving data; collect the noise data of urban roads based on the acquisition frequency;
[0009] Step S3: Generate the spatial characteristics of noise points on urban roads according to the collected noise data, and analyze the time characteristics of noise points according to the acquisition time of the noise data;
[0010] Step S4: Integrate the time characteristics and spatial characteristics of the noise points to obtain the noise prediction table of urban roads.
[0011] Preferably, the data sensors are set according to urban roads, including:
[0012] Obtain the road information of urban roads; wherein, the road information includes: road grade, number of lanes, and intersection data;
[0013] Divide the roads with the same road grade in the road information into the same type, and set the basic number of sensors for each type; Mark the number of lanes and the number of intersections as CS and JS respectively; Through the formula Calculate the road score DF of urban roads; wherein, α and β are proportionality coefficients greater than 0;
[0014] Compare the road scores with the score threshold respectively to obtain the number of added sensors; Calculate the sum of the basic number of sensors and the number of added sensors to obtain the final number of sensors; Uniformly set the data sensors on urban roads according to the final number of sensors.
[0015] It should be noted that the basic number of sensors is set according to historical experience, and the basic number of sensors corresponds to the minimum number of sensors for each type; The basic number of sensors can be updated according to the actual situation; The setting of the proportionality coefficient is based on actual experience. When the number of lanes and the number of intersections of several roads differ little, the proportionality coefficient is set larger. When the number of lanes and the number of intersections of several roads differ greatly, the proportionality coefficient is set smaller; The range of the proportionality coefficient is from 0 to 100; The score threshold is adjusted according to the setting of the proportionality coefficient. When the value of the proportionality coefficient increases, the score threshold also increases accordingly; When the value of the proportionality coefficient decreases, the score threshold also decreases accordingly.
[0016] The present invention sets the number of basic sensors for each road according to the road type of urban roads, calculates the road score of urban roads based on the road information of urban roads, determines the final number of sensors for urban roads according to the road score, and evenly arranges data sensors on urban roads according to the final number of sensors; it can set data sensors according to the actual situation of roads, which is beneficial to improving the comprehensiveness and integrity of the collected data.
[0017] Preferably, the acquisition frequency of noise data is analyzed according to the driving data, including:
[0018] Retrieve the driving data of urban roads; divide the driving data according to time periods; wherein, the driving data includes: traffic flow and traffic jam time.
[0019] Mark the traffic flow and traffic jam time as CLi and DTi; calculate the acquisition frequency of noise data through the formula CPi = JP - [γ × ln(CLi + 1) + θ × DTi]; where γ and θ are unit adjustment coefficients greater than 0; JP represents the basic acquisition frequency; i represents the i-th time period, i = 1, 2,..., n; n is a positive integer.
[0020] It should be noted that when the calculated acquisition frequency is less than the minimum acquisition frequency, the noise data is collected according to the minimum acquisition frequency; the minimum acquisition frequency is set according to historical data; the unit adjustment coefficient is used to remove the dimension in the formula and is obtained through experimental simulation.
[0021] The present invention calculates the acquisition frequency for each time period according to the driving data of urban roads and collects noise according to the acquisition frequency. It can set the acquisition frequency according to the traffic flow and traffic jam conditions in historical time periods, which is beneficial to improving the integrity and comprehensiveness of the collected data.
[0022] Preferably, generating the spatial characteristics of noise points on urban roads according to the collected noise data includes:
[0023] Retrieve the noise data within a set time period; after normalizing the noise data, fit the noise data into a noise signal.
[0024] Use the local outlier factor to identify the outliers in the noise signal; regard the outliers as the noise points on urban roads; obtain the structural topology map of urban roads, map the corresponding noise points to the structural topology map of urban roads, and mark and number the noise points; obtain the spatial characteristics of the noise points.
[0025] The present invention analyzes the outliers in the noise signal according to the collected noise data, regards the outliers as the noise points on urban roads, and maps the corresponding noise points to the structural topology map of urban roads; it is beneficial to lay a data foundation for subsequent analysis.
[0026] Preferably, identifying the outliers in the noise signal by using the local outlier factor includes:
[0027] Retrieving the noise signal; setting the number of neighbors of each point to k;
[0028] Calculating the reachability distance reach-dist k (p, o) = max{k - distance(o), d(p, o)} between each point p and its neighbor o; where k - distance(o) represents the distance from o to its k-th nearest neighbor; d(p, o) is the actual distance between p and o. k (p, o);
[0029] Calculating the local reachability density lrd of p corresponding to its k nearest neighbors through the formula k (p); where N k (p) represents the set of k nearest neighbors of p; calculating the LOF value of point p through the formula ;
[0030] Determining the LOF threshold in a cross - validation manner, and when the LOF value is greater than the LOF threshold, marking the corresponding point as an outlier.
[0031] Preferably, analyzing the time characteristics of the noise points according to the acquisition time of the noise data includes:
[0032] Retrieving the noise data; integrating the noise data according to the set time period; calculating the total noise value of each time period;
[0033] Judging whether the total noise value is greater than the noise threshold; if yes, marking the corresponding time period; if no, analyzing the total noise value of the next time period; integrating the marked time periods to obtain the time characteristics of the corresponding noise points.
[0034] Preferably, calculating the total noise value of each time period includes:
[0035] Retrieving the noise data, fitting the noise data into a noise function f(t) according to the time period; dividing the time into m time nodes according to the set time period;
[0036] Calculating the total noise value of the j-th time period through the formula ; where δ is a correction coefficient greater than 0; j = 1, 2,..., m.
[0037] Preferably, integrating the time characteristics and spatial characteristics of the noise points to obtain the noise prediction table of the urban road includes:
[0038] Retrieve the numbers of noise points and their corresponding time features; integrate the changes of noise points and time features into a noise prediction sequence;
[0039] Retrieve a noise prediction model, input the noise prediction sequence into the noise prediction model to obtain the corresponding noise time; wherein, the noise prediction model is constructed based on an artificial intelligence model; the noise time refers to the time period when the total noise value is greater than the noise threshold;
[0040] Integrate the noise time to obtain a time prediction table for the corresponding noise points; integrate the time prediction tables of several noise points into a noise prediction table for the urban road.
[0041] The present invention uses the time features and spatial features of noise points to predict the noise of noise points, analyzes and obtains the noise time, and integrates the noise time to generate a noise prediction table; it can predict the noise occurring at each noise point, integrate the time features and spatial features of the noise, and can accurately locate the time and location where the noise appears, which is beneficial to taking interference measures for the emerging noise in a timely manner.
[0042] Preferably, the noise prediction model is constructed based on an artificial intelligence model and includes:
[0043] Obtain a standard data set; wherein, the standard data set includes standard input data consistent with the content attributes of the noise prediction sequence and standard output data consistent with the content attributes of the noise time;
[0044] Divide the standard data set into a training set, a validation set, and a test set according to a set ratio; use the training set to train the artificial intelligence model; use the validation set to adjust the internal parameters of the artificial intelligence model; use the test set to test the trained artificial intelligence model; when the test passes, mark the artificial intelligence model as the noise prediction model; otherwise, retrain the artificial intelligence model.
[0045] The second aspect of the present invention provides an urban road travel time noise data processing system, including: a noise processing module, and a data acquisition module and a noise prediction module connected thereto;
[0046] The data acquisition module: is used to collect the driving data of the urban road through data sensors; wherein, the data sensors are set according to the urban road;
[0047] The noise processing module: is used to analyze the acquisition frequency of the noise data according to the driving data; collect the noise data of the urban road based on the acquisition frequency; generate the spatial features of the noise points on the urban road according to the collected noise data, and analyze the time features of the noise points according to the acquisition time of the noise data;
[0048] Noise prediction module: used to integrate the time features and spatial features of noise points to obtain a noise prediction table for urban roads.
[0049] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0050] 1. The present invention sets the number of basic sensors for each road according to the road type of urban roads, calculates the road score of urban roads according to the road information of urban roads, determines the final number of sensors for urban roads according to the road score, and evenly arranges data sensors on urban roads according to the final number of sensors; it can set data sensors according to the actual situation of the road; calculates the acquisition frequency for each time period according to the driving data of urban roads, and collects noise according to the acquisition frequency, and can set the acquisition frequency according to the traffic flow and traffic jam conditions in historical time periods; is conducive to improving the integrity and comprehensiveness of the collected data.
[0051] 2. The present invention analyzes the outliers in the noise signal based on the collected noise data, takes the outliers as the noise points of urban roads, and maps the corresponding noise points to the structural topology map of urban roads; is conducive to laying a data foundation for subsequent analysis; uses the time features and spatial features of noise points to predict the noise of noise points, analyzes to obtain the noise time, and integrates the noise time to generate a noise prediction table; can predict the noise that appears at each noise point, integrates the time features and spatial features of the noise, and can accurately locate the time and location where the noise appears, which is conducive to taking interference measures in time for the appearance of noise. Description of the Drawings
[0052] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0053] Figure 1 It is a schematic diagram of the overall steps of the method of the present invention;
[0054] Figure 2 It is a schematic diagram of the steps of sensor setting and acquisition frequency calculation of the present invention;
[0055] Figure 3 It is a schematic diagram of the noise prediction steps of the present invention;
[0056] Figure 4 It is a schematic diagram of the working steps of the system of the present invention. Detailed Embodiments
[0057] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.
[0058] Please refer to Figure 1 , an embodiment of the first aspect of the present invention provides a method for processing urban road travel time noise data, including:
[0059] Step S1: Collect driving data of urban roads through data sensors; wherein, the data sensors are set according to urban roads;
[0060] Step S2: Analyze the acquisition frequency of noise data based on the driving data; collect the noise data of urban roads based on the acquisition frequency;
[0061] Step S3: Generate the spatial characteristics of the noise points on the urban road according to the collected noise data, and analyze the time characteristics of the noise points according to the acquisition time of the noise data;
[0062] Step S4: Integrate the time characteristics and spatial characteristics of the noise points to obtain the noise prediction table of the urban road.
[0063] Please refer to Figure 2 , obtain the road information of the urban road; wherein, the road information includes: road grade, number of lanes and intersection data; divide the roads with the same road grade in the road information into the same type, and set the basic number of sensors for each type; mark the number of lanes and the number of intersections as CS and JS respectively; through the formula Calculate the road score DF of the urban road; wherein, α and β are proportionality coefficients greater than 0; compare the road score with the score threshold respectively to obtain the number of added sensors; calculate the sum of the basic number of sensors and the number of added sensors to obtain the final number of sensors; evenly set the data sensors on the urban road according to the final number of sensors.
[0064] It should be noted that when the number of lanes of the urban road is more, the value of α×arctan(CSπ) is larger, and the road score of the urban road is larger; when the number of intersections of the urban road is more, then The value is larger, and the road score of the urban road is larger; therefore, the road score of the urban road is positively correlated with the number of lanes and the number of intersections of the urban road.
[0065] Collect the driving data of urban roads through data sensors; divide the driving data according to time periods; among them, the driving data includes: traffic flow and traffic jam time; mark the traffic flow and traffic jam time as CLi and DTi; calculate the acquisition frequency of noise data through the formula CPi = JP - [γ × ln(CLi + 1) + θ × DTi]; collect the noise data of urban roads based on the acquisition frequency; where γ and θ are unit adjustment coefficients greater than 0; JP represents the basic acquisition frequency; i represents the i-th time period, i = 1, 2,..., n; n is a positive integer.
[0066] It should be noted that when the calculated acquisition frequency is less than the minimum acquisition frequency, the noise data is collected according to the minimum acquisition frequency; the minimum acquisition frequency is set according to historical data; the unit adjustment coefficient is used to remove the dimension in the formula and is obtained according to experimental simulation.
[0067] It should be noted that the greater the traffic flow of the road, the greater the value of γ × ln(CLi + 1), and the smaller the acquisition frequency CPi in the corresponding time period; the longer the traffic jam time of the road, the greater the value of θ × DTi, and the smaller the corresponding acquisition frequency CPi; therefore, the acquisition frequency is inversely correlated with the traffic flow and traffic jam time of the road.
[0068] It should be noted that the number of basic sensors is set according to the type of urban roads, and the number of additional sensors is analyzed according to the road information of each road to obtain the final number of sensors; the sensors are evenly arranged on the urban roads according to the final number of sensors, which can make the collected noise data more comprehensive and is conducive to subsequent data analysis; the acquisition frequency of the noise data of urban roads is analyzed according to the driving data of urban roads, and the noise data is collected based on the acquisition frequency; the acquisition frequency can be adjusted in real time according to the traffic flow and traffic jam situation, which is conducive to improving the integrity and effectiveness of the collected data.
[0069] Please refer to Figure 3 , retrieve the noise data within the set time period; after standardizing the noise data, fit the noise data into a noise signal; set the number of neighbors of each point to k; calculate the reachable distance reach-dist k (p, o) = max(k - distance(o), d(p, o)} between each point p and its neighbor o; where k - distance(o) represents the distance from o to its k-th nearest neighbor; d(p, o) is the actual distance between points p and o; calculate the local reachability density lrd k (p, o); where, k - distance(o) represents the distance from o to its k-th nearest neighbor; d(p, o) is the actual distance between points p and o; calculate the local reachability density lrd of p corresponding to its k nearest neighbors through the formula k (p); where, N k(p) represents the set of k nearest neighbors of p; the LOF value of point p is calculated by the formula ; the LOF threshold is determined by cross-validation. When the LOF value is greater than the LOF threshold, the corresponding point is marked as an outlier; the outlier is used as the noise point of the urban road; the structural topology map of the urban road is obtained, the corresponding noise point is mapped to the structural topology map of the urban road, and the noise point is marked and numbered.
[0070] Retrieve the noise data; integrate the noise data according to the set time period; fit the noise data into a noise function f(t) according to the time period; divide the time into m time nodes according to the set time period; calculate the total noise value of the jth time period by the formula ; where δ is a correction coefficient greater than 0; j = 1, 2,..., m; determine whether the total noise value is greater than the noise threshold; if yes, mark the corresponding time period; if no, analyze the total noise value of the next time period; integrate the marked time periods to obtain the time characteristics of the corresponding noise point.
[0071] Retrieve the number of the noise point and the corresponding time characteristics; integrate the change of the noise point and the time characteristics into a noise prediction sequence; retrieve the noise prediction model, input the noise prediction sequence into the noise prediction model to obtain the corresponding noise time; where the noise prediction model is constructed based on an artificial intelligence model; the noise time refers to the time period when the total noise value is greater than the noise threshold; integrate the noise times to obtain the time prediction table of the corresponding noise point; integrate the time prediction tables of several noise points to obtain the noise prediction table of the urban road.
[0072] It should be noted that the noise prediction model is constructed based on an artificial intelligence model, including:
[0073] Obtain a standard data set; where the standard data set includes standard input data consistent with the content attributes of the noise prediction sequence and standard output data consistent with the content attributes of the noise time; divide the standard data set into a training set, a validation set and a test set according to the set ratio; use the training set to train the artificial intelligence model; use the validation set to adjust the internal parameters of the artificial intelligence model; use the test set to test the trained artificial intelligence model; when the test passes, mark the artificial intelligence model as the noise prediction model; otherwise, retrain the artificial intelligence model.
[0074] It should be noted that the noise data within a set time period is integrated to obtain a noise signal. The spatial and temporal characteristics of the noise signal are analyzed respectively, and the number of the noise point and the corresponding temporal characteristics are integrated to obtain a noise prediction sequence. The trained model is used to analyze the noise prediction sequence to obtain the noise time corresponding to the noise point. The noise times are integrated to obtain a noise prediction table for the urban road. It is possible to analyze the noise data of the noise points, which is conducive to taking measures for the noise points in a timely manner and reducing the problem of noise disturbing residents.
[0075] Please refer to Figure 4 , an embodiment of the second aspect of the present invention provides an urban road travel time noise data processing system, including: a noise processing module, and a data acquisition module and a noise prediction module connected thereto;
[0076] Data acquisition module: used to collect the driving data of the urban road through data sensors; wherein, the data sensors are set according to the urban road;
[0077] Noise processing module: used to analyze the acquisition frequency of the noise data according to the driving data; collect the noise data of the urban road based on the acquisition frequency; generate the spatial characteristics of the noise points on the urban road according to the collected noise data, and analyze the temporal characteristics of the noise points according to the acquisition time of the noise data;
[0078] Noise prediction module: used to integrate the temporal characteristics and spatial characteristics of the noise points to obtain a noise prediction table for the urban road.
[0079] Some of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is obtained by software simulation of a large amount of collected data to get a formula closest to the actual situation; the preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.
[0080] Working principle of the present invention: The present invention collects the driving data of the urban road through data sensors; wherein, the data sensors are set according to the urban road; analyzes the acquisition frequency of the noise data according to the driving data; collects the noise data of the urban road based on the acquisition frequency; generates the spatial characteristics of the noise points on the urban road according to the collected noise data, and analyzes the temporal characteristics of the noise points according to the acquisition time of the noise data; integrates the temporal characteristics and spatial characteristics of the noise points to obtain a noise prediction table for the urban road.
[0081] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.
Claims
1. A method for processing urban road travel time noise data, characterized in that: include: Step S1: collecting driving data of urban roads through data sensors; wherein the data sensors are set according to urban roads; Step S2: analyzing the collection frequency of noise data according to the driving data; collecting noise data of urban roads based on the collection frequency; Step S3: Generate spatial characteristics of noise points on urban roads according to the collected noise data, and analyze temporal characteristics of noise points according to the collection time of the noise data; Step S4: Integrate the temporal characteristics and spatial characteristics of the noise points to obtain a noise prediction table for urban roads.
2. The method for processing urban road travel time noise data according to claim 1, characterized in that: The data sensor is arranged according to the urban road, and includes: Obtaining road information of urban roads; wherein the road information includes: road grade, number of lanes and intersection data; The roads with the same road grade in the road information are divided into the same type, and the number of basic sensors of each type is set; the number of lanes and the number of intersections are marked as CS and JS respectively; through the formula Calculate the road score DF of the urban road; where α and β are proportional coefficients greater than 0; The road scores are compared with the score thresholds to obtain the number of sensors to be added; the sum of the number of basic sensors and the number of added sensors is calculated to obtain the final number of sensors; and the data sensors are evenly arranged on the urban roads according to the final number of sensors.
3. The method for processing urban road travel time noise data according to claim 1, characterized in that: The step of analyzing the collection frequency of noise data according to the driving data includes: Retrieving the driving data of urban roads; dividing the driving data into time periods; wherein the driving data includes: traffic volume and traffic jam time; The traffic volume and traffic jam time are marked as CLi and DTi; the collection frequency of noise data is calculated by the formula CPi=JP-[γ×ln(CLi+1)+θ×DTi]; where γ and θ are unit adjustment coefficients greater than 0; JP represents the basic collection frequency; i represents the i-th time period, i=1, 2,…, n; and n is a positive integer.
4. The method for processing urban road travel time noise data according to claim 1, characterized in that: The generating of the spatial characteristics of the noise points of the urban roads according to the collected noise data includes: Retrieving noise data within a set time period; after standardizing the noise data, fitting the noise data into a noise signal; The outliers in the noise signal are identified by using the local outlier factor; the outliers are regarded as the noise points of the urban roads; the structural topology map of the urban roads is obtained, the corresponding noise points are mapped to the structural topology map of the urban roads, and the noise points are marked and numbered; the spatial characteristics of the noise points are obtained.
5. The method for processing urban road travel time noise data according to claim 4, characterized in that: The method of using the local outlier factor to identify outliers in the noise signal includes: Retrieve the noise signal; set the number of neighbors of each point to k; Through the formula reach-dist k (p,o)=max{k-distance(o),d(p,o)}Calculate the reach-dist between each point p and its neighbor o k (p,o); where k-distance(o) represents the distance from o to its kth nearest neighbor; d(p,o) is the actual distance between points p and o; By formula Calculate the local reachability density lrd of p corresponding to its k nearest neighbors k (p); where N k (p) represents the set of k nearest neighbors of p; by the formula Calculate the LOF value of point p; The LOF threshold is determined by cross-validation. When the LOF value is greater than the LOF threshold, the corresponding point is marked as an outlier.
6. The method for processing urban road travel time noise data according to claim 1, characterized in that: The step of analyzing the time characteristics of noise points according to the acquisition time of noise data includes: Retrieve noise data; integrate noise data according to the set time period; calculate the total noise value of each time period; Determine whether the total noise value is greater than the noise threshold; if yes, mark the corresponding time period; if no, analyze the total noise value of the next time period; integrate the marked time periods to obtain the time characteristics of the corresponding noise points.
7. The method for processing urban road travel time noise data according to claim 6, characterized in that: The calculating of the total noise value in each time period includes: Retrieve noise data, and fit the noise data into a noise function f(t) according to the time period; divide the time into m time nodes according to the set time period; By formula Calculate the total noise value of the j-th time period; where δ is a correction coefficient greater than 0; j=1, 2, ..., m.
8. The method for processing urban road travel time noise data according to claim 1, characterized in that: The time characteristics and spatial characteristics of the noise points are integrated to obtain a noise prediction table for urban roads, including: Retrieve the number of noise points and the corresponding time characteristics; integrate the changes of noise points and time characteristics into a noise prediction sequence; Retrieve the noise prediction model, input the noise prediction sequence into the noise prediction model, and obtain the corresponding noise time; wherein the noise prediction model is constructed based on the artificial intelligence model; the noise time refers to the time period when the total noise value is greater than the noise threshold; The noise time is integrated to obtain the time prediction table of the corresponding noise point; the time prediction tables of several noise points are integrated into the noise prediction table of the urban road.
9. The method for processing urban road travel time noise data according to claim 8, characterized in that: The noise prediction model is constructed based on an artificial intelligence model, including: Acquire a standard data set; wherein the standard data set includes standard input data consistent with the content attributes of the noise prediction sequence, and standard output data consistent with the temporal content attributes of the noise; Divide the standard data set into training set, validation set and test set according to the set ratio; use the training set to train the artificial intelligence model; use the validation set to adjust the internal parameters in the artificial intelligence model; use the test set to test the trained artificial intelligence model; when the test passes, mark the artificial intelligence model as a noise prediction model; otherwise, retrain the artificial intelligence model.
10. A system for processing urban road travel time noise data, applied to an urban road travel time noise data processing method according to any one of claims 1 to 9, characterized in that: include: Noise processing module, and the data acquisition module and noise prediction module connected thereto; Data collection module: used to collect driving data of urban roads through data sensors; wherein the data sensors are set according to urban roads; Noise processing module: used to analyze the collection frequency of noise data according to driving data; collect noise data of urban roads based on the collection frequency; generate spatial characteristics of noise points of urban roads according to the collected noise data, and analyze the time characteristics of noise points according to the collection time of noise data; Noise prediction module: used to integrate the temporal and spatial characteristics of noise points to obtain a noise prediction table for urban roads.
Citation Information
Patent Citations
Urban Road Travel Time Noise Data Processing Method
CN106571035B
