CN112330074A - Bayonet traffic early warning method based on mobile police service - Google Patents
Bayonet traffic early warning method based on mobile police service Download PDFInfo
- Publication number
- CN112330074A CN112330074A CN202011393599.1A CN202011393599A CN112330074A CN 112330074 A CN112330074 A CN 112330074A CN 202011393599 A CN202011393599 A CN 202011393599A CN 112330074 A CN112330074 A CN 112330074A
- Authority
- CN
- China
- Prior art keywords
- traffic
- early warning
- data
- bayonet
- day
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims abstract description 15
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims abstract 10
- 238000007781 pre-processing Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 15
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 abstract description 5
- 238000012423 maintenance Methods 0.000 abstract description 3
- 230000002354 daily effect Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000003203 everyday effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241001622623 Coeliadinae Species 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000001373 regressive effect Effects 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Operations Research (AREA)
- Human Resources & Organizations (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Algebra (AREA)
- Development Economics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a bayonet traffic early warning method based on mobile police, which can ensure that a traffic police can find an abnormal road section in time, simplify the configuration process of traffic police on bayonet traffic early warning parameters, and further ensure that the traffic police can optimize bayonet distribution and improve the operation and maintenance level of bayonet equipment. In the technical scheme of the invention, the traffic flow of the forecast day is forecasted by the difference autoregressive moving average model ARIMA, and the traffic police can receive early warning information before the occurrence of traffic abnormality by setting an early warning threshold value once the traffic abnormality occurs, so that the traffic police can reach the abnormal place in time and solve the problem in time; based on historical data, a differential autoregressive moving average model ARIMA is established on the main road to be monitored on each day of the week, and the predicted value of the traffic flow obtained by predicting the differential autoregressive moving average model ARIMA is ensured to accord with the characteristics of the peak value and the valley value of the bayonet daily flow in each day of urban life.
Description
Technical Field
The invention relates to the technical field of intelligent traffic monitoring, in particular to a bayonet traffic early warning method based on mobile police service.
Background
In the existing traffic management mode, traffic abnormality is often allocated to a traffic police for correspondence when the traffic abnormality occurs on a certain road section, and the arrival time of the traffic police is often later than the accident occurrence time; although some managers may predict the road section with the problem in advance due to experience, the manager may not accurately determine specific parameters such as time and place because the manager depends too much on personal experience.
Disclosure of Invention
In order to solve the problem that a traffic police cannot allocate an abnormal road section in time due to the fact that the road section with abnormal traffic cannot be obtained in time in the conventional traffic management mode, the invention provides a bayonet flow early warning method based on mobile police, which can ensure that the traffic police can find the abnormal road section in time, simplify the configuration process of traffic police on bayonet flow early warning parameters, and further ensure that the traffic police can optimize bayonet distribution and improve the operation and maintenance level of bayonet equipment.
The technical scheme of the invention is as follows: a bayonet traffic early warning method based on mobile police service is characterized by comprising the following steps:
s1: constructing a differential autoregressive moving average model ARIMA;
s2: confirming a main road to be monitored; acquiring a specific date of a predicted day;
s3: setting: the prediction day is a week tau, and the periodicity xi selected by the observation data is set;
collecting all historical traffic flow data which pass through all gates on the main road to be monitored in the whole day of each week tau in xi weeks before the prediction day; preprocessing the acquired historical traffic flow data, and recording the preprocessed sample data LiWherein xi is a positive integer;
s4: based on dynamic time warping algorithm DTW, the preprocessed sample data L is processediAnd the sample data L after the previous pretreatmentjJudging the similarity of the phase time;
when DTW (L)i,Lj) If > λ, executing step S5;
otherwise, go to step S6;
wherein, the sample data L after the previous preprocessingjThe training sample data of each week tau in the previous xi week corresponding to the previous same-frequency prediction day; the same-frequency prediction day as the prediction day is the prediction day of the week tau;
when the last same-frequency prediction day does not exist, the sample data L after the previous preprocessing isjThe value of (1) is null;
λ is the preset similarity comparison threshold when DTW (L)i,Lj) λ represents that the similarity of the two participating in comparison is low;
s5: based on the sample data L after the pretreatmentiTraining the autoregressive moving average model ARIMA to obtain the trained autoregressive moving average model ARIMA;
setting the trained autoregressive moving average model ARIMA as a week tau prediction model used at this time; step S7 is executed;
s6: setting the trained autoregressive moving average model ARIMA corresponding to the last same-frequency prediction day as the week tau prediction model used at this time;
s7: obtaining a prediction time period, wherein the length of the prediction time period is no more than 24 hours of the day of the prediction day;
s8: predicting to obtain a predicted value of the traffic flow of the road bayonet of the main road to be monitored in the prediction time period based on the used model for the week tau prediction corresponding to the prediction day;
when the predicted value of the traffic flow exceeds a preset early warning threshold value, sending early warning information;
s9: and acquiring the next prediction day and the main road to be monitored, and circularly executing the steps S3-S8.
It is further characterized in that:
in step S8: the early warning threshold includes: a flow early warning threshold value and a comparability early warning threshold value;
the traffic early warning threshold value means that early warning is generated when the variation range of the traffic flow number in the last hour exceeds the set early warning threshold value;
the geometric early warning threshold value means that early warning can be generated when the geometric variation amplitude of the vehicle passing flow number in the latest hour and the vehicle passing flow number in the same time period of yesterday exceeds a set early warning threshold value;
in step S4, DTW (L)i,Lj) The algorithm of (1) is as follows:
D(Li,Lj) Representing the sequence a
With sequence b
European distance
The sum of the cumulative distances to the smallest proximate point that the point can reach;
the number ξ of the cycles is set as 4;
the setting mode of the early warning threshold value comprises the following steps: the traffic police sets through the mobile police service device;
the traffic police can also set the starting time, the ending time, the flow and the same proportion relation of the prediction time period through the mobile police device, and select the main road to be monitored; wherein, the flow and the same proportion relation are as follows: sending out early warning information under the condition that two early warning thresholds are met simultaneously, or sending out early warning information when one selected early warning threshold is met;
in step S8, after the warning information is sent to the mobile police device of the traffic police, the traffic police disposes according to the warning information;
after the number of vehicles passing through the checkpoint of the early warning information is manually verified and does not conform to the actual situation, the historical data is manually corrected through the mobile police service device, and the original data is uploaded and covered to serve as observation data for updating the differential autoregressive moving average model ARIMA subsequently;
the parameters of the autoregressive moving average model ARIMA support manual configuration;
in step S3, preprocessing the acquired historical traffic data, where the preprocessing includes:
a 1: keeping the traffic data of which the total number of unidirectional average daily traffic vehicles is greater than a preset available traffic value of the traffic data; deleting data related to the bayonets which do not meet the conditions;
a 2: removing invalid bayonet traffic data from the historical traffic data;
the data of the traffic flow of the invalid card port is as follows: under the condition that the traffic capacity of the road is normal, the historical traffic flow data is 0 or the number of abnormal data items of which the change range of the historical traffic flow data exceeds the data change invalid threshold exceeds the preset no-day threshold.
According to the bayonet traffic early warning method based on mobile police, the traffic flow of a predicted day is predicted through a differential autoregressive moving average model ARIMA, so that traffic polices can obtain predicted data in advance, and the data is accurate and objective; the early warning threshold value is set to ensure that once the traffic abnormity occurs, the traffic police can receive early warning information before the traffic abnormity occurs, can reach the abnormal place in time and solve the problem in time; in the technical scheme, a differential autoregressive moving average model ARIMA is established on the main road to be monitored on the basis of each day of a week based on historical data, so that the traffic flow predicted value obtained by predicting the differential autoregressive moving average model ARIMA is ensured to accord with the characteristics of the peak value and the valley value of the bayonet daily flow of each day in urban life, and the problem of inaccurate result caused by predicting different working days and rest days by a unified model is avoided; the Dynamic Time Warping (DTW) algorithm is used for judging the similarity of the time sequence of the training data of the two models before and after the week tau, so that the prediction model is ensured to be dynamically updated, the training frequency of the stable bayonet prediction model is reduced on the basis of improving the referenceability of the predicted value, the calculated amount of the system is reduced, and the working efficiency of the system is improved; training and adjusting a differential autoregressive moving average model ARIMA by setting the cycle number selected by the observation data and passing the latest historical data in the cycle every day again, so as to ensure that the data obtained on each prediction day are in accordance with the latest road condition; based on the early warning information and the traffic flow prediction result in the technical scheme of the invention, the configuration process of traffic police on the traffic flow early warning parameters of the gate is simplified, and further the traffic police can optimize the gate layout and improve the operation and maintenance level of the gate equipment.
Drawings
Fig. 1 is a flow diagram of a bayonet traffic early warning method based on mobile police service.
Detailed Description
As shown in fig. 1, the invention relates to a bayonet traffic early warning method based on mobile police service, which comprises the following steps.
S1: and constructing a differential autoregressive moving average model ARIMA.
S2: confirming a main road to be monitored; the specific date of the predicted day is obtained.
S3: setting: predicting day as week tau, and setting cycle number xi selected by observation data;
collecting all historical traffic flow data which pass through all gates on a main road to be monitored in the whole day of each week tau in a xi week before the forecast day; preprocessing the collected historical traffic flow data, and recording the preprocessed sample data LiWherein xi is a positive integer; preprocessing the collected historical traffic flow data, wherein the preprocessing content comprises the following steps:
a 1: keeping the traffic data of which the total number of unidirectional average daily traffic vehicles is greater than a preset available traffic value of the traffic data; deleting data related to the bayonets which do not meet the conditions;
a 2: removing data related to invalid gates from historical traffic flow data;
the data of the traffic flow of the invalid card port is as follows: under the condition that the traffic capacity of the road is normal, the historical traffic flow data is 0 or the number of abnormal data items of which the change range of the historical traffic flow data exceeds the data change invalid threshold exceeds the preset invalid day threshold; that is, when the road is normally on, the generated historical traffic data of the bayonet records is continuously 0 or is close to the white noise in the historical traffic data.
In actual work, some bayonets fail accidentally, so invalid data can be returned, the generation of time sequence data by the invalid data can cause too large fluctuation of the whole time sequence, and further cause that the model cannot be effectively trained, so that the bayonets are not in the training range of the model, and parameters are manually configured by policemen under necessary conditions for the bayonets;
in the embodiment, historical traffic flow data of 5 urban main road checkpoints of different areas of a certain provincial meeting city are selected for analysis; the preprocessing content of the data comprises the following steps: the total daily flow of the unidirectional bayonet flow data in the time range of one month (invalid day threshold) has no abnormal data, and the total average daily traffic of the bayonet is more than 10000 (available bayonet flow value);
the traffic data of the traffic data are acquired under the condition that the traffic capacity of the road where the traffic data is located under normal conditions can be represented by the historical traffic data, a time sequence is constructed on the basis of the data for selecting a differential autoregressive moving average model ARIMA, and the constructed model can be predicted according to the actual conditions of the road; in the present embodiment, the cycle number ξ is set as 4; that is, the historical traffic flow data of the day 4 weeks before the observation day, which is the same as the observation day as the day τ, is extracted as the historical traffic flow data each time; setting the periodicity ξ according to the stable conditions of different roads; the road periodicity of the main road to be monitored with stable traffic condition can be set relatively small, and the periodicity ξ of the road with poor traffic condition stability can be set relatively large; the method ensures that historical data collection can correctly represent the actual condition of the road.
In specific implementation, the collected data is preprocessed to obtain available sample data, and the selected time sequence is recorded as { Y }t,ξ,τB, wherein t represents a certain moment at 24, ξ represents the periodicity selected by the observation data, τ represents the day of prediction as the day of week, such as Monday and Tuesday, and τ takes the value of 1-7 respectively; grouping all data according to the corresponding tau, so as to obtain all data of 7 days in a week; the details are shown in table 1 below:
table 1: training data of time series
Table 1 shows the sample data L after this preprocessing with the number 00001iThe observed values in table 1 are bayonet flow historical data of bayonet with the number of 00001 at the corresponding moment; where ξ is 4, the data of week 1 and week 4 are shown in table 1, and the data of week 2 and week 3 are omitted.
S4: sample data L after the preprocessing is performed based on a Dynamic Time Warping (DTW) algorithmiAnd the sample data L after the previous pretreatmentjJudging the time similarity;
when DTW (L)i,Lj) If > λ, executing step S5;
otherwise, go to step S6;
wherein, the sample data L after the previous pretreatmentjTraining sample data of tau in each week in the previous xi week corresponding to the previous same-frequency prediction day; with the same frequency of days of prediction being weeks tau as days of predictionPredicting the day;
when the last same-frequency prediction day does not exist, sample data L after the previous preprocessingjThe value of (1) is null;
λ is the preset similarity comparison threshold when DTW (L)i,Lj) λ represents that the similarity of the two participating in comparison is low;
DTW(Li,Lj) The algorithm of (1) is as follows:
D(Li,Lj) Representing the sequence a
With sequence b
European distance
The sum of the cumulative distances to the minimum proximate point that the point can reach.
According to the technical scheme, time similarity judgment is carried out on training data of a front model and a rear model of a week tau on the basis of a dynamic time warping algorithm DTW, invalid data caused by bayonet data abnormity and other factors cannot be in one-to-one correspondence, the Euclidean distance is not suitable for similarity measurement, and the smaller the DTW distance is, the smaller the time sequence change is; the similarity comparison threshold lambda is preset, when the DTW distance is smaller than or equal to the parameter lambda, a new time series model does not need to be trained, the flow can be directly predicted by using a previous model corresponding to a week tau prediction day, otherwise, the traffic flow of a road in the week is greatly changed, the prediction model can be predicted only by retraining the prediction model by using new training data, and the setting of the parameter lambda can ensure that the model can be trained by using the latest flow data and the predicted value can meet the latest change of traffic flow; and when the road traffic condition is stable, the calculation amount of the system can be reduced, and the system efficiency is improved.
S5: based on sample data L after the preprocessingiTraining an autoregressive moving average model ARIMA to obtain a trained autoregressive moving average model ARIMA; setting the trained autoregressive moving average model ARIMA as a week tau prediction model used at this time; step S7 is executed.
S6: setting the trained autoregressive moving average model ARIMA corresponding to the previous same-frequency prediction day as the week tau prediction model used at this time; step S7 is executed.
The autoregressive Moving Average model ARIMA (auto Regressive Integrated Moving Average model) comprises three important components, an autoregressive model AR (p) with the order p, a Moving Average model MA (q) with the order q, and a difference term D (d) with the order d. The p-order AR model describes a time series { Y }tThe linear relationship of hourly bayonet flow observations at time t and the previous p times can be expressed as:
Yt＝εt+θ1Yt-1+θ2Yt-2+…+θpYt-p
wherein epsilontTo the error term, θpAre coefficients. The q-order MA model describes the time series YtLinear relationship to historical noise:
wherein,
is an error term, mu is historical noise, lambdaqFor coefficients, a linear combination of AR (p) and MA (q) can be used to predict the stationary sequence { Y }tIf the observation is passed { Y }tIf the sequence is a non-stationary sequence, d-order difference calculation is needed:
ΔdYt＝(1-L)dYt
wherein Δ is a difference sign, L is a lag operator, and the ARIMA model can be expressed as:
θ(L)ΔdYt＝ε+λ(L)μt；
and predicting the xi +1 period by the trained autoregressive moving average model ARIMA according to xi period data, and outputting a predicted value of the traffic flow of the bayonet in 24 hours per hour.
S7: acquiring a prediction time period, wherein the length of the prediction time period does not exceed 24 hours of a prediction day; that is, data within 24 hours of the day of the forecast day can be given at the longest; in specific implementation, according to the needs of police officers, all the predicted values do not need to be obtained, and only the numerical values of the specified time periods in a day need to be obtained, such as: early warning start time 7: 30. early warning end time 18: 40.
s8: calculating to obtain a passing traffic flow predicted value of a road bayonet of a main road to be monitored in a predicted time period based on a week tau prediction model corresponding to the prediction day and used at this time;
the early warning threshold includes: a flow early warning threshold value and a comparability early warning threshold value; such as: the flow early warning threshold value is set to be 110, namely, more than 110 vehicles pass by every hour, namely, the vehicle flow is abnormal; the comparably early warning threshold is set to be 5%, namely when the traffic flow variation range in the same time period of the last week tau exceeds 5%, data abnormity occurs, and whether traffic abnormity or bayonet device abnormity occurs needs to be confirmed;
the traffic early warning threshold value means that early warning is generated when the change range of the traffic flow number in the last hour exceeds the set early warning threshold value;
the geometric early warning threshold value means that early warning can be generated when the geometric change amplitude of the vehicle passing flow number in the latest hour and the vehicle passing flow number in the same time period of yesterday exceeds a set early warning threshold value.
Through the setting of the early warning threshold value, police officers can be ensured to obtain the appointed early warning information, and corresponding matters are arranged in time before the road abnormity occurs.
During specific implementation, the mobile police service platform APP displays flow information and early warning feedback information in a bayonet flow early warning detail page, and a user can feed back early warning reasons and processing results according to the actual conditions of a bayonet and also support uploading of on-site bayonet pictures; the traffic police can set an early warning threshold value or adjust the early warning threshold value through the mobile police device; the traffic police can also set the starting time, the ending time, the flow and the same proportion relation of a prediction time period needing early warning through the mobile police device and select a main road to be monitored; the flow and the same relation are as follows: sending out early warning information under the condition that two early warning thresholds are met simultaneously, or sending out early warning information when one selected early warning threshold is met;
after the early warning information is sent to a mobile police device of the traffic police, the traffic police disposes according to the early warning information;
after the number of the vehicles passing through the checkpoint of the early warning information is manually verified by a traffic police, when the number of the vehicles passing through the checkpoint is not in accordance with the actual situation, historical data is corrected manually, and the original data is uploaded and covered, and the data is used as observation data for updating a subsequent differential autoregressive moving average model ARIMA.
And when the predicted value of the traffic flow exceeds a preset early warning threshold value, sending out early warning information.
The early warning information is sent to a mobile police device of the police officer, so that the police officer can obtain the relevant early warning information, and the police officer can reasonably and timely arrive at a place with abnormal traffic state; police officers manually correct the abnormal data through the mobile police officer device, a data correction way is provided for the abnormal card port, the configuration process of the police officers on the card port flow early warning parameters is greatly simplified, the follow-up model training can be carried out under the correct training data, and the accuracy of the follow-up early warning information is further ensured.
In the technical scheme, feedback information (such as corrected bayonet flow data, abnormal bayonet troubleshooting and artificially corrected early warning threshold) given by police officers provides an important basis for analysis and processing of subsequent bayonet data, and the bayonet with the early warning information type of flow congestion can be used for arranging personnel in advance to dredge on site, and the bayonet with the early warning information type of flow congestion can be used for reminding related personnel to treat and repair the bayonet problem; meanwhile, the fed back information can also provide a value setting basis for the flow early warning threshold value and the same-ratio early warning threshold value in the card port flow subscription, and therefore meaningless early warning is received when the value setting is too small or important early warning information is omitted when the value setting is too large.
S9: acquiring the next prediction day, and circularly executing the steps S3-S8; in a server of the public security traffic integrated command platform, different calculation processes are executed circularly on the main road to be monitored in real time according to the technical scheme of the patent; police officers pass through the removal police affairs and lead to APP, collude the bayonet socket that needs carry out traffic flow monitoring according to the jurisdiction of oneself every day, dispose early warning prediction time quantum, parameters such as early warning threshold value, then begin the traffic control work of every day, in the course of the work, pass through the removal police affairs and lead to APP and carry out artifical feedback to the traffic flow predicted value that gives, information such as early warning information, on the basis of having guaranteed that can in time accurate handling various traffic abnormalities in this day work, also guarantee that following flow early warning work can be more accurate.
Claims (8)
1. A bayonet traffic early warning method based on mobile police service is characterized by comprising the following steps:
s1: constructing a differential autoregressive moving average model ARIMA;
s2: confirming a main road to be monitored; acquiring a specific date of a predicted day;
s3: setting: the prediction day is a week tau, and the periodicity xi selected by the observation data is set;
collecting all historical traffic flow data which pass through all gates on the main road to be monitored in the whole day of each week tau in xi weeks before the prediction day; preprocessing the acquired historical traffic flow data, and recording the preprocessed sample data LiWherein xi is a positive integer;
s4: based on dynamic time warping algorithm DTW, the preprocessed sample data L is processediAnd the sample data L after the previous pretreatmentjJudging the similarity of the phase time;
when DTW (L)i,Lj) If > λ, executing step S5;
otherwise, go to step S6;
wherein, the sample data L after the previous preprocessingjThe training sample data of each week tau in the previous xi week corresponding to the previous same-frequency prediction day; the same-frequency prediction day as the prediction day is the prediction day of the week tau;
when the last same-frequency prediction day does not exist, the sample data L after the previous preprocessing isjThe value of (1) is null;
λ is the preset similarity comparison threshold when DTW (L)i,Lj) λ represents that the similarity of the two participating in comparison is low;
s5: based on the sample data L after the pretreatmentiTraining the autoregressive moving average model ARIMA to obtain the trained autoregressive moving average model ARIMA;
setting the trained autoregressive moving average model ARIMA as a week tau prediction model used at this time; step S7 is executed;
s6: setting the trained autoregressive moving average model ARIMA corresponding to the last same-frequency prediction day as the week tau prediction model used at this time;
s7: obtaining a prediction time period, wherein the length of the prediction time period is no more than 24 hours of the day of the prediction day;
s8: predicting to obtain a predicted value of the traffic flow of the road bayonet of the main road to be monitored in the prediction time period based on the used model for the week tau prediction corresponding to the prediction day;
when the predicted value of the traffic flow exceeds a preset early warning threshold value, sending early warning information;
s9: and acquiring the next prediction day and the main road to be monitored, and circularly executing the steps S3-S8.
2. The bayonet traffic early warning method based on mobile police service as claimed in claim 1, wherein: in step S8: the early warning threshold includes: a flow early warning threshold value and a comparability early warning threshold value;
the traffic early warning threshold value means that early warning is generated when the variation range of the traffic flow number in the last hour exceeds the set early warning threshold value;
the geometric early warning threshold value means that early warning can be generated when the geometric change amplitude of the vehicle passing flow number in the latest hour and the vehicle passing flow number in the same time period of yesterday exceeds a set early warning threshold value.
3. The bayonet traffic early warning method based on mobile police service as claimed in claim 1, wherein: in step S4, DTW (L)i,Lj) The algorithm of (1) is as follows:
D(Li,Lj) Representing the sequence a
With sequence b
European distance
The sum of the cumulative distances to the minimum proximate point that the point can reach.
4. The bayonet traffic early warning method based on mobile police service as claimed in claim 1, wherein: the number ξ of the cycles is set at 4.
5. The bayonet traffic early warning method based on mobile police service as claimed in claim 1, wherein: the setting mode of the early warning threshold value comprises the following steps: the traffic police sets through the mobile police service device;
the traffic police can also set the starting time, the ending time, the flow and the same proportion relation of the prediction time period through the mobile police device, and select the main road to be monitored; wherein, the flow and the same proportion relation are as follows: and sending out early warning information under the condition that two early warning thresholds are met simultaneously, or sending out early warning information when one selected early warning threshold is met.
6. The bayonet traffic early warning method based on mobile police service as claimed in claim 1, wherein: in step S8, after the warning information is sent to the mobile police device of the traffic police, the traffic police disposes according to the warning information;
and after the number of the vehicles passing through the checkpoint of the early warning information is manually verified, when the number of the vehicles passing through the checkpoint of the early warning information does not accord with the actual situation, the historical data is manually corrected through the mobile police service device, and the original data is uploaded and covered to serve as observation data for updating the differential autoregressive moving average model ARIMA subsequently.
7. The bayonet traffic early warning method based on mobile police service as claimed in claim 1, wherein: the parameters of the autoregressive moving average model ARIMA support manual configuration.
8. The bayonet traffic early warning method based on mobile police service as claimed in claim 1, wherein: in step S3, preprocessing the acquired historical traffic data, where the preprocessing includes:
a 1: keeping the traffic data of which the total number of unidirectional average daily traffic vehicles is greater than a preset available traffic value of the traffic data; deleting data related to the bayonets which do not meet the conditions;
a 2: removing invalid bayonet traffic data from the historical traffic data;
the data of the traffic flow of the invalid card port is as follows: under the condition that the traffic capacity of the road is normal, the historical traffic flow data is 0 or the number of abnormal data items of which the change range of the historical traffic flow data exceeds the data change invalid threshold exceeds the preset no-day threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011393599.1A CN112330074A (en) | 2020-12-02 | 2020-12-02 | Bayonet traffic early warning method based on mobile police service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011393599.1A CN112330074A (en) | 2020-12-02 | 2020-12-02 | Bayonet traffic early warning method based on mobile police service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112330074A true CN112330074A (en) | 2021-02-05 |
Family
ID=74301736
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011393599.1A Pending CN112330074A (en) | 2020-12-02 | 2020-12-02 | Bayonet traffic early warning method based on mobile police service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112330074A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159374A (en) * | 2021-03-05 | 2021-07-23 | 北京化工大学 | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method |
| CN115188186A (en) * | 2022-06-28 | 2022-10-14 | 公安部交通管理科学研究所 | Method for monitoring traffic flow in area |
| CN115331440A (en) * | 2022-08-09 | 2022-11-11 | 山东旗帜信息有限公司 | High-adaptation early warning method and system based on monitoring threshold information |
| CN116994441A (en) * | 2023-09-26 | 2023-11-03 | 北京清创美科环境科技有限公司 | Traffic flow information data processing method and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1617512A (en) * | 2004-11-25 | 2005-05-18 | 中国科学院计算技术研究所 | Adaptive network flow forecasting and abnormal alarming method |
| CN106530762A (en) * | 2016-12-26 | 2017-03-22 | 东软集团股份有限公司 | Traffic signal control method and device |
| CN107220734A (en) * | 2017-06-26 | 2017-09-29 | 江南大学 | CNC Lathe Turning process Energy Consumption Prediction System based on decision tree |
| CN107503797A (en) * | 2017-08-25 | 2017-12-22 | 合肥明信软件技术有限公司 | Mine Methane tendency early warning system based on 3D emulation platforms |
| CN110222383A (en) * | 2019-05-22 | 2019-09-10 | 微云（武汉）科技有限公司 | A kind of bridge security method for early warning, device and storage medium |
| CN110852476A (en) * | 2019-09-29 | 2020-02-28 | 华东理工大学 | Passenger flow prediction method and device, computer equipment and storage medium |
| CN110929648A (en) * | 2019-11-22 | 2020-03-27 | 广东睿盟计算机科技有限公司 | Monitoring data processing method and device, computer equipment and storage medium |
| CN111445694A (en) * | 2020-03-04 | 2020-07-24 | 青岛海信网络科技股份有限公司 | Festival and holiday traffic scheduling method and device based on traffic flow prediction |
| CN111882867A (en) * | 2020-07-03 | 2020-11-03 | 多伦科技股份有限公司 | City wisdom traffic early warning system based on thing networking |
-
2020
- 2020-12-02 CN CN202011393599.1A patent/CN112330074A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1617512A (en) * | 2004-11-25 | 2005-05-18 | 中国科学院计算技术研究所 | Adaptive network flow forecasting and abnormal alarming method |
| CN106530762A (en) * | 2016-12-26 | 2017-03-22 | 东软集团股份有限公司 | Traffic signal control method and device |
| CN107220734A (en) * | 2017-06-26 | 2017-09-29 | 江南大学 | CNC Lathe Turning process Energy Consumption Prediction System based on decision tree |
| CN107503797A (en) * | 2017-08-25 | 2017-12-22 | 合肥明信软件技术有限公司 | Mine Methane tendency early warning system based on 3D emulation platforms |
| CN110222383A (en) * | 2019-05-22 | 2019-09-10 | 微云（武汉）科技有限公司 | A kind of bridge security method for early warning, device and storage medium |
| CN110852476A (en) * | 2019-09-29 | 2020-02-28 | 华东理工大学 | Passenger flow prediction method and device, computer equipment and storage medium |
| CN110929648A (en) * | 2019-11-22 | 2020-03-27 | 广东睿盟计算机科技有限公司 | Monitoring data processing method and device, computer equipment and storage medium |
| CN111445694A (en) * | 2020-03-04 | 2020-07-24 | 青岛海信网络科技股份有限公司 | Festival and holiday traffic scheduling method and device based on traffic flow prediction |
| CN111882867A (en) * | 2020-07-03 | 2020-11-03 | 多伦科技股份有限公司 | City wisdom traffic early warning system based on thing networking |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159374A (en) * | 2021-03-05 | 2021-07-23 | 北京化工大学 | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method |
| CN113159374B (en) * | 2021-03-05 | 2022-04-22 | 北京化工大学 | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method |
| CN115188186A (en) * | 2022-06-28 | 2022-10-14 | 公安部交通管理科学研究所 | Method for monitoring traffic flow in area |
| CN115188186B (en) * | 2022-06-28 | 2024-02-20 | 公安部交通管理科学研究所 | Method for monitoring traffic flow in area |
| CN115331440A (en) * | 2022-08-09 | 2022-11-11 | 山东旗帜信息有限公司 | High-adaptation early warning method and system based on monitoring threshold information |
| CN115331440B (en) * | 2022-08-09 | 2023-08-18 | 山东旗帜信息有限公司 | High-adaptation early warning method and system based on monitoring threshold information |
| CN116994441A (en) * | 2023-09-26 | 2023-11-03 | 北京清创美科环境科技有限公司 | Traffic flow information data processing method and system |
| CN116994441B (en) * | 2023-09-26 | 2023-12-12 | 北京清创美科环境科技有限公司 | Traffic flow information data processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112330074A (en) | Bayonet traffic early warning method based on mobile police service | |
| CN110491146B (en) | Deep learning-based traffic signal control scheme real-time recommendation method | |
| CN109376906B (en) | Travel time prediction method and system based on multi-dimensional trajectory and electronic equipment | |
| CN114971356A (en) | Electric power engineering project progress prediction system and method | |
| CN118037014B (en) | Road construction monitoring system based on Internet of things | |
| CN116822769A (en) | Intelligent traffic route optimizing system based on artificial intelligence | |
| CN109191842A (en) | Congestion regulating strategy recommended method and system based on the real-time traffic capacity | |
| GB2614004A (en) | Predictive maintenance of vehicle components | |
| CN109378031B (en) | Rice sheath blight prediction method based on combination of plant protection and meteorological information | |
| CN116581750A (en) | Intelligent line load charging method based on power grid load level | |
| CN114463972A (en) | Road section interval traffic analysis and prediction method based on ETC portal communication data | |
| CN117935561B (en) | Intelligent traffic flow analysis method based on Beidou data | |
| CN118134172B (en) | Urban public resource management and allocation system | |
| CN110110339B (en) | Japanese hydrologic forecast error correction method and system | |
| CN103002165B (en) | Method for predicting short-term telephone traffic of power supply service center | |
| CN116882672A (en) | Internet-based building engineering personnel management system | |
| CN117912235B (en) | Planning data processing method and system for smart city | |
| CN118504991A (en) | Power failure processing method, device, equipment and medium for power guarantee area | |
| CN117634727A (en) | Intelligent park monitoring method and system based on digital twinning | |
| CN117423238A (en) | Integrated traffic flow prediction device and prediction method based on convolution switching network | |
| CN112418662A (en) | Power distribution network operation reliability analysis method using artificial neural network | |
| CN117437774A (en) | AI-based multi-mode traffic flow prediction system | |
| CN116882582A (en) | Tobacco plant equipment production plan making method based on yield prediction | |
| Tu et al. | Analysis and forecast of passenger flow based on public transportation IC card and GPS data | |
| CN106779241B (en) | Short-term passenger flow prediction method for rail transit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210205 |
|
| RJ01 | Rejection of invention patent application after publication |