CN117456732A - Signal lamp monitoring management method and device for intelligent urban traffic based on big data and computing equipment - Google Patents
Signal lamp monitoring management method and device for intelligent urban traffic based on big data and computing equipment Download PDFInfo
- Publication number
- CN117456732A CN117456732A CN202311469752.8A CN202311469752A CN117456732A CN 117456732 A CN117456732 A CN 117456732A CN 202311469752 A CN202311469752 A CN 202311469752A CN 117456732 A CN117456732 A CN 117456732A
- Authority
- CN
- China
- Prior art keywords
- traffic
- intersection
- congestion
- information
- traffic information
- 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.)
- Withdrawn
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 41
- 238000007726 management method Methods 0.000 title claims description 20
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 33
- 238000011144 upstream manufacturing Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims description 21
- 239000013598 vector Substances 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 17
- 230000004913 activation Effects 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000002790 cross-validation Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 230000009849 deactivation Effects 0.000 claims description 5
- 238000013499 data model Methods 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000009467 reduction Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000001965 increasing effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000020411 cell activation Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000002779 inactivation Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 239000002243 precursor Substances 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/081—Plural intersections under common control
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Automation & Control Theory (AREA)
- Computational Mathematics (AREA)
- Fuzzy Systems (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a signal lamp monitoring and managing method, a device and computing equipment of intelligent city traffic based on big data, wherein the method comprises the following steps: acquiring traffic information of each traffic intersection from an urban traffic signal lamp control system; respectively constructing road networks sequentially connected in all directions of the traffic intersections according to the upstream and downstream intersections in all directions of the road networks, and dividing the time period of traffic information of each traffic intersection; training a traffic flow prediction model; and inputting the traffic information at the current moment into a traffic flow prediction model to predict the congestion state of the target intersection at the next moment in each direction, so as to control the traffic light signals of the target intersection according to the congestion state. The method and the system automatically identify the implicit traffic rules and modes through the big data model based on a large amount of historical traffic flow information, can predict the congestion state of each direction of each traffic intersection at the next moment in real time and globally so as to control the intersection signals, are widely suitable for various traffic scenes, and are easy to deploy and apply.
Description
Technical Field
The invention relates to the technical field of intersection signal lamp control and artificial intelligence, in particular to a signal lamp monitoring management method, device and computing equipment for intelligent city traffic based on big data.
Background
With the increasing number of urban vehicles, traffic congestion on urban road networks has become a serious socioeconomic problem. In the case where it is difficult to further construct and widen the road, effective use of the existing road by enhancing traffic management and control is a major choice for urban traffic. Although the traffic flow pressure can be relieved to a certain extent through management measures such as green travel and traffic restriction number restriction, the problems of traffic jam and the like still seriously affect the travel life of people, especially when vehicles pass through an intersection, smooth traffic flow is interrupted due to unreasonable traffic signal period.
Existing traffic signal control schemes can generally be divided into two categories: the method is characterized in that the method comprises the step of controlling a fixed timing signal lamp, and a controller determines a fixed timing scheme of the traffic signal lamp offline, wherein the scheme mainly comprises parameters such as cycle time, dividing time, offset and the like. Wherein the cycle time defines the duration of one complete signal cycle, the split time defines the time the lamp stays in each state (e.g., green light), and the offset defines the directional difference relative to other intersection traffic lights. The scheme cannot respond to various traffic conditions in real time, especially in the case of sudden increase of traffic flow; another class is adaptive signal lamp control schemes that provide traffic lamp control decisions based on algorithms such as dynamic programming, fuzzy logic, and reinforcement learning. Adaptive signal lamp control schemes utilize real-time data to determine optimal signal timing to maximize a defined objective function and have become popular in the last few decades due to their adaptability and flexibility. However, this solution has the disadvantage that it cannot be globally optimized, since the control decisions only take into account the traffic demand in the current green direction, whereas the traffic light control in the other directions is ignored.
Therefore, there is a need to develop a signal lamp monitoring management system for smart city traffic based on big data, which can be applied to various scenes in real time and is easy to apply.
Disclosure of Invention
In view of the above problems, the present invention is to provide a method and apparatus for monitoring and managing signal lights of intelligent urban traffic based on big data, and a computing device, which overcome the problems of insufficient application scenarios and difficulty in implementing the application of the signal light monitoring and management.
According to one aspect of the present invention, there is provided a signal lamp monitoring and managing method for smart city traffic based on big data, comprising: acquiring traffic information of each traffic intersection from an urban traffic signal lamp control system, wherein the traffic information comprises historical traffic data, positions, directions, signal periods of traffic lights and congestion states of each direction, and the congestion states comprise smooth, basically smooth, slight congestion, medium congestion and serious congestion;
aiming at any traffic intersection, respectively constructing a road network sequentially connected in each direction of the traffic intersection according to upstream and downstream intersections in each direction of the traffic intersection, and dividing the traffic information of each traffic intersection into time periods, wherein the time periods comprise holidays, saturday and rush hours;
Training a traffic flow prediction model according to the traffic information of each traffic intersection, the connection road network of each direction and the time information;
and acquiring traffic information of the current moment of the target intersection, and inputting the traffic information into the traffic flow prediction model to predict the congestion state of the target intersection at the next moment in each direction so as to control traffic light signals of the target intersection according to the congestion state, wherein the traffic information of the current moment of the target intersection comprises the number of license plates of vehicles shot by monitoring in each direction and shooting time.
In an optional manner, before the traffic flow prediction model is trained according to the traffic information of each traffic intersection, the connection road network of each direction and the time period information, the method further includes:
establishing a data set according to the historical flow data of the traffic information, and setting the historical flow data of each preset period as input by using a sliding window, wherein the congestion state at the next moment is taken as output;
dividing the input and the corresponding output into a training set, a testing set and a cross-validation set according to a preset proportion.
In an alternative way, the loss function of the traffic flow prediction model is:
Wherein K is the kth traffic intersection, K is the number of the traffic intersections, y t For the serial number of the current traffic intersection, P Jam Is the congestion probability of the current traffic intersection, y t-1 C is the serial number of the previous traffic intersection t-1 The traffic vector of the previous traffic intersection is represented by x, which is the vector feature of the traffic intersection.
In an alternative manner, each convolution network module in the traffic flow prediction model comprises one-dimensional convolution, gating unit activation and random deactivation operations;
the specific formula for calculating the one-dimensional convolution is:
wherein s (t) is a convolution operation result, u, v is a function with an independent variable of t, and a is an accumulated variable;
the specific formula of the gating unit activation is as follows:
where K is the input of the current network layer, F, G is the convolution kernel, σ is the activation function, and b, c are the bias parameters.
In an optional manner, before the obtaining the traffic information of the current moment of the target intersection and inputting the traffic information into the traffic flow prediction model to predict the congestion state of the next moment in each direction of the target intersection, the method further includes:
normalizing the vector of the traffic information, wherein the normalization function is specifically:
wherein, min gamma k (i)、maxγ Good grade (good) (i) Respectively the vector columns gamma k Minimum and maximum values of f (gamma) k (i) A normalized value of each element.
In an alternative, the method further comprises:
and after the traffic light signals of the target intersection are controlled, predicting the congestion state of the current direction, other directions and adjacent intersections of the target intersection again.
In an alternative, the method further comprises:
calculating traffic congestion degree according to the traffic information of the target intersection;
and carrying out weighted summation on the traffic congestion degree and the congestion state predicted by the traffic flow prediction model to obtain a second congestion state of the target intersection, and controlling a traffic light signal of the target intersection according to the second congestion state.
In an alternative manner, the specific formula of the traffic congestion degree is:
wherein,c is the number of vehicles in the direction, L is the length of the road in the direction, < > in the direction>mc is the number of license plates of the monitored shooting (i.e. the number of vehicles moving on the directional road).
According to another aspect of the present invention, there is provided a traffic light monitoring and management device for smart city traffic based on big data, comprising:
the system comprises an acquisition module, a traffic signal lamp control system and a traffic signal lamp control system, wherein the acquisition module is used for acquiring traffic information of each traffic intersection from the urban traffic signal lamp control system, the traffic information comprises historical flow data, positions, directions, signal periods of traffic lights and congestion states of each direction, and the congestion states comprise smooth, basically smooth, slight congestion, medium congestion and serious congestion;
The processing module is used for respectively constructing road networks sequentially connected in all directions of the traffic intersections according to upstream and downstream intersections in all directions of any traffic intersection, and dividing the traffic information of each traffic intersection, wherein the time periods comprise holidays, saturday and rush hours.
The training module is used for training a traffic flow prediction model according to the traffic information of each traffic intersection, the connection road network in each direction and the time information;
the prediction module is used for acquiring traffic information of the current moment of the target intersection, inputting the traffic information into the traffic flow prediction model, predicting the congestion state of the target intersection at the next moment in each direction, and controlling traffic light signals of the target intersection according to the congestion state, wherein the traffic information of the current moment of the target intersection comprises the number of license plates of vehicles shot by monitoring in each direction and shooting time.
According to yet another aspect of the present invention, there is provided a computing device comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
The memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the signal lamp monitoring management method of the intelligent urban traffic based on big data.
According to the scheme provided by the invention, the traffic information of each traffic intersection is obtained from an urban traffic signal lamp control system, wherein the traffic information comprises historical traffic data, positions, directions, signal periods of traffic lights and congestion states of each direction, and the congestion states comprise unblocked, basically unblocked, slightly congested, moderately congested and severely congested; aiming at any traffic intersection, respectively constructing a road network sequentially connected in each direction of the traffic intersection according to upstream and downstream intersections in each direction of the traffic intersection, and dividing the traffic information of each traffic intersection into time periods, wherein the time periods comprise holidays, saturday and rush hours; training a traffic flow prediction model according to the traffic information of each traffic intersection, the connection road network of each direction and the time information; and acquiring traffic information of the current moment of the target intersection, and inputting the traffic information into the traffic flow prediction model to predict the congestion state of the target intersection at the next moment in each direction so as to control traffic light signals of the target intersection according to the congestion state, wherein the traffic information of the current moment of the target intersection comprises the number of license plates of vehicles shot by monitoring in each direction and shooting time. The method and the system automatically identify the implicit traffic rules and modes through the big data model based on a large amount of historical traffic flow information, can predict the congestion state of each direction of each traffic intersection at the next moment in real time and globally so as to control the intersection signals, are widely suitable for various traffic scenes, and are easy to deploy and apply.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 shows a flow diagram of a signal lamp monitoring and managing method for smart city traffic based on big data according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a signal lamp monitoring and managing device for smart city traffic based on big data according to an embodiment of the present invention;
FIG. 3 illustrates a schematic diagram of a computing device in accordance with an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 shows a flow diagram of a signal lamp monitoring and managing method for smart city traffic based on big data according to an embodiment of the present invention. The method. Specifically, as shown in fig. 1, the method comprises the following steps:
step S101, acquiring traffic information of each traffic intersection from an urban traffic signal lamp control system, wherein the traffic information comprises historical flow data, positions, directions, signal periods of traffic lights and congestion states of each direction, and the congestion states comprise smooth, basically smooth, slightly congested, moderately congested and severely congested.
The traffic light control system is a networking system, provides functions including monitoring, management, safety detection, data interfaces and the like, and can acquire traffic information of each traffic intersection from the urban traffic signal light control system through the data interfaces, for example, acquire a signal control scheme and flow index data and the like in the system, wherein the signal control scheme comprises a period length, a direction scheme, each direction release time and signal light structured static data (such as GPS positioning and the like). The traffic index data comprises historical traffic data, positions, directions of various intersections in the past several periods of various traffic intersections, signal periods of traffic lights and congestion states of various directions, wherein the congestion states comprise smooth, basically smooth, slightly congested, moderately congested and severely congested. The traffic situation can be replaced by other indexes capable of representing traffic situations according to application requirements, such as the number of vehicles passing through, the passing time, the queuing length of the vehicles and the like according to the number of license plates photographed by monitoring, and the passing speed and the congestion situation of the vehicles can be further obtained according to the passing number and the passing time of the vehicles. According to the traffic information, compared with a method based on image segmentation, the method is easy to obtain data, high in accuracy, easy to apply and implement, and capable of only reading the data of the urban traffic signal lamp control system without additional hardware equipment.
Step S102, constructing a road network for sequentially connecting all directions of the traffic intersection according to upstream and downstream intersections of all directions of any traffic intersection, and dividing the traffic information of all the traffic intersections into time periods, wherein the time periods comprise holidays, saturday and rush hours.
Specifically, for any direction of any traffic intersection, the roads in the same direction of the upstream and downstream intersections in the direction are connected to obtain a road network connection state table in the direction, and the road network connection state table can be realized through a double linked list structure, wherein each data node of the double linked list is provided with two pointers which point to a direct successor and a direct predecessor respectively. Starting from any node in the doubly linked list, the precursor node and the successor node can be conveniently accessed. Optionally, the road network connection state table is stored by using a circular linked list, and the last node of the circular linked list points to the head node to form a ring. Any other node can be found starting from any node in the circular linked list. And dividing the traffic information of each traffic intersection in time periods, wherein the time period division is set by referring to the traffic flow conditions of other intersections nearby in different time periods, and generally at least comprises: holidays, saturday days, rush hours, morning and evening peaks, peaked peaks, night valleys, etc.
And step S103, training a traffic flow prediction model according to the traffic information of each traffic intersection, the connection road network of each direction and the time slot information.
According to traffic information of each traffic intersection, the connection road network in each direction and the time information, a traffic flow prediction model is trained, the congestion state of each traffic intersection is output, traffic signals of a plurality of traffic intersections can be controlled simultaneously according to the congestion state, and the traffic flow prediction model takes the minimized intersection waiting time as an optimization target. In this embodiment, the traffic flow prediction model is composed of a plurality of neural network layers, and the network inputs are traffic information and time period information of each traffic intersection and road network link vectors representing connection relations between each traffic intersection in each direction, wherein each network layer performs information propagation and information aggregation on the input feature vectors.
In an optional manner, before the traffic flow prediction model is trained according to the traffic information of each traffic intersection, the connection road network of each direction and the time period information, the method further includes:
establishing a data set according to the historical flow data of the traffic information, and setting the historical flow data of each preset period as input by using a sliding window, wherein the congestion state at the next moment is taken as output;
Dividing the input and the corresponding output into a training set, a testing set and a cross-validation set according to a preset proportion.
The method comprises the steps of establishing a data set by using historical data of traffic information, taking the collected historical data as one input by using a sliding window at each T moment, taking congestion data at the next moment as output, manufacturing the historical data into the data set according to the input and the corresponding output, and dividing the data set into a training set and a testing set according to a proportion. Training a model by using a training set, wherein the training process has certain randomness, so that multiple times of training are needed, and a local test of data transmission quantity reduction is performed by using a test set, namely, data in a time period related to the test set is generated by using a sliding window to generate model input data, the data of the next moment is predicted, if the difference value between a predicted value and a true value is smaller than or equal to a threshold value, the predicted value is used for replacing the data of the next moment, the data reduction number is increased by 1, otherwise, the true data number is increased by 1, the data reduction number is increased by the true data number, namely the total data number, and the data reduction number is divided by the total data number, namely the data transmission quantity reduction proportion. The cross-validation method is used for attempting to perform multiple groups of different training/testing on the model by utilizing different training sets/test set divisions so as to solve the problems of excessively unilateral test results and insufficient training data, the cross-validation method is used for roughly dividing the data set into K parts which are equal and disjoint, then taking one part for testing, training the other K-1 parts, then obtaining the average value of error as final evaluation, for example, dividing an initial sample into K sub-samples, reserving one single sub-sample as data of a verification model, and using the other K-1 samples for training. The cross-validation is repeated K times, each sub-sample is validated once, the K results are averaged or other combinations are used to finally obtain a single estimate. The advantage of cross-validation is that training and validation are repeated using randomly generated subsamples simultaneously, with each validation result being validated once (10-fold cross-validation is most common).
In an alternative way, the loss function of the traffic flow prediction model is:
wherein K is the kth traffic intersection, K is the number of the traffic intersections, y t For the serial number of the current traffic intersection，P Jam Is the congestion probability of the current traffic intersection, y t-1 C is the serial number of the previous traffic intersection t-1 The traffic vector of the previous traffic intersection is represented by x, which is the vector feature of the traffic intersection.
The loss function L is used for measuring the difference degree of the predicted congestion probability and the real congestion probability of the model, and the smaller the loss function is, the better the robustness of the model is. In the training stage of the traffic flow prediction model, after training data of each batch is sent into the model, a congestion probability prediction value is output through forward propagation, and then a loss function calculates a difference value between the predicted congestion probability and the real congestion probability, namely a loss value. After the loss value is obtained, the model updates each parameter through back propagation to reduce the loss between the real congestion probability and the predicted congestion probability, so that the predicted congestion probability generated by the model is close to the real congestion probability.
In an alternative manner, each convolution network module in the traffic flow prediction model comprises one-dimensional convolution, gating unit activation and random deactivation operations;
The specific formula for calculating the one-dimensional convolution is:
wherein s (t) is a convolution operation result, u, v is a function with an independent variable of t, and a is an accumulated variable;
the specific formula of the gating unit activation is as follows:
where K is the input of the current network layer, F, G is the convolution kernel, σ is the activation function, and b, c are the bias parameters.
For example, the convolutional neural network model includes 10 convolutional blocks, each containing 3 operations, one-dimensional convolutional, gating cell activation, and random deactivation operations, respectively. The random inactivation operation can effectively relieve the over-fitting problem of the model, plays a role of regularization, and can complement methods such as L1 regularization, L2 regularization, maximum norm constraint and the like.
Step S104, obtaining traffic information of the current moment of the target intersection, and inputting the traffic information into the traffic flow prediction model to predict the congestion state of the target intersection at the next moment in each direction so as to control traffic light signals of the target intersection according to the congestion state, wherein the traffic information of the current moment of the target intersection comprises the number of license plates of vehicles shot by monitoring in each direction and shooting time.
Specifically, the traffic information of the current moment of the target intersection is obtained from the urban traffic signal lamp control system, for example, the traffic quantity, the traffic time and the vehicle queuing length of the traffic of the current moment of each direction of the target intersection are obtained according to the license plate quantity of monitoring photographing, and the time period information of holidays, saturday, rush hour, peak, valley and the like, and the connecting road network information of each direction are obtained. The traffic information at the current moment of the target intersection comprises the number of license plates of the vehicle shot by monitoring in each direction and shooting time.
In an optional manner, before the obtaining the traffic information of the current moment of the target intersection and inputting the traffic information into the traffic flow prediction model to predict the congestion state of the next moment in each direction of the target intersection, the method further includes:
normalizing the vector of the traffic information, wherein the normalization function is specifically:
wherein, min gamma k (i)、maxγ k (i) Respectively the vector columns gamma k Minimum and maximum values of f (gamma) k (i) A normalized value of each element.
Since different evaluation indexes often have different dimensions and dimension units, in order to eliminate the dimension influence among indexes, data standardization processing is required to solve the comparability among data indexes. After the original data is subjected to data normalization processing, all indexes are in the same order of magnitude, so that the preprocessed data is limited in a certain range (such as [0,1] or [ -1,1 ]), and adverse effects caused by singular sample data are eliminated.
In an alternative, the method further comprises:
and after the traffic light signals of the target intersection are controlled, predicting the congestion state of the current direction, other directions and adjacent intersections of the target intersection again.
The congestion state of the target intersection (the preset direction or the main lane), other directions and adjacent intersections is predicted again, so that the congestion state of each traffic intersection is dynamically and globally adjusted.
In an alternative, the method further comprises:
calculating traffic congestion degree according to the traffic information of the target intersection;
and carrying out weighted summation on the traffic congestion degree and the congestion state predicted by the traffic flow prediction model to obtain a second congestion state of the target intersection, and controlling a traffic light signal of the target intersection according to the second congestion state.
Because the neural network is a black box model and lacks of interpretability, the traffic congestion degree is calculated according to the traffic information of the target intersection through the traffic congestion calculation formula, the method is simple in calculation and good in interpretability, the traffic congestion calculation formula is integrated with the neural network, the traffic congestion degree and the congestion state predicted by the traffic flow prediction model are weighted and summed to obtain a second congestion state of the target intersection, the traffic light signal of the target intersection is controlled according to the second congestion state, and accuracy and stability of the traffic congestion degree calculation can be further improved.
In an alternative manner, the specific formula of the traffic congestion degree is:
wherein,c is the number of vehicles in the direction, L is the length of the road in the direction, < > in the direction>mc is the number of license plates of the monitored shooting (i.e. the number of vehicles moving on the directional road).
According to the scheme provided by the invention, the traffic information of each traffic intersection is obtained from an urban traffic signal lamp control system, wherein the traffic information comprises historical traffic data, positions, directions, signal periods of traffic lights and congestion states of each direction, and the congestion states comprise unblocked, basically unblocked, slightly congested, moderately congested and severely congested; aiming at any traffic intersection, respectively constructing a road network sequentially connected in each direction of the traffic intersection according to upstream and downstream intersections in each direction of the traffic intersection, and dividing the traffic information of each traffic intersection into time periods, wherein the time periods comprise holidays, saturday and rush hours; training a traffic flow prediction model according to the traffic information of each traffic intersection, the connection road network of each direction and the time information; and acquiring traffic information of the current moment of the target intersection, and inputting the traffic information into the traffic flow prediction model to predict the congestion state of the target intersection at the next moment in each direction so as to control traffic light signals of the target intersection according to the congestion state, wherein the traffic information of the current moment of the target intersection comprises the number of license plates of vehicles shot by monitoring in each direction and shooting time. The method and the system automatically identify the implicit traffic rules and modes through the big data model based on a large amount of historical traffic flow information, can predict the congestion state of each direction of each traffic intersection at the next moment in real time and globally so as to control the intersection signals, are widely suitable for various traffic scenes, and are easy to deploy and apply.
It should be noted that, according to the scheme provided by the invention, a great amount of historical traffic flow information is obtained from the existing urban traffic signal lamp control system, and the hidden traffic rules and modes are automatically identified through the big data model to predict the congestion state of each direction at the next moment of each traffic intersection so as to control the intersection signal. Only the data and license plate monitoring facilities in the urban traffic signal lamp control system are needed, and other additional monitoring equipment is not needed to be deployed, so that the system is widely applicable to various traffic scenes and is easy to deploy and apply. Because the connection road network information of each direction is considered, not only the traffic demand of the current green direction of the traffic intersection is considered, but also the signal lamp control demands of other traffic intersections in each direction are considered, and the traffic signal lamps are monitored and managed from the global traffic angle, the congestion state of each direction of each traffic intersection at the next moment can be predicted in real time and globally to control the intersection signals.
Fig. 2 is a schematic structural diagram of a signal lamp monitoring and managing device for smart city traffic based on big data according to an embodiment of the present invention. The signal lamp monitoring management device of the intelligent city traffic based on big data comprises: the system comprises an acquisition module 210, a processing module 220, a training module 230 and a prediction module 240.
The collecting module 210 is configured to obtain traffic information of each traffic intersection from the urban traffic signal lamp control system, where the traffic information includes historical traffic data, a position, a direction, a signal period of a traffic light, and congestion states of each direction, and the congestion states include unblocked, basically unblocked, slightly congested, moderately congested, and severely congested;
the processing module 220 is configured to, for any one of the traffic intersections, respectively construct a road network sequentially connected to each direction of the traffic intersection according to upstream and downstream intersections in each direction, and divide traffic information of each traffic intersection by time periods, where the time periods include holidays, saturday days, and rush hours;
the training module 230 is configured to train a traffic flow prediction model according to traffic information of each traffic intersection, the connection road network of each direction, and the time information;
the prediction module 240 is configured to obtain traffic information at a current time of a target intersection, and input the traffic information to the traffic flow prediction model to predict a congestion state at a next time in each direction of the target intersection, so as to control a traffic light signal of the target intersection according to the congestion state, where the traffic information at the current time of the target intersection includes a number of license plates of vehicles captured by monitoring in each direction and capturing time.
In an optional manner, before the training module 230 trains the traffic flow prediction model according to the traffic information of each traffic intersection, the connection network of each direction and the time period information, the training module further includes a preprocessing module, which is further configured to: establishing a data set according to the historical flow data of the traffic information, and setting the historical flow data of each preset period as input by using a sliding window, wherein the congestion state at the next moment is taken as output;
dividing the input and the corresponding output into a training set, a testing set and a cross-validation set according to a preset proportion.
In an alternative way, the loss function of the traffic flow prediction model is:
wherein K is the kth traffic intersection, K is the number of the traffic intersections, y t For the serial number of the current traffic intersection, P Jam Is the congestion probability of the current traffic intersection, y t-1 C is the serial number of the previous traffic intersection t-1 The traffic vector of the previous traffic intersection is represented by x, which is the vector feature of the traffic intersection.
In an alternative manner, each convolution network module in the traffic flow prediction model comprises one-dimensional convolution, gating unit activation and random deactivation operations;
the specific formula for calculating the one-dimensional convolution is:
Wherein s (t) is a convolution operation result, u, v is a function with an independent variable of t, and a is an accumulated variable;
the specific formula of the gating unit activation is as follows:
where K is the input of the current network layer, F, G is the convolution kernel, σ is the activation function, and b, c are the bias parameters.
In an optional manner, before the traffic information of the current moment of the target intersection is obtained and input to the traffic flow prediction model to predict the congestion state of the next moment in each direction of the target intersection, the method further includes a normalization module, which is further configured to:
normalizing the vector of the traffic information, wherein the normalization function is specifically:
wherein, min gamma k (i)、maxγ k (i) Respectively the vector columns gamma k Minimum and maximum values of f (gamma) k (i) A normalized value of each element.
In an alternative manner, after the traffic light signal of the target intersection is controlled, the congestion state of the direction, other directions and adjacent intersections of the target intersection is predicted again.
In an alternative manner, the congestion calculation module is further configured to: calculating traffic congestion degree according to the traffic information of the target intersection;
and carrying out weighted summation on the traffic congestion degree and the congestion state predicted by the traffic flow prediction model to obtain a second congestion state of the target intersection, and controlling a traffic light signal of the target intersection according to the second congestion state.
In an alternative manner, the specific formula of the traffic congestion degree is:
wherein,c is the number of vehicles in the direction, L is the length of the road in the direction, < > in the direction>mc is the number of license plates of the monitored shooting (i.e. the number of vehicles moving on the directional road).
FIG. 3 illustrates a schematic diagram of an embodiment of a computing device of the present invention, and the embodiments of the present invention are not limited to a particular implementation of the computing device.
As shown in fig. 3, the computing device may include: a processor (processor) 302, a communication interface (Communications Interface) 304, a memory (memory) 306, and a communication bus 308.
Wherein: processor 302, communication interface 304, and memory 306 perform communication with each other via communication bus 308. A communication interface 304 for communicating with network elements of other devices, such as clients or other servers. The processor 302 is configured to execute the program 310, and may specifically perform the relevant steps in the embodiment of the signal monitoring management method for smart city traffic based on big data.
In particular, program 310 may include program code including computer-operating instructions.
The processor 302 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 306 for storing programs 310. Memory 306 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
According to the scheme provided by the invention, the traffic information of each traffic intersection is obtained from an urban traffic signal lamp control system, wherein the traffic information comprises historical traffic data, positions, directions, signal periods of traffic lights and congestion states of each direction, and the congestion states comprise unblocked, basically unblocked, slightly congested, moderately congested and severely congested; aiming at any traffic intersection, respectively constructing a road network sequentially connected in each direction of the traffic intersection according to upstream and downstream intersections in each direction of the traffic intersection, and dividing the traffic information of each traffic intersection into time periods, wherein the time periods comprise holidays, saturday and rush hours; training a traffic flow prediction model according to the traffic information of each traffic intersection, the connection road network of each direction and the time information; and acquiring traffic information of the current moment of the target intersection, and inputting the traffic information into the traffic flow prediction model to predict the congestion state of the target intersection at the next moment in each direction so as to control traffic light signals of the target intersection according to the congestion state, wherein the traffic information of the current moment of the target intersection comprises the number of license plates of vehicles shot by monitoring in each direction and shooting time. The method and the system automatically identify the implicit traffic rules and modes through the big data model based on a large amount of historical traffic flow information, can predict the congestion state of each direction of each traffic intersection at the next moment in real time and globally so as to control the intersection signals, are widely suitable for various traffic scenes, and are easy to deploy and apply.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components according to embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.
Claims (10)
1. A signal lamp monitoring and managing method of intelligent city traffic based on big data is characterized by comprising the following steps:
acquiring traffic information of each traffic intersection from an urban traffic signal lamp control system, wherein the traffic information comprises historical traffic data, positions, directions, signal periods of traffic lights and congestion states of each direction, and the congestion states comprise smooth, basically smooth, slight congestion, medium congestion and serious congestion;
Aiming at any traffic intersection, respectively constructing a road network sequentially connected in each direction of the traffic intersection according to upstream and downstream intersections in each direction of the traffic intersection, and dividing the traffic information of each traffic intersection into time periods, wherein the time periods comprise holidays, saturday and rush hours;
training a traffic flow prediction model according to the traffic information of each traffic intersection, the connection road network of each direction and the time information;
and acquiring traffic information of the current moment of the target intersection, and inputting the traffic information into the traffic flow prediction model to predict the congestion state of the target intersection at the next moment in each direction so as to control traffic light signals of the target intersection according to the congestion state, wherein the traffic information of the current moment of the target intersection comprises the number of license plates of vehicles shot by monitoring in each direction and shooting time.
2. The traffic light monitoring and management method for intelligent urban traffic based on big data according to claim 1, wherein before the training of the traffic flow prediction model according to the traffic information of each traffic intersection, the connection road network of each direction and the time slot information, the method further comprises:
Establishing a data set according to the historical flow data of the traffic information, and setting the historical flow data of each preset period as input by using a sliding window, wherein the congestion state at the next moment is taken as output;
dividing the input and the corresponding output into a training set, a testing set and a cross-validation set according to a preset proportion.
3. The traffic light monitoring and management method of intelligent urban traffic based on big data according to claim 2, wherein the loss function of the traffic flow prediction model is:
wherein K is the kth traffic intersection, K is the number of the traffic intersections, y t For the serial number of the current traffic intersection, P Jam Is the congestion probability of the current traffic intersection, y t-1 C is the serial number of the previous traffic intersection t-1 The traffic vector of the previous traffic intersection is represented by x, which is the vector feature of the traffic intersection.
4. The traffic light monitoring and management method of intelligent urban traffic based on big data according to claim 1, wherein each convolution network module in the traffic flow prediction model comprises one-dimensional convolution, gating unit activation and random deactivation operations;
the specific formula for calculating the one-dimensional convolution is:
wherein s (t) is a convolution operation result, u, v is a function with an independent variable of t, and a is an accumulated variable;
The specific formula of the gating unit activation is as follows:
where K is the input of the current network layer, F, G is the convolution kernel, σ is the activation function, and b, c are the bias parameters.
5. The traffic light monitoring and management method according to claim 4, wherein before the traffic information of the current time of the obtained target intersection is input to the traffic flow prediction model to predict the congestion state of the next time in each direction of the target intersection, the method further comprises:
normalizing the vector of the traffic information, wherein the normalization function is specifically:
wherein, min gamma k (i)、maxγ k (i) Respectively the vector columns gamma k Minimum and maximum values of f (gamma) k (i) A normalized value of each element.
6. The traffic light monitoring and management method for big data based intelligent urban traffic according to claim 5, further comprising:
and after the traffic light signals of the target intersection are controlled, predicting the congestion state of the current direction, other directions and adjacent intersections of the target intersection again.
7. The traffic light monitoring and management method for big data based smart city traffic of claim 1, further comprising:
Calculating traffic congestion degree according to the traffic information of the target intersection;
and carrying out weighted summation on the traffic congestion degree and the congestion state predicted by the traffic flow prediction model to obtain a second congestion state of the target intersection, and controlling a traffic light signal of the target intersection according to the second congestion state.
8. The traffic light monitoring and management method for intelligent urban traffic based on big data according to claim 7, wherein the specific formula of the traffic congestion degree is:
wherein,c is the number of vehicles in the direction, L is the length of the road in the direction, < > in the direction>mc is the number of license plates of the monitored shooting (i.e. the number of vehicles moving on the directional road).
9. A signal lamp monitoring management device of wisdom urban traffic based on big data, characterized by comprising:
the system comprises an acquisition module, a traffic signal lamp control system and a traffic signal lamp control system, wherein the acquisition module is used for acquiring traffic information of each traffic intersection from the urban traffic signal lamp control system, the traffic information comprises historical flow data, positions, directions, signal periods of traffic lights and congestion states of each direction, and the congestion states comprise smooth, basically smooth, slight congestion, medium congestion and serious congestion;
the processing module is used for respectively constructing road networks sequentially connected in all directions of the traffic intersections according to upstream and downstream intersections in all directions of any traffic intersection, and dividing the traffic information of each traffic intersection, wherein the time periods comprise holidays, saturday and rush hours.
The training module is used for training a traffic flow prediction model according to the traffic information of each traffic intersection, the connection road network in each direction and the time information;
the prediction module is used for acquiring traffic information of the current moment of the target intersection, inputting the traffic information into the traffic flow prediction model, predicting the congestion state of the target intersection at the next moment in each direction, and controlling traffic light signals of the target intersection according to the congestion state, wherein the traffic information of the current moment of the target intersection comprises the number of license plates of vehicles shot by monitoring in each direction and shooting time.
10. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the operations corresponding to the big data based traffic light monitoring management method for smart city traffic as set forth in any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311469752.8A CN117456732A (en) | 2023-11-07 | 2023-11-07 | Signal lamp monitoring management method and device for intelligent urban traffic based on big data and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311469752.8A CN117456732A (en) | 2023-11-07 | 2023-11-07 | Signal lamp monitoring management method and device for intelligent urban traffic based on big data and computing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117456732A true CN117456732A (en) | 2024-01-26 |
Family
ID=89594525
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311469752.8A Withdrawn CN117456732A (en) | 2023-11-07 | 2023-11-07 | Signal lamp monitoring management method and device for intelligent urban traffic based on big data and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117456732A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117809460A (en) * | 2024-03-01 | 2024-04-02 | 电子科技大学 | Intelligent traffic regulation and control method and system |
-
2023
- 2023-11-07 CN CN202311469752.8A patent/CN117456732A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117809460A (en) * | 2024-03-01 | 2024-04-02 | 电子科技大学 | Intelligent traffic regulation and control method and system |
| CN117809460B (en) * | 2024-03-01 | 2024-05-14 | 电子科技大学 | Intelligent traffic regulation and control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zonoozi et al. | Periodic-CRN: A convolutional recurrent model for crowd density prediction with recurring periodic patterns. | |
| CN112700072B (en) | Traffic condition prediction method, electronic device, and storage medium | |
| CN110503833B (en) | Entrance ramp linkage control method based on depth residual error network model | |
| CN111680377B (en) | Traffic situation simulation method, system and electronic equipment | |
| CN111613072A (en) | Intelligent signal lamp timing optimization method, device, equipment, system and medium | |
| CN113362491B (en) | Vehicle track prediction and driving behavior analysis method | |
| CN112400192A (en) | Method and system for multi-modal deep traffic signal control | |
| CN109345832B (en) | Urban road overtaking prediction method based on deep recurrent neural network | |
| CN117456732A (en) | Signal lamp monitoring management method and device for intelligent urban traffic based on big data and computing equipment | |
| CN107977683A (en) | Joint SAR target identification methods based on convolution feature extraction and machine learning | |
| Nubert et al. | Traffic density estimation using a convolutional neural network | |
| CN111047078A (en) | Traffic characteristic prediction method, system and storage medium | |
| CN113159403A (en) | Method and device for predicting pedestrian track at intersection | |
| CN111126303B (en) | Multi-parking-place detection method for intelligent parking | |
| Dai et al. | Attention based simplified deep residual network for citywide crowd flows prediction | |
| CN115691165A (en) | Traffic signal lamp scheduling method, device and equipment and readable storage medium | |
| Khan et al. | Machine learning driven intelligent and self adaptive system for traffic management in smart cities | |
| CN114418606B (en) | Network vehicle order demand prediction method based on space-time convolution network | |
| CN116089875A (en) | Traffic flow prediction method, device and storage medium integrating multisource space-time data | |
| CN111341109A (en) | City-level signal recommendation system based on space-time similarity | |
| He et al. | Real-time pedestrian warning system on highway using deep learning methods | |
| CN117456730A (en) | Traffic flow prediction method based on self-adaptive partial attention spread graph convolutional neural network | |
| CN117351746A (en) | Dynamic signal timing optimization method and system based on short-time traffic prediction | |
| AU2019100967A4 (en) | An environment perception system for unmanned driving vehicles based on deep learning | |
| Al Afif et al. | Enhanced adaptive traffic signal control system using camera sensor and embedded system |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20240126 |