CN115546497A - Ship route network extraction method based on track big data - Google Patents
Ship route network extraction method based on track big data Download PDFInfo
- Publication number
- CN115546497A CN115546497A CN202211139055.1A CN202211139055A CN115546497A CN 115546497 A CN115546497 A CN 115546497A CN 202211139055 A CN202211139055 A CN 202211139055A CN 115546497 A CN115546497 A CN 115546497A
- Authority
- CN
- China
- Prior art keywords
- ship
- route network
- network
- ship route
- track
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Navigation (AREA)
Abstract
The invention discloses a track big data-based ship route network extraction method, which is used for determining route network characteristic elements by analyzing the basic characteristics of a route network, constructing a ship route network automatic generation model and realizing the quick and automatic generation of the ship route network. The invention mainly comprises the following steps: based on graph theory, a ship route network is regarded as a topological structure formed by route points in a navigable water area and connecting lines between the route points, and the quick extraction and low-dimensional representation of large-area routes are realized; based on a deep learning network, the space-time constraint of ship activities is fully considered, a ship route network characteristic element matching mechanism is designed according to the rules and characteristics of the ship activities, an automatic generation model of the ship route network is constructed, and the conversion from space-time tracks to ship experience routes is realized.
Description
Technical Field
The invention relates to the technical field of big data mining, in particular to a ship route network extraction method based on track big data, which is characterized in that a track nuclear density analysis algorithm is improved on the basis of analyzing and processing historical ship AIS big data to provide a new route point extraction method, a generation model is constructed on the basis of a generated countermeasure network to finish automatic generation of a ship route network, and the invention particularly relates to the ship route network extraction method based on the track big data.
Background
With the gradual popularization of sensors in intelligent equipment and the rapid development of positioning technology, the motion information of target objects such as vehicles, ships, pedestrians and the like is more convenient to capture and collect, and the motion information of the target objects in the space is combined according to time sequence to form corresponding track data. AIS provides almost global spatial coverage, and these AIS-related facilities improve waterway traffic supervision efficiency to a great extent, and electronic chart and route information with rich semantic information become indispensable spatial data resources. Experts at home and abroad deeply research the field of ship route network extraction, and provide algorithms such as a geometric analysis method and a cluster analysis method for navigable waters. The algorithms achieve certain results, and the progress of the intelligent channel technology is greatly promoted.
However, the current ship route network information research method mainly analyzes and identifies the problems of turning points, turning point connection and route center line extraction, and considers less characteristics of the environment, so that the research content for guiding ship navigation and designing routing design reference is lack of rationality. The existing ship route network extraction research has the following problems: the calculation amount is large, the method is difficult to be suitable for large-scale water areas, the dynamic environment of complex water areas cannot be processed, the channel characteristics are not considered, and the like.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a ship route network extraction method based on track big data.
Aiming at the problem of difficulty in obtaining ship route network information caused by complexity and dynamics of a navigation water area, the invention develops research and exploration from the perspective of data driving, designs a ship experience route extraction method, analyzes the range and hot spot area of a ship historical route based on ship track big data, provides a route point extraction algorithm of self-adaptive route width and track point density, and constructs an automatic generation model of a ship route network by considering the time-space characteristics of the traffic flow of the whole ship.
Analyzing the structural characteristics of the ship route network under the complex water area. Aiming at the complexity of waterway traffic, a ship and waterway network structure definition is provided, relevant definitions such as a waterway and a ship track are researched, the space-time characteristics of a ship and waterway network are analyzed by combining factors such as natural environment and traffic environment, the characteristics such as complexity, dynamics and timeliness of the ship and waterway network structure are researched, and the requirements of the ship and waterway network extraction method are summarized by comprehensively analyzing the researches of waterway planning, path planning and road network extraction.
The method for extracting traffic characteristic elements of navigable waters based on massive AIS data is researched. In order to capture the potential characteristics of ships and traffic, the traffic characteristics of navigable water areas are taken as research objects, firstly, the track density characteristics of the ships are mined, and the point-like characteristic elements of the ship route network are extracted. Then, an image processing technology is utilized to construct the boundary morphology of the empirical airway, wherein the boundary morphology comprises boundary detection, boundary smoothness and boundary completion, a traceable chain code tracking algorithm is provided to realize the vectorization of linear characteristic elements, and finally the extraction of planar characteristic elements is realized.
The research of the intelligent generation method of the ship route network facing to the complex water area. And aiming at characteristic element data of the navigation water area route network, constructing an automatically generated ship route network method. Firstly, coding the density characteristics of the ship track and learning the potential space-time characteristics of the track points. Then, the Skip-Connection structure is designed to capture and analyze the interaction information of the waypoints. Finally, considering the historical navigation track characteristics of the ship, designing a convolution layer to capture and analyze the connectivity of the route points, and establishing a ship route network element matching mechanism to obtain a more perfect ship route network topological structure
In order to solve the technical problems, the invention provides the following technical scheme:
the invention relates to a ship route network extraction method based on track big data, which comprises the following steps of;
s1, analyzing the structural characteristics of a ship route network;
s2, extracting network characteristics of the navigation water area airway;
and S3, intelligently generating a ship route network.
As a preferred technical scheme of the invention, the structural characteristic analysis of the ship route network is as follows; aiming at the complexity of waterway traffic, after the definition of a ship waterway network is provided, the specific contents of characteristic elements of the ship waterway network are explained, the space-time characteristics of ship tracks are considered, the interrelation among various characteristic elements is excavated, and the construction of a topological structure of the ship waterway network is realized.
As a preferred embodiment of the present invention, the characteristics of the airway network include dynamics, complexity, and timeliness, and the characteristic elements include a point characteristic element, a line characteristic element, and a surface characteristic element.
As a preferred technical scheme of the invention, the method for extracting the network characteristics of the navigation water area airway comprises the following steps of; ship track data are matched with research areas divided by a grid model, a ship empirical route is extracted by an improved kernel density estimation method, route point extraction is realized by capturing traffic flow characteristics of ships in a group, the boundary form of the empirical route is constructed by using a digital image processing technology, and extracted grid boundary information is converted into vector information.
As a preferred technical scheme of the invention, the method for intelligently generating the ship route network comprises the following steps of; the characteristic elements of the ship route network are subjected to superposition analysis, ship navigation experience is considered, a matching mechanism of the characteristic elements of the ship route network is designed, a deep learning method is provided according to the dynamic change characteristic of the ship route network to complete a generation task of the ship route network, and the quick generation of the ship route network structure is realized.
Compared with the prior art, the invention has the following beneficial effects:
1: the method comprehensively considers factors such as ship navigation experience, ship operation behaviors, channel width characteristics and the like, designs a ship route network characteristic element matching mechanism, constructs a ship route network automatic generation model based on the generated countermeasure network, can completely and accurately generate the complex route network, and provides a new method for reconstructing the ship route network from complex track data.
2: compared with the traditional clustering extraction method, the self-adaptive waypoint extraction method based on ship big data realizes dynamic and real-time waypoint extraction, and improves the adaptability of the ship waypoint network extraction method to dynamically changing waterway traffic environments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of the steps corresponding to the method of the present invention;
FIG. 2 is a flow chart of the matching of characteristic elements of the ship route network of the present invention;
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example 1
As shown in fig. 1-2, the invention provides a ship route network extraction method based on track big data, which comprises the following steps;
s1, analyzing the structural characteristics of a ship route network, namely defining the concept of the ship route network through a data structure based on the regularity of water route traffic, analyzing relevant definitions of ship tracks, routes, ship stopping and moving and the like, researching the network characteristics of the route network in navigable water areas, researching the characteristics of different elements, comparing the characteristics of the route network in a modern traffic transportation mode, and analyzing the characteristics of the ship route network such as dynamic property, complexity, timeliness and the like;
s2, extracting network characteristics of the navigation water area route, namely constructing a self-adaptive route point extraction algorithm aiming at the problem that the density distribution of track points is uneven. Based on a digital image processing technology, extracting the boundary of the ship empirical route, providing a method for grid data vectorization, automatically realizing the generation of a vector boundary, considering the characteristics of a ship and designing a KDE-T algorithm to quickly excavate a historical track hotspot region of the ship aiming at the problem of dynamic change of the ship empirical route;
and S3, intelligently generating a ship route network, namely providing an automatic extraction model of the ship route network, establishing a potential structure consisting of route points, traffic flow density and ship experience routes, designing a route network component element matching mechanism, and automatically generating a complex route network to provide reference for a port department to know the structure and evolution of marine traffic.
Further, analyzing the structural characteristics of the ship route network into; aiming at the complexity of waterway traffic, after the definition of the ship waterway network is provided, the specific contents of characteristic elements of the ship waterway network are explained, and the interrelation among various characteristic elements is excavated by considering the space-time characteristics of ship tracks, so that the construction of a topological structure of the ship waterway network is realized.
Further, the characteristics of the air route network comprise dynamic property, complexity and timeliness, and the characteristic elements comprise point characteristic elements, linear characteristic elements and surface characteristic elements.
Further, the method for extracting the network characteristics of the navigation water area airway comprises the following steps of; ship track data are matched with research areas divided by a grid model, a ship empirical route is extracted by an improved kernel density estimation method, route point extraction is realized by capturing traffic flow characteristics of ships in a group, the boundary form of the empirical route is constructed by using a digital image processing technology, and extracted grid boundary information is converted into vector information.
Furthermore, the method for intelligently generating the ship route network comprises the following steps of; the characteristic elements of the ship route network are subjected to superposition analysis, ship navigation experience is considered, a matching mechanism of the characteristic elements of the ship route network is designed, a deep learning method is provided according to the dynamic change characteristic of the ship route network to complete a generation task of the ship route network, and the quick generation of the ship route network structure is realized.
Specifically, S1, analyzing the structural characteristics of a ship route network; the AIS data contains three different types of information, namely dynamic information, static information, and vessel voyage information. The dynamic information comprises ship navigation information such as MMSI (multimedia messaging service), ship position, ship speed, course and the like, the static information comprises information such as MMSI (multimedia messaging service), ship name, call sign, ship type and the like, and the ship range information comprises ship draught, destination, estimated arrival time and the like.
The method comprises the steps of extracting historical tracks of ships based on time periods and space ranges, mining navigation information behavior characteristics of track points of the ships, distinguishing voyages to generate actual voyages, analyzing ship density conditions and trends by using a space data mining method according to the space distribution characteristics of the actual voyages, calculating high-density areas to represent main voyages and navigate, and using a deep learning network prediction model to realize automatic generation of a ship voyage network.
For the structural characteristic analysis of the ship route network, the specific analysis method is that for the ship route network Z = (P, W, O), wherein P is a node set,
is a set of edges and O is a set of faces.
Node p i E P is an waypoint, and the course and the speed of the ship are required to be changed when the ship sails to the waypoint.
Side w k ＝(p i ，p j ) E W is the leg, indicating that a waypoint p can be initiated from i Sailing to the ending waypoint.
Noodle o m ＝(LB x ，LB y ，RT x ，RT y ) E.O is a space grid of a navigation water area, and each grid comprises a lower left corner coordinate (LB) x ，LB y ) And coordinates of the upper right corner (RT) x ，RT y )。
S2, extracting network characteristics of the navigation water area airway; and (3) estimating the track Density of the ship by adopting a KDE-T (Kernel sensitivity estimation for Traffic) algorithm, and using the track Density for estimating the empirical route of the ship in the water area.
The KDE-T algorithm comprises the following three steps: the first step is to compress the tracks in the whole range into a two-dimensional density estimation grid map; secondly, calculating the track times of each grid to obtain a rough track density distribution map; and thirdly, setting a density threshold value to deduce an empirical ship route according to the density distribution condition.
The method comprises the steps of optimizing a ship empirical airway by using an image processing method, extracting ship empirical airway raster data by applying KDE-T analysis aiming at ship tracks, opening and operating mathematical morphology to smooth airway boundaries, closing and operating to construct airway boundary morphology, detecting planar characteristic elements by using Canny operators, generating airway boundaries with high accuracy, strong connectivity and smoothness, positioning the raster boundaries, tracking the airway boundaries by using chain codes, and extracting characteristic points to realize airway boundary instantiation.
The self-adaptive waypoint extracting method extracts punctiform characteristic elements, deduces a hot spot region of traffic flow by using a ship track kernel density matrix, extracts control points by using the speed change trend in the ship historical track, and filters the waypoints by combining the control points to realize the waypoint extraction.
S3, generating a ship route network intelligently; generating a ship route network based on the historical ship track, designing a characteristic element matching mechanism of the ship route network, and realizing the generation of real data of the ship route network, as shown in fig. 2, the specific steps are as follows:
first, based on the neighborhood radius P l Calculating the influence range P of all waypoints * 。
Secondly, traversing all historical tracks X of the ship and judging whether the tracks are positioned at P * Inner, i.e. track x i And waypoint p h Distance D (x) i ，p h ) Whether or not less than radius P δ 。
Thirdly, recording the ship in two adjacent P * Move the sub-locus X in between * 。
And finally, judging whether the moving sub-track is selected as a navigation section of the ship navigation network or not based on four indexes:
(a) Time of flight
Whether the span is greater than the time threshold T δ ；
(b) Length of track
Whether or not it is greater than the spatial threshold L δ ；
(c) Whether the trajectory crosses the airway boundary E o ；
(d) Whether a connection has been established between adjacent waypoints, i.e., two waypoints are not connected for a while, ED is false.
The correlation formula is:
X * ＝(x i ，x i+1 ，...，x j )，D(x i ，p h )＜P δ ，D(x j ，p h+1 )～P δ
(formula 1)
The intelligent generation method of the ship route network inputs X into n ship track sequences:
X＝(X 1 ，X 2 ，...，X n )，X i ＝(x 1 ，x 2 ，...x t )，x ii = (lon, lat, v, c, t) (equation 3)
The ship AIS data records longitude lon, latitude lat, speed v, heading c and sending time t.
The intelligent generation method of the ship route network comprises a generator based on a U-Net framework and a discriminator based on convolution PatchGAN, wherein the generator comprises an encoder and a decoder. The encoder comprises 8 convolutional layers, wherein each layer comprises a convolutional layer, a normalization layer and an active layer; the decoder comprises 7 deconvolution layers, and each layer comprises four parts, namely an deconvolution layer, a normalization layer, a Dropout and an activation layer. And the discriminator encodes the airway network elements through the full-connection layer convolutional network, learns hidden characteristic information of the ship airway network, classifies the image characteristics and finally outputs a classification result.
The method comprehensively considers factors such as ship navigation experience, ship operation behaviors, channel width characteristics and the like, designs a ship route network characteristic element matching mechanism, constructs a ship route network automatic generation model based on the generated countermeasure network, can completely and accurately generate a complex route network, and provides a new method for reconstructing the ship route network from complex track data; compared with the traditional clustering extraction method, the method realizes dynamic and real-time waypoint extraction, and improves the adaptability of the ship route network extraction method to dynamically-changed waterway traffic environments.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described above, or equivalents may be substituted for elements thereof. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A ship route network extraction method based on track big data is characterized by comprising the following steps;
s1, analyzing the structural characteristics of a ship route network;
s2, extracting network characteristics of the navigation water area airway;
and S3, intelligently generating a ship route network.
2. The ship route network extraction method based on the track big data is characterized in that the structural characteristics of the ship route network are analyzed as follows; aiming at the complexity of waterway traffic, after the definition of a ship waterway network is provided, the specific contents of characteristic elements of the ship waterway network are explained, the space-time characteristics of ship tracks are considered, the interrelation among various characteristic elements is excavated, and the construction of a topological structure of the ship waterway network is realized.
3. The ship route network extraction method based on the track big data as claimed in claim 2, wherein the route network features include dynamics, complexity and timeliness, and the feature elements include point feature elements, line feature elements and surface feature elements.
4. The ship route network extraction method based on the track big data as claimed in claim 3, wherein the method for extracting the navigable water area route network features is; ship track data are matched with research areas divided by a grid model, ship empirical routes are extracted by an improved kernel density estimation method, route point extraction is realized by capturing traffic flow characteristics of group ships, the boundary form of the empirical routes is constructed by using a digital image processing technology, and extracted grid boundary information is converted into vector information.
5. The ship route network extraction method based on the big track data as claimed in claim 4, wherein the method for intelligently generating the ship route network is; the characteristic elements of the ship route network are subjected to superposition analysis, ship navigation experience is considered, a matching mechanism of the characteristic elements of the ship route network is designed, a deep learning method is provided according to the dynamic change characteristic of the ship route network to complete a generation task of the ship route network, and the quick generation of the ship route network structure is realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211139055.1A CN115546497A (en) | 2022-09-19 | 2022-09-19 | Ship route network extraction method based on track big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211139055.1A CN115546497A (en) | 2022-09-19 | 2022-09-19 | Ship route network extraction method based on track big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115546497A true CN115546497A (en) | 2022-12-30 |
Family
ID=84726696
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211139055.1A Pending CN115546497A (en) | 2022-09-19 | 2022-09-19 | Ship route network extraction method based on track big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115546497A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117251748A (en) * | 2023-10-10 | 2023-12-19 | 中国船舶集团有限公司第七〇九研究所 | Track prediction method, equipment and storage medium based on historical rule mining |
-
2022
- 2022-09-19 CN CN202211139055.1A patent/CN115546497A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117251748A (en) * | 2023-10-10 | 2023-12-19 | 中国船舶集团有限公司第七〇九研究所 | Track prediction method, equipment and storage medium based on historical rule mining |
| CN117251748B (en) * | 2023-10-10 | 2024-04-19 | 中国船舶集团有限公司第七〇九研究所 | Track prediction method, equipment and storage medium based on historical rule mining |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210352B (en) | Ship track abnormity detection method based on channel model | |
| CN113032502B (en) | Ship anomaly detection method based on improved track segment DBSCAN clustering | |
| Shah et al. | Long-distance path planning for unmanned surface vehicles in complex marine environment | |
| CN112906830B (en) | Automatic generation method of ship optimal route based on AIS big data | |
| Varlamis et al. | A Network Abstraction of Multi-vessel Trajectory Data for Detecting Anomalies. | |
| Lolla et al. | Time-optimal path planning in dynamic flows using level set equations: Realistic applications | |
| CN108536140A (en) | A kind of unmanned boat autonomous navigation system and method | |
| Choi et al. | Local volumetric hybrid-map-based simultaneous localization and mapping with moving object tracking | |
| Tang et al. | Detection of abnormal vessel behaviour based on probabilistic directed graph model | |
| CN112698653A (en) | Robot autonomous navigation control method and system based on deep learning | |
| Chang et al. | Vessel traffic analysis for maritime intelligent transportation system | |
| CN115546497A (en) | Ship route network extraction method based on track big data | |
| Liu et al. | Visualization and visual analysis of vessel trajectory data: A survey | |
| Niedoba et al. | Improving movement prediction of traffic actors using off-road loss and bias mitigation | |
| CN105243354B (en) | A kind of vehicle checking method based on target feature point | |
| Campo et al. | Learning probabilistic awareness models for detecting abnormalities in vehicle motions | |
| Lee et al. | In-pipe robot navigation based on the landmark recognition system using shadow images | |
| Dong et al. | Two-staged method for ice channel identification based on image segmentation and corner point regression | |
| Zheng et al. | A hierarchical approach for mobile robot exploration in pedestrian crowd | |
| Xu et al. | Improved vessel trajectory prediction model based on stacked-bigrus | |
| Lei et al. | Trajectory data restoring: A way of visual analysis of vessel identity base on optics | |
| Lee et al. | Generation of Ship’s passage plan using data-driven shortest path algorithms | |
| CN114139642A (en) | Ship route extraction method combining ship journey semantic object and graph theory | |
| CN116150299A (en) | Multi-source track association method guided by credibility propagation network | |
| Eljabu et al. | Spatial clustering model of vessel trajectory to extract sailing routes based on ais data |
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 |