CN112330069A - Early warning removing method and device, electronic equipment and storage medium - Google Patents
Early warning removing method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112330069A CN112330069A CN202011364754.7A CN202011364754A CN112330069A CN 112330069 A CN112330069 A CN 112330069A CN 202011364754 A CN202011364754 A CN 202011364754A CN 112330069 A CN112330069 A CN 112330069A
- Authority
- CN
- China
- Prior art keywords
- cloud
- training
- image
- weather
- early warning
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012549 training Methods 0.000 claims abstract description 157
- 238000003066 decision tree Methods 0.000 claims abstract description 62
- 238000012544 monitoring process Methods 0.000 claims abstract description 24
- 238000013145 classification model Methods 0.000 claims description 38
- 238000013135 deep learning Methods 0.000 claims description 16
- 238000013136 deep learning model Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 230000010006 flight Effects 0.000 abstract description 5
- 230000002349 favourable effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000015572 biosynthetic process Effects 0.000 description 5
- 238000009825 accumulation Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000005096 rolling process Methods 0.000 description 4
- 230000001550 time effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005562 fading Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 201000004384 Alopecia Diseases 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000036621 balding Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003676 hair loss Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G06Q50/40—
Abstract
The invention discloses an early warning cancellation method and device, electronic equipment and a storage medium. The method comprises the following steps: monitoring a cloud image of convection weather after entering a convection cloud early warning state; if the cloud image is monitored to have accumulated rain clouds, inputting the cloud image in a preset time period, the cloud type in the cloud image and weather parameters into a pre-trained decision tree, wherein the decision tree is obtained by training according to a training cloud image in the preset time period before the convective weather rain is stopped, the cloud type in the training cloud image and the weather parameters; and if the prediction result output by the decision tree is rain stop, removing the convection cloud cluster early warning state. The embodiment of the invention realizes that the cloud cluster state and whether the cloud cluster state is rainy after the preset time are judged according to the cloud images in the preset time, is favorable for an airport to determine the time for relieving large-area delay early warning of flights, and makes normal take-off and landing of subsequent flights in advance.
Description
Technical Field
The embodiment of the invention relates to the technical field of computer vision, in particular to an early warning removing method and device, electronic equipment and a storage medium.
Background
Convective weather generally refers to weather changes including thunderstorms, squall, hail, tornados, etc., produced by convective clouds. Convection weather generally has prominent characteristics of burstiness, locality, disaster causing and the like, such as: "thunderstorms" are the violent discharges of lightning events that occur in a cloud of accumulated rain, which are generally accompanied by thunderstorms. The thunderstorm is a common rainfall form in summer and is strong in duration, and the strong rainfall of the duration brings disasters of different degrees to people, so that the lives and properties of the people are threatened.
Because the aircraft has certain requirements on weather elements such as fog, thunderstorm, cloud height, visibility, wind direction, wind speed and the like in weather conditions during flying, the phenomena of strong disturbance, icing, violent discharge and the like in the accumulated rain cloud in the cloud cluster can greatly threaten the flying safety of the aircraft. Thus, thunderstorm weather also poses a hazard to aircraft flight, and prediction of convective cloud formation and dissipation is highly desirable. At present, the formation and the dissipation of the convection cloud are predicted mostly by means of a radar echo diagram, and the radar is high in economic cost and cannot be popularized.
Disclosure of Invention
The invention provides an early warning removing method, an early warning removing device, electronic equipment and a storage medium, which are used for removing the early warning state of a cloud cluster according to a cloud image in real time, so that the rain stopping time is accurately predicted, and the accurate time for removing the large-area delay early warning of a flight is determined.
In a first aspect, an embodiment of the present invention provides an early warning cancellation method, where the method includes:
monitoring a cloud image of convection weather after entering a convection cloud early warning state;
if the cloud image is monitored to have accumulated rain clouds, inputting the cloud image in a preset time period, the cloud type in the cloud image and weather parameters into a pre-trained decision tree, wherein the decision tree is obtained by training according to a training cloud image in the preset time period before the convective weather rain is stopped, the cloud type in the training cloud image and the weather parameters;
and if the prediction result output by the decision tree is rain stop, removing the convection cloud cluster early warning state.
Further, the decision tree is obtained according to training cloud images in a preset time period before the convective weather is stopped, the types of clouds in the training cloud images and the weather parameters, and the training comprises:
inputting training cloud images in a preset time before the convective weather is stopped for a preset number of times, the cloud types in the training cloud images and weather parameters into a deep learning model, and training a decision tree to be trained.
Further, before monitoring the cloud image of the convective weather, the method further includes:
monitoring a cloud image of convective weather through a pre-trained cloud classification model;
the acquisition mode of the cloud classification model comprises the following steps:
acquiring a cloud image to be trained;
and training the deep learning classification network for preset times according to the cloud image to be trained until the deep learning classification network is converged to obtain the cloud classification model.
Further, acquiring a cloud image to be trained; according to the cloud image to be trained, training a deep learning classification network for a preset number of times until the deep learning classification network converges to obtain the cloud classification model, the method further comprises the following steps:
inputting the normalized training cloud image into a classification network structure, and determining a probability value of a cloud type corresponding to the training cloud image;
and determining the cloud category corresponding to the training cloud image according to the probability value of the cloud category corresponding to the training cloud image and the threshold value corresponding to each cloud category.
Further, before determining the cloud class corresponding to the training cloud image according to the probability value of the cloud class label corresponding to the training cloud image and the threshold value corresponding to each cloud class, the method further includes:
determining a probability value corresponding to the cloud type in the training cloud image according to the classification network structure;
determining a threshold value corresponding to each cloud class according to the training cloud image, the probability value corresponding to the cloud class in the training cloud image and the cloud class corresponding to the training cloud image label
Further, the method includes the steps of inputting training cloud images in a preset time before the convective weather is stopped for a preset number of times, the types of clouds in the training cloud images and weather parameters into a deep learning model, and before training a decision tree to be trained, further including:
performing non-deformation scaling on the training cloud image;
correspondingly adding cloud class labels to the zoomed training cloud images according to preset cloud classes;
and storing the cloud class label corresponding to the training cloud image in association with the training cloud image.
Further, the prediction result output by the decision tree is rain-stop, and the method comprises the following steps:
and if no rain cloud or cloud layered cloud exists in the cloud category corresponding to the cloud image, the air pressure is increased, and the air speed is reduced, the prediction result is rain stop.
In a second aspect, an embodiment of the present invention further provides an early warning cancellation apparatus, where the apparatus includes:
the early warning monitoring module is used for monitoring a cloud image of convection weather after entering a convection cloud early warning state;
the cloud-shaped analysis module is used for inputting the cloud-shaped image in a preset time period, the type of cloud in the cloud-shaped image and the weather parameters into a pre-trained decision tree if it is monitored that the cloud-shaped image has accumulated rain clouds, and the decision tree is obtained by training according to a training cloud-shaped image in the preset time period before the convective weather rain is stopped, the type of cloud in the training cloud-shaped image and the weather parameters;
and the early warning removing module is used for removing the early warning state of the convection cloud cluster if the prediction result output by the decision tree is rain stop.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
one or more processors;
a storage device for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the disarm alert method.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for canceling an early warning.
After entering a convection cloud early warning state, the cloud image of convection weather is monitored; if the cloud image is monitored to have accumulated rain clouds, inputting the cloud image in a preset time period, the cloud type in the cloud image and weather parameters into a pre-trained decision tree, wherein the decision tree is obtained by training according to a training cloud image in the preset time period before the convective weather rain is stopped, the cloud type in the training cloud image and the weather parameters; and if the prediction result output by the decision tree is rain stop, removing the convection cloud cluster early warning state. The method solves the problems that most of the prediction on the formation and the dissipation of the convection cloud cluster is carried out by means of a radar echo map, the economic cost is high, and the popularization rate is low, and the early warning state of the convection cloud cluster is relieved in real time according to the cloud image, so that the rain stop time is accurately predicted, and the accurate time effect of relieving the large-area delay early warning of flights is determined.
Drawings
Fig. 1 is a flowchart of an early warning cancellation method according to a first embodiment of the present invention;
fig. 1A is a schematic diagram of a convective cloud cluster change of an early warning cancellation method according to a first embodiment of the present invention;
fig. 1B is a schematic diagram of a decision tree of an early warning cancellation method according to a first embodiment of the present invention;
fig. 2 is a flowchart of an early warning cancellation method in the second embodiment of the present invention;
fig. 2A is a schematic flowchart of an early warning cancellation method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an early warning cancellation device in the third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device in a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of an early warning cancellation method according to an embodiment of the present invention, where the method is applicable to a situation that weather early warning cancellation is required, and the method may be executed by an early warning cancellation apparatus, and the apparatus may be implemented in a software and/or hardware manner, and may specifically inherit in an electronic device with storage and computing capabilities to perform weather early warning cancellation.
As shown in fig. 1, there is provided an early warning cancellation method, including:
step S110, monitoring a cloud image of convection weather after entering a convection cloud early warning state;
in the embodiment of the present invention, the convective cloud may be understood as a cloud appearing in the sky in strong convective weather, and the cloud includes various types of cloud with various shapes, for example: broken cloudiness, light cloudiness, bald cloudiness, bristle cloudiness, pseudo-rolling clouds, cloudy high cloudiness, cloudy layer clouds, and the like. The bald and rain clouds can be understood as the transition stage of the thick cloud to the bristle cloud, the shape and the contour of the bald and rain clouds are blurred, and the top of the bald and rain clouds is frozen to form a white hairy-silk-like ice crystal structure; bristle clouding is understood to be the mature stage of development of a dense cloud, "bristle-like" with fine bristle streaks, with the appearance of a large number of ice crystals; pseudo-cloud may be understood as a cloud of bristle-like parts of the rain cloud during the convective decay phase; the high clouding cloud can be understood as the cloud body of the bristle rain cloud in the middle collapse state in the convection recession stage; a cloudy layer cloud is understood to mean a cloud of bristles in the convective decay phase with a flat, laminar bottom portion. The convection cloud early warning state can be understood as that the current weather state is judged to be in convection cloud weather according to the characteristic attribute of the convection cloud weather, and the end time of the convection weather needs to be early warned according to the current stage of the convection cloud. The cloud image of the convective weather can be understood as an image of a cloud in the sky collected in the convective weather, where the image includes a plurality of features of the cloud, for example: shape, color, etc. of the cloud.
In the embodiment of the present invention, the mode of entering the convection cloud early warning state may be that after determining the convection cloud weather according to the type of cloud in the cloud image appearing in the primary stage of the convection weather and the weather parameter corresponding to the convection cloud weather, the mode of entering the convection cloud early warning state is not further limited here. And after entering a convection cloud cluster early warning state, starting to monitor whether rain clouds are accumulated in the cloud type in the cloud image in the convection weather in real time. The rain cloud convection weather in different stages can be divided into: baldness, rain clouds and sideburns.
Fig. 1A is a schematic diagram of a change of a cloud cluster of a convection current of an early warning cancellation method according to an embodiment of the present invention, as shown in fig. 1A, a broken cloud and a light cloud appear in a primary stage of a convection current, where the broken cloud and the light cloud can be understood as a primary state of the cloud, and the light cloud can be transformed into the light cloud by a heating force of the light-transmitting layer cloud, the light cloud can be transformed into a thick cloud under a suitable thermal condition, and the thick cloud can be further transformed into a bald cloud and a bristled cloud. Balding clouds and bristle clouds have evolved into pseudo-or rolling clouds. Pseudo rolling clouds or rolling clouds are evolved to form cloud-accumulating laminated clouds or cloud-accumulating high-accumulated clouds, wherein the cloud-accumulating high-accumulated clouds are formed by flattening the middle-layer high clouds in the fading process of the rain clouds, have cloud-accumulating characteristics, but the weather gradually tends to be stable; the cloud-like laminated cloud can be understood as being formed by flattening in the cloud fading process and has cloud-like characteristics.
Step S120, if it is monitored that the cloud image has accumulated rain clouds, inputting the cloud image in a preset time period, the cloud type in the cloud image and weather parameters into a pre-trained decision tree, wherein the decision tree is obtained by training according to a training cloud image in the preset time period before the convective weather is stopped, the cloud type in the training cloud image and the weather parameters;
in the embodiment of the present invention, the preset time period may be understood as a time length of a time window set according to a requirement, or may be a state of the convection cloud after the time period needs to be determined, that is, a convection weather state. The cloud image in the preset time period can be understood as a cloud image corresponding to the collected convection weather in a set time window. The cloud category may be understood as all cloud categories that occur during convective weather. The training cloud image can be understood as a training cloud image acquired in a multi-convection weather. Weather parameters may be understood as having an index of influence on the shape of the cloud during convective weather, for example: wind speed, air pressure, humidity, temperature, etc.
In the embodiment of the invention, the occurrence of the convection cloud cluster is accompanied by the rain cloud, and the strong disturbance, icing and discharge phenomena exist in the rain cloud, so that the detection of the rain cloud is equivalent to the detection of the occurrence of the convection cloud cluster, and the early warning cancellation time needs to be determined in the weather of the convection cloud. And inputting the cloud images in the preset time period, the cloud types in the cloud images and the weather parameters into a pre-trained decision tree, and judging whether the cloud images in the preset time period accord with the characteristics of the convection weather in the preset time period before the convection weather is stopped or not according to the pre-trained decision tree so as to predict the weather state after the preset time period.
Further, the decision tree is obtained according to training cloud images in a preset time period before the convective weather is stopped, the types of clouds in the training cloud images and the weather parameters, and the training comprises:
inputting training cloud images in a preset time before the convective weather is stopped for a preset number of times, the cloud types in the training cloud images and weather parameters into a deep learning model, and training a decision tree to be trained.
In the embodiment of the present invention, the decision tree to be trained may be understood as a tree structure before inputting the parameter features, where each internal node represents a test on an attribute, each branch represents a test output, and each leaf node represents a category. A deep learning model may be understood as a machine learning algorithm that is capable of learning the intrinsic laws and representation hierarchies of sample data. The preset times can be understood as the times of the selected convective weather from the convective weather times stored in the historical data, and can also be understood as the number of training samples of the deep learning model.
In the embodiment of the invention, the training cloud-shaped image in the preset time before the convection weather rainstop for the preset times, the cloud type in the training cloud-shaped image and the weather parameters are input into the deep learning model, then the deep learning model analyzes the intrinsic rules and characteristics of the data before the convection weather rainstop for the convection weather according to the input data before the convection weather rainstop for the preset times, so that the decision tree to be trained is trained according to the intrinsic rules and characteristics of the data analyzed by the deep learning model, and the decision data to be trained classifies the weather characteristics corresponding to the cloud-shaped image according to the intrinsic rules and characteristics of the data, so as to obtain the decision tree capable of predicting the convection weather.
And step S130, if the prediction result output by the decision tree is rain stop, the convection cloud cluster early warning state is released.
In the embodiment of the invention, the prediction result can be understood as a result of determining whether the convection cloud cluster dissipates or not in the convection cloud sky state according to the trained decision tree.
In the embodiment of the invention, the input cloud image, the cloud type in the cloud image and the prediction result corresponding to the weather parameter are decided, and if the cloud image is in a rain stop state, the convection cloud cluster dissipates after a preset time period, and the early warning state of the convection cloud cluster needs to be relieved.
Further, the prediction result output by the decision tree is rain-stop, and the method comprises the following steps:
and if no rain cloud or cloud layered cloud exists in the cloud category corresponding to the cloud image, the air pressure is increased, and the air speed is reduced, the prediction result is rain stop.
Illustratively, the decision tree features presented according to the internal rules and features of the data before the weather is rainy and stopped are different according to different preset times, which are specifically as follows:
fig. 1B is a schematic diagram of a decision tree of an early warning cancellation method according to a first embodiment of the present invention, as shown in fig. 1B, in step S1, it is first determined whether there is a rain cloud in the cloud type of the cloud in the input cloud image, if there is a rain cloud in the input cloud image, the convection cloud is not dissipated, and the early warning cannot be cancelled after a preset time in the rain; if there is no rain cloud in the input cloud image, step S2 is performed. Step S2, determining whether or not there is a cloud-accumulating laminated cloud in the type of cloud in the input cloud image, and if there is a cloud-accumulating laminated cloud in the type of cloud in the input cloud image, determining whether or not the air pressure is increased in the weather parameter corresponding to the cloud image input within the preset time period. If the air pressure in the weather parameters does not rise, the convection cloud cluster is not dissipated, and the early warning cannot be relieved after the preset time in the rain; and if the air pressure in the weather parameters rises, judging whether the wind speed in the weather parameters corresponding to the cloud images in the preset time period drops. And if the wind speed in the weather parameters is reduced, the convection cloud cluster is dissipated, and the early warning is removed after the rain is stopped for a preset time. If the wind speed is not reduced in the weather parameters, the convection cloud cluster is not dissipated, and the early warning cannot be relieved after the preset time in the rain. If the cloud type does not have a cloud-like layered cloud in the input cloud image, the process proceeds to step S3. Step S3, judging whether the cloud type in the input cloud image has the cloud accumulation high cloud accumulation or not, if the cloud type in the input cloud image has no the cloud accumulation high cloud accumulation, the convection cloud cluster is not dissipated, and the early warning can not be removed after the preset time in the rain; if the cloud type in the input cloud image has a high cloud point, the process proceeds to step S4. Step S4, judging whether the air pressure in the weather parameter corresponding to the input cloud image rises or not, if the air pressure in the weather parameter corresponding to the input cloud image does not rise, the convection cloud cluster is not dissipated, and the early warning cannot be relieved after the preset time in the rain; if the air pressure in the weather parameter corresponding to the input cloud image is increased, the process proceeds to step S5. Step S5, judging whether the wind speed in the weather parameters corresponding to the input cloud images is reduced, if the wind speed in the weather parameters corresponding to the input cloud images is not reduced, the convection cloud cluster is not dissipated, and the early warning cannot be relieved after the preset time in the rain; and if the wind speed in the weather parameter corresponding to the input cloud image is reduced, dissipating the convection cloud cluster, and removing the early warning after the rain stops for a preset time.
After entering a convection cloud early warning state, the cloud image of convection weather is monitored; if the cloud image is monitored to have accumulated rain clouds, inputting the cloud image in a preset time period, the cloud type in the cloud image and weather parameters into a pre-trained decision tree, wherein the decision tree is obtained by training according to a training cloud image in the preset time period before the convective weather rain is stopped, the cloud type in the training cloud image and the weather parameters; and if the prediction result output by the decision tree is rain stop, removing the convection cloud cluster early warning state. The method solves the problems that most of the prediction on the formation and the dissipation of the convection cloud cluster is carried out by means of a radar echo map, the economic cost is high, and the popularization rate is low, and the early warning state of the convection cloud cluster is relieved in real time according to the cloud image, so that the rain stop time is accurately predicted, and the accurate time effect of relieving the large-area delay early warning of flights is determined.
Example two
Fig. 2 is a flowchart of an early warning cancellation method in the second embodiment of the present invention, and the technical solution of the second embodiment of the present invention is further detailed on the basis of the above technical solution, and specifically includes the following steps:
step S210, monitoring a cloud image of convective weather through a pre-trained cloud classification model; the acquisition mode of the cloud classification model comprises the following steps: acquiring a cloud image to be trained; and training the deep learning classification network for preset times according to the cloud image to be trained until the deep learning classification network is converged to obtain the cloud classification model.
In the embodiment of the invention, the pre-trained cloud classification model can be understood as a pre-trained recognition model for recognizing the cloud type in the cloud image. The deep learning classification network can be understood as a classification network according to the inherent rules and characteristics of the preset cloud category in the training cloud image. Cloud classification model convergence may be understood as the cloud classification model being available after the error of the cloud classification model is less than a certain threshold, while training is stopped.
In the embodiment of the invention, the monitoring of the cloud image of the convection cloud weather is to substantially monitor the cloud type in the cloud image of the convection cloud weather, and a pre-trained cloud classification model needs to be trained in advance. And after entering a convection cloud cluster early warning state, identifying the cloud type in the cloud image of the convection weather monitored in real time according to the pre-trained cloud classification model. When the pre-trained cloud classification model is trained, the training cloud images and the cloud types in the training cloud images are input into a deep learning classification network for training. After the training is finished, whether the cloud classification model which is pre-trained is converged or not needs to be judged if the cloud classification model which is formed after the training is finished, the convergence error is smaller than a certain threshold value when the calculated binary cross entropy is smaller than the set threshold value according to the binary cross entropy of the loss function, and the model is available; when the calculated binary cross entropy is larger than the set value, the divergence error is larger than the threshold value, and the model is unavailable.
Step S220, after entering a convection cloud early warning state and entering the convection cloud early warning state, monitoring a cloud image of convection weather;
in the embodiment of the invention, the pre-trained cloud classification model can be used after the cloud classification model is converged. After the pre-trained classification model is used, the cloud type in the cloud image is identified according to the pre-trained cloud classification model. And identifying the cloud type in the cloud image according to the pre-trained cloud classification model, judging whether the current cloud is in convection cloud weather, and entering a convection cloud cluster early warning state.
Further, the method includes the steps of inputting training cloud images, cloud types in the training cloud images and weather parameters within a preset time before the convective weather is stopped for a preset number of times into a deep learning model, and before training a decision tree to be trained, further including:
performing non-deformation scaling on the training cloud image;
correspondingly adding cloud class labels to the zoomed training cloud images according to preset cloud classes;
and storing the cloud class label corresponding to the training cloud image in association with the training cloud image.
In the embodiment of the present invention, the non-deformation scaling may be understood as changing the size of the image to a specified size and maintaining the shape of each element in the image unchanged, i.e. scaling. The preset cloud category may be understood as a category in which all cloud categories may appear in convective weather. The cloud category label may be understood as a label having a mapping relationship set according to a preset cloud category, and each cloud category has a corresponding label.
In the embodiment of the invention, the training cloud images corresponding to the convection weather for the preset times are subjected to the non-deformation scaling value preset size, and the training cloud images corresponding to the convection weather for the preset times are marked according to the cloud types in the training cloud images corresponding to the convection weather for the preset times and the preset cloud type labels. The cloud class label may be a preset number class according to a preset cloud class, or may be a shape having a mapping relationship, for example: the preset cloud types are i types and can be classified into i types, and the cloud type labels can be [1, 0, 0, …, 0] and represent that the 1 st type of cloud appears in the training cloud images. The cloud type in the training cloud image corresponding to the convection weather for the preset times is known in advance, and the training cloud image corresponding to the convection weather for the preset times and the cloud type label are stored in an associated mode.
Further, acquiring a cloud image to be trained; according to the cloud image to be trained, training a deep learning classification network for a preset number of times until the deep learning classification network converges to obtain the cloud classification model, the method further comprises the following steps:
inputting the normalized training cloud image into a classification network structure, and determining a probability value of a cloud category corresponding to the training cloud image;
and determining the cloud category corresponding to the training cloud image according to the probability value of the cloud category corresponding to the training cloud image and the threshold value corresponding to each cloud category.
In the embodiment of the invention, normalization can be understood as standard processing transformation of the marked training cloud images, so that the marked training cloud images represent standard images in the same form. The classification network structure can be understood as a part of a network structure in a classification network model, and can be formed by adding an activation layer after a full connection layer of the last layer in a DenseNet121 structure, so as to convert the output of an i-dimensional array of the full connection layer into the output of an i-bit probability array. The probability value of the cloud class label can be understood as the probability value of each preset cloud class appearing in the cloud image.
In the embodiment of the invention, before the cloud classification model is converged, the training cloud image needs to be input into the cloud classification model for verification, so as to obtain the cloud type identified by inputting the training cloud image into the cloud classification model. And comparing the cloud type recognized in the cloud classification model with the cloud type corresponding to the training cloud image label to judge the usability of the cloud classification model.
Further, before determining the cloud class corresponding to the training cloud image according to the probability value of the cloud class label corresponding to the training cloud image and the threshold value corresponding to each cloud class, the method further includes:
determining a probability value corresponding to the cloud type in the training cloud image according to the classification network structure;
and determining a threshold value corresponding to each cloud class according to the training cloud image, the probability value corresponding to the cloud class in the training cloud image and the cloud class corresponding to the training cloud image label.
In the embodiment of the present invention, the threshold corresponding to each cloud category may be understood as a threshold of a probability value corresponding to each cloud category in the cloud image.
In the embodiment of the invention, after the marked training cloud images and cloud class labels are input into the cloud classification model to be trained, the marked training cloud images and cloud class labels are input into the classification network structure to obtain the probability value corresponding to the cloud class in the training cloud images. And comparing and selecting the probability value corresponding to the cloud type in the training cloud image with the cloud type in the training cloud image, and selecting the probability value with the highest accuracy as the threshold corresponding to each cloud type for each cloud type.
Step S230, if it is monitored that the cloud image has accumulated rain clouds, inputting the cloud image in a preset time period, the cloud type in the cloud image and weather parameters into a pre-trained decision tree, wherein the decision tree is obtained by training according to a training cloud image in the preset time period before the convective weather is stopped, the cloud type in the training cloud image and the weather parameters;
and step S240, if the prediction result output by the decision tree is rain stop, the convection cloud cluster early warning state is released.
The process of warning cancellation can be realized in various ways, specifically:
fig. 2A is a schematic flowchart of an early warning cancellation method in the second embodiment of the present invention, and as shown in fig. 2A, when a cloud image of convective weather is monitored, the cloud image of convective weather is acquired in real time. And after normalization processing is carried out on the obtained cloud image of the convection cloud weather, the cloud image is input into a pre-trained cloud classification model. After the cloud type in the cloud image of the convection cloud weather is identified according to the pre-trained cloud classification model, whether the rain cloud is accumulated in the cloud type in the cloud image of the convection cloud weather is judged, and if the rain cloud is accumulated, the early warning release time needs to be predicted for the convection cloud weather. Collecting the cloud images in the preset time period, inputting the cloud images in the preset time period into a pre-trained cloud classification model to identify the cloud type in the cloud images, and inputting the identified cloud images in the preset time period, the cloud type in the cloud images and weather parameters into a pre-trained decision tree to obtain a prediction result.
After entering a convection cloud early warning state, the cloud image of convection weather is monitored; if the cloud image is monitored to have accumulated rain clouds, inputting the cloud image in a preset time period, the cloud type in the cloud image and weather parameters into a pre-trained decision tree, wherein the decision tree is obtained by training according to a training cloud image in the preset time period before the convective weather rain is stopped, the cloud type in the training cloud image and the weather parameters; and if the prediction result output by the decision tree is rain stop, removing the convection cloud cluster early warning state. The method solves the problems that most of the prediction on the formation and the dissipation of the convection cloud cluster is carried out by means of a radar echo map, the economic cost is high, and the popularization rate is low, and the early warning state of the convection cloud cluster is relieved in real time according to the cloud image, so that the rain stop time is accurately predicted, and the accurate time effect of relieving the large-area delay early warning of flights is determined.
EXAMPLE III
Fig. 3 is a schematic structural diagram of an early warning cancellation device in the third embodiment of the present invention. The device includes: an early warning monitoring module 310, a cloud analysis module 320 and an early warning cancellation module 330;
the early warning monitoring module 310 is configured to monitor a cloud image of the convective weather after entering a convective cloud early warning state;
the cloud analysis module 320 is configured to, if it is monitored that a raining cloud occurs in the cloud image, input the cloud image within a preset time period, the type of cloud in the cloud image, and a weather parameter into a pre-trained decision tree, where the decision tree is obtained by training a training cloud image within a preset time period before a convective weather rain is stopped, the type of cloud in the training cloud image, and a weather parameter;
the early warning releasing module 330 is configured to release the convective cloud cluster early warning state if the prediction result output by the decision tree is rain-down.
Further, the cloud analysis module 320 specifically uses:
inputting training cloud images in a preset time before the convective weather is stopped for a preset number of times, the cloud types in the training cloud images and weather parameters into a deep learning model, and training a decision tree to be trained.
Further, the early warning monitoring module 310 is specifically configured to:
monitoring a cloud image of convective weather through a pre-trained cloud classification model;
the acquisition mode of the cloud classification model comprises the following steps:
acquiring a cloud image to be trained;
and training the deep learning classification network for preset times according to the cloud image to be trained until the deep learning classification network is converged to obtain the cloud classification model.
Further, the early warning monitoring module 310 is further specifically configured to:
inputting the normalized training cloud image into a classification network structure, and determining a probability value of a cloud type corresponding to the training cloud image;
and determining the cloud category corresponding to the training cloud image according to the probability value of the cloud category corresponding to the training cloud image and the threshold value corresponding to each cloud category.
Further, the early warning monitoring module 310 is further specifically configured to:
determining a probability value corresponding to the cloud type in the training cloud image according to the classification network structure;
and determining a threshold value corresponding to each cloud class according to the training cloud image, the probability value corresponding to the cloud class in the training cloud image and the cloud class corresponding to the training cloud image label.
Further, the early warning monitoring module 310 is further specifically configured to:
performing non-deformation scaling on the training cloud image;
correspondingly adding cloud class labels to the zoomed training cloud images according to preset cloud classes;
and storing the cloud class label corresponding to the training cloud image in association with the training cloud image.
Further, the warning cancellation module 330 is specifically configured to:
and if no rain cloud or cloud layered cloud exists in the cloud category corresponding to the cloud image, the air pressure is increased, and the air speed is reduced, the prediction result is rain stop.
The early warning cancellation device provided by the embodiment of the invention can execute the early warning cancellation method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of an electronic device according to embodiment 4 of the present invention. FIG. 4 illustrates a block diagram of an exemplary electronic device 12 suitable for use in implementing embodiments of the present invention. The electronic device 12 shown in fig. 4 is only an example and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.
As shown in FIG. 4, electronic device 12 is embodied in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, and commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, implementing an alarm cancellation method provided by an embodiment of the present invention, the method including:
monitoring a cloud image of convection weather after entering a convection cloud early warning state;
if the cloud image is monitored to have accumulated rain clouds, inputting the cloud image in a preset time period, the cloud type in the cloud image and weather parameters into a pre-trained decision tree, wherein the decision tree is obtained by training according to a training cloud image in the preset time period before the convective weather rain is stopped, the cloud type in the training cloud image and the weather parameters;
and if the prediction result output by the decision tree is rain stop, removing the convection cloud cluster early warning state.
EXAMPLE five
An embodiment of the present invention further provides a storage medium including computer-executable instructions, which when executed by a computer processor, perform an early warning cancellation method, including:
monitoring a cloud image of convection weather after entering a convection cloud early warning state;
if the cloud image is monitored to have accumulated rain clouds, inputting the cloud image in a preset time period, the cloud type in the cloud image and weather parameters into a pre-trained decision tree, wherein the decision tree is obtained by training according to a training cloud image in the preset time period before the convective weather rain is stopped, the cloud type in the training cloud image and the weather parameters;
and if the prediction result output by the decision tree is rain stop, removing the convection cloud cluster early warning state.
Computer storage media for embodiments of the invention may employ any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, or the like, as well as conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. An early warning cancellation method, comprising:
monitoring a cloud image of convection weather after entering a convection cloud early warning state;
if the cloud image is monitored to have accumulated rain clouds, inputting the cloud image in a preset time period, the cloud type in the cloud image and weather parameters into a pre-trained decision tree, wherein the decision tree is obtained by training according to a training cloud image in the preset time period before the convective weather rain is stopped, the cloud type in the training cloud image and the weather parameters;
and if the prediction result output by the decision tree is rain stop, removing the convection cloud cluster early warning state.
2. The method of claim 1, wherein the decision tree is trained according to a training cloud image in a preset time period before a convective weather rain break, a type of cloud in the training cloud image, and weather parameters, and comprises:
inputting training cloud images in a preset time before the convective weather is stopped for a preset number of times, the cloud types in the training cloud images and weather parameters into a deep learning model, and training a decision tree to be trained.
3. The method of claim 1, wherein prior to monitoring the cloud image of convective weather, further comprising:
monitoring a cloud image of convective weather through a pre-trained cloud classification model;
the cloud classification model obtaining method comprises the following steps:
acquiring a cloud image to be trained;
and training the deep learning classification network for preset times according to the cloud image to be trained until the deep learning classification network is converged to obtain the cloud classification model.
4. The method of claim 3, wherein the acquiring a cloud image to be trained; according to the cloud image to be trained, training a deep learning classification network for a preset number of times until the deep learning classification network converges to obtain the cloud classification model, the method further comprises the following steps:
inputting the normalized training cloud image into a classification network structure, and determining a probability value of a cloud type corresponding to the training cloud image;
and determining the cloud category corresponding to the training cloud image according to the probability value of the cloud category corresponding to the training cloud image and the threshold value corresponding to each cloud category.
5. The method of claim 4, wherein before determining the cloud class corresponding to the training cloud image according to the probability value of the cloud class label corresponding to the training cloud image and the threshold value corresponding to each cloud class, the method further comprises:
determining a probability value corresponding to the cloud type in the training cloud image according to the classification network structure;
and determining a threshold value corresponding to each cloud class according to the training cloud image, the probability value corresponding to the cloud class in the training cloud image and the cloud class corresponding to the training cloud image label.
6. The method according to claim 2, wherein the inputting the training cloud images, the cloud types in the training cloud images, and the weather parameters within a preset time before the convective weather rain stops for a preset number of times into the deep learning model further comprises, before training the decision tree to be trained:
performing non-deformation scaling on the training cloud image;
correspondingly adding cloud class labels to the zoomed training cloud images according to preset cloud classes;
and storing the cloud class label corresponding to the training cloud image in association with the training cloud image.
7. The method of claim 1, wherein the predicted outcome of the decision tree output is a rain stop, comprising:
and if no rain cloud or cloud layered cloud exists in the cloud category corresponding to the cloud image, the air pressure is increased, and the air speed is reduced, the prediction result is rain stop.
8. An advance warning cancellation apparatus, characterized by comprising:
the early warning monitoring module is used for monitoring a cloud image of convection weather after entering a convection cloud early warning state;
the cloud-shaped analysis module is used for inputting the cloud-shaped image in a preset time period, the type of cloud in the cloud-shaped image and the weather parameters into a pre-trained decision tree if it is monitored that the cloud-shaped image has accumulated rain clouds, and the decision tree is obtained by training according to a training cloud-shaped image in the preset time period before the convective weather rain is stopped, the type of cloud in the training cloud-shaped image and the weather parameters;
and the early warning removing module is used for removing the early warning state of the convection cloud cluster if the prediction result output by the decision tree is rain stop.
9. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a storage device for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the warning cancellation method of any one of claims 1-7.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the warning cancellation method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011364754.7A CN112330069A (en) | 2020-11-27 | 2020-11-27 | Early warning removing method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011364754.7A CN112330069A (en) | 2020-11-27 | 2020-11-27 | Early warning removing method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112330069A true CN112330069A (en) | 2021-02-05 |
Family
ID=74309669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011364754.7A Pending CN112330069A (en) | 2020-11-27 | 2020-11-27 | Early warning removing method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112330069A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100100328A1 (en) * | 2008-06-17 | 2010-04-22 | Moore John S | System and Method for Generating a Cloud Type and Coverage Prediction Database |
| CN109992367A (en) * | 2017-12-29 | 2019-07-09 | 广东欧珀移动通信有限公司 | Application processing method and device, electronic equipment, computer readable storage medium |
| CN110752942A (en) * | 2019-09-06 | 2020-02-04 | 平安科技（深圳）有限公司 | Alarm information decision method and device, computer equipment and storage medium |
| CN111340093A (en) * | 2020-02-21 | 2020-06-26 | 上海眼控科技股份有限公司 | Cloud identification method and device |
| CN111507399A (en) * | 2020-04-16 | 2020-08-07 | 上海眼控科技股份有限公司 | Cloud recognition and model training method, device, terminal and medium based on deep learning |
| CN111553541A (en) * | 2020-05-15 | 2020-08-18 | 航迅信息技术有限公司 | System and method for predicting weather based on image |
| CN111932519A (en) * | 2020-08-12 | 2020-11-13 | 上海眼控科技股份有限公司 | Weather prediction method and device, computer equipment and storage medium |
-
2020
- 2020-11-27 CN CN202011364754.7A patent/CN112330069A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100100328A1 (en) * | 2008-06-17 | 2010-04-22 | Moore John S | System and Method for Generating a Cloud Type and Coverage Prediction Database |
| CN109992367A (en) * | 2017-12-29 | 2019-07-09 | 广东欧珀移动通信有限公司 | Application processing method and device, electronic equipment, computer readable storage medium |
| CN110752942A (en) * | 2019-09-06 | 2020-02-04 | 平安科技（深圳）有限公司 | Alarm information decision method and device, computer equipment and storage medium |
| CN111340093A (en) * | 2020-02-21 | 2020-06-26 | 上海眼控科技股份有限公司 | Cloud identification method and device |
| CN111507399A (en) * | 2020-04-16 | 2020-08-07 | 上海眼控科技股份有限公司 | Cloud recognition and model training method, device, terminal and medium based on deep learning |
| CN111553541A (en) * | 2020-05-15 | 2020-08-18 | 航迅信息技术有限公司 | System and method for predicting weather based on image |
| CN111932519A (en) * | 2020-08-12 | 2020-11-13 | 上海眼控科技股份有限公司 | Weather prediction method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112037266B (en) | Falling object identification method and device, terminal equipment and storage medium | |
| CN113486938B (en) | Multi-branch time convolution network-based re-landing analysis method and device | |
| CN109935080B (en) | Monitoring system and method for real-time calculation of traffic flow on traffic line | |
| CN110362907B (en) | SSD neural network-based power transmission line target defect identification and diagnosis method | |
| Wang et al. | Modeling weather impact on ground delay programs | |
| CN113177968A (en) | Target tracking method and device, electronic equipment and storage medium | |
| CN115857059B (en) | Ice accumulation forecast management method, system, readable storage medium and device | |
| CN114120650A (en) | Method and device for generating test result | |
| CN115471487A (en) | Insulator defect detection model construction and insulator defect detection method and device | |
| US20200074559A1 (en) | System and a method for computing infrastructural damages | |
| CN110705759A (en) | Water level early warning monitoring method and device, storage medium and electronic equipment | |
| CN112559371A (en) | Automatic driving test method and device and electronic equipment | |
| CN115359471A (en) | Image processing and joint detection model training method, device, equipment and storage medium | |
| CN114594532A (en) | Method and device for predicting cold weather, electronic equipment and computer readable medium | |
| US20220198641A1 (en) | Tree fall management | |
| CN115508917B (en) | Airport weather element forecasting method, device, equipment and storage medium | |
| CN112330069A (en) | Early warning removing method and device, electronic equipment and storage medium | |
| CN113313962A (en) | Signal lamp fault monitoring method and device, electronic equipment and storage medium | |
| CN116736409A (en) | Automobile safety early warning method, device, equipment and storage medium | |
| CN115294048A (en) | Foreign matter detection method, device, equipment and storage medium | |
| CN115293366A (en) | Model training method, information prediction method, device, equipment and medium | |
| CN115083229A (en) | Intelligent recognition and warning system of flight training equipment based on AI visual recognition | |
| CN114859864A (en) | Vehicle testing method, device, equipment and storage medium | |
| CN113657287A (en) | Target detection method based on deep learning improved YOLOv3 | |
| CN114120208A (en) | Flame detection method, device, equipment and storage medium |
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 |