CN113610304A - Congestion prediction method, device, equipment and storage medium - Google Patents
Congestion prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113610304A CN113610304A CN202110918699.XA CN202110918699A CN113610304A CN 113610304 A CN113610304 A CN 113610304A CN 202110918699 A CN202110918699 A CN 202110918699A CN 113610304 A CN113610304 A CN 113610304A
- Authority
- CN
- China
- Prior art keywords
- current
- congestion prediction
- congestion
- flow rate
- monitoring node
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 238000012544 monitoring process Methods 0.000 claims abstract description 123
- 238000012549 training Methods 0.000 claims abstract description 12
- 230000001105 regulatory effect Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 8
- 230000003287 optical effect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000033764 rhythmic process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012805 post-processing 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
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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a congestion prediction method, a congestion prediction device, congestion prediction equipment and a congestion prediction storage medium, wherein the method comprises the following steps: determining current parcel flow rate information corresponding to each inlet of a sorting device; inputting the current parcel flow velocity information into a preset congestion prediction model, and determining a current congestion prediction result corresponding to each monitoring node in the sorting device according to the output of the preset congestion prediction model; the preset congestion prediction model is obtained in advance based on sample data training. By the technical scheme of the embodiment of the invention, the congestion condition can be predicted in advance, so that congestion can be processed in advance, and the sorting efficiency is effectively improved.
Description
Technical Field
Embodiments of the present invention relate to computer technologies, and in particular, to a congestion prediction method, apparatus, device, and storage medium.
Background
Along with the rapid development of scientific technology, more and more automatic equipment is applied to the letter sorting center to improve letter sorting efficiency.
Generally, the sorting centers have a large number of parcels to be handled and the capacity of the sorting devices is limited, which can cause congestion in certain areas of the conveyor belt, greatly affecting the sorting efficiency, and even causing late points of transportation and distribution. In order to deal with the condition of the conveyor belt congestion, the congestion condition of a monitoring node is identified by using a sensor or a computer vision mode at present, and once the congestion is found, the congestion is eliminated by using an artificial means.
However, in the process of implementing the invention, at least the following problems are found in the prior art:
in the existing mode, when congestion occurs, recognition is carried out, and then manual processing is carried out. Therefore, certain loss is caused by congestion during manual processing, so that the sorting efficiency is influenced by the post-processing mode, and the sorting efficiency cannot be effectively improved.
Disclosure of Invention
The embodiment of the invention provides a congestion prediction method, a congestion prediction device, congestion prediction equipment and a storage medium, which are used for realizing the prediction of congestion conditions in advance and facilitating the follow-up processing of congestion in advance, thereby effectively improving the sorting efficiency.
In a first aspect, an embodiment of the present invention provides a congestion prediction method, including:
determining current parcel flow rate information corresponding to each inlet of a sorting device;
inputting the current parcel flow velocity information into a preset congestion prediction model, and determining a current congestion prediction result corresponding to each monitoring node in the sorting device according to the output of the preset congestion prediction model;
the preset congestion prediction model is obtained in advance based on sample data training.
In a second aspect, an embodiment of the present invention further provides a congestion prediction apparatus, including:
the current parcel flow rate information determining module is used for determining current parcel flow rate information corresponding to each inlet of the sorting device;
the current congestion prediction result determining module is used for inputting the current parcel flow rate information into a preset congestion prediction model and determining a current congestion prediction result corresponding to each monitoring node in the sorting device according to the output of the preset congestion prediction model;
the preset congestion prediction model is obtained in advance based on sample data training.
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 memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a congestion prediction method as provided by any of the embodiments of the invention.
In a fourth aspect, embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements a congestion prediction method as provided in any of the embodiments of the present invention.
The embodiment of the invention has the following advantages or beneficial effects:
the current package flow speed information corresponding to each inlet of the sorting device is input into the preset congestion prediction model, and the current congestion prediction result corresponding to each monitoring node in the sorting device can be determined according to the output of the preset congestion prediction model, so that the congestion condition can be predicted in advance, the congestion can be processed in advance, and the sorting efficiency is effectively improved.
Drawings
Fig. 1 is a flowchart of a congestion prediction method according to an embodiment of the present invention;
fig. 2 is a flowchart of a congestion prediction method according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a congestion prediction apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to 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 a congestion prediction method according to an embodiment of the present invention, which is applicable to a case where congestion conditions in sorting equipment are predicted in advance. The method may be performed by a congestion prediction apparatus, which may be implemented by software and/or hardware, integrated in an electronic device. As shown in fig. 1, the method specifically includes the following steps:
and S110, determining current parcel flow rate information corresponding to each inlet of the sorting device.
Wherein the sorting device can correspond to a plurality of inlets. Each portal may correspond to a scanning device for scanning information about the package. And scanning the packages to be sorted by the scanning device and then placing the packages to the corresponding inlets. The conveyors in the sorting apparatus may route packages at the inlets to respective outlets to complete the sorting operation. The current parcel flow rate information for each portal may refer to the scanned frequency of parcels at each portal, characterizing the frequency at which each portal delivers parcels.
Specifically, by the scanning device, the scanning information corresponding to each parcel scanned by each entrance is obtained, and the current parcel flow rate information corresponding to each entrance is determined based on the scanning information. For example, for each portal, the scanning time corresponding to each parcel currently scanned by the portal may be obtained, and based on these scanning times, the total number of parcels scanned in a preset time period may be determined as the current parcel flow rate information corresponding to the portal. For example, the total number of parcels scanned in the last minute is taken as the current parcel flow rate for that portal.
S120, inputting the current parcel flow rate information into a preset congestion prediction model, and determining a current congestion prediction result corresponding to each monitoring node in the sorting device according to the output of the preset congestion prediction model; the preset congestion prediction model is obtained in advance based on sample data training.
The preset congestion prediction model may be a deep neural network model for predicting congestion conditions. For example, the preset congestion prediction model may be any two-class network model. The monitoring nodes can refer to the conveyor belt nodes needing to be monitored in the sorting device, and the specific positions and the number of the monitoring nodes can be determined based on the service demands and actual scenes. For example, each node on the conveyor belt that is most often congested may be considered a monitoring node. The current congestion prediction result may include both a congestion state prediction result and a non-congestion state prediction result. The congestion state may refer to a state in which it is predicted that the monitoring node will be congested. The non-congestion state may refer to a state in which it is predicted that the monitoring node will not be congested.
Specifically, the current parcel flow rate information corresponding to all the entrances can be input into a trained preset congestion prediction model for congestion prediction, and a current congestion prediction result corresponding to each monitoring node is determined according to the output of the preset congestion prediction model. For example, an input vector X ═ X of a preset congestion prediction model is determined according to the current parcel flow rate X corresponding to each entrance1，x2，...，xM]Wherein M is the inlet number of the sorting device. Correspondingly, the output vector of the preset congestion prediction model is as follows: y ═ Y1，y2，...，yS]And S is the number of monitoring nodes of the sorting device, and y is the probability of congestion of each monitoring node. The method and the device can detect whether the probability of congestion of each monitoring node is greater than the preset probability, if so, the current congestion prediction result corresponding to the monitoring node is determined to be in a congestion state, and if not, the current congestion prediction result corresponding to the monitoring node is determined to be in a non-congestion state, so that the congestion condition of each monitoring node can be predicted in advance, congestion can be processed in advance in the subsequent process, and therefore the sub-rate is effectively improvedThe picking efficiency is improved.
The preset congestion prediction model in this embodiment is a model trained on sample data in advance. The predetermined congestion prediction model may be represented by a deep neural network f (·): y ═ f (x). Sample data for training the preset congestion prediction model f (-) can be obtained from actual production. For example, the inputs to the sorting device and the congestion at each monitoring node are sampled at time node T e {1, 2tThe output is Yt. For these samples, since it is known whether each monitoring node is congested, YtEach position in (a) has a value of 0 or 1. The network parameters of the preset congestion prediction model f (-) can be subjected to model training based on the T collected training samples by using a random gradient descent mode, and a preset congestion prediction model which can be used for predicting congestion conditions is obtained.
According to the technical scheme, the current package flow speed information corresponding to each inlet of the sorting device is input into the preset congestion prediction model, and the current congestion prediction result corresponding to each monitoring node in the sorting device can be determined according to the output of the preset congestion prediction model, so that the congestion condition can be predicted in advance, congestion can be processed in advance, and the sorting efficiency is effectively improved.
On the basis of the above technical solution, S110 may include: acquiring scanning time corresponding to each parcel in a preset number of parcels recently scanned by an entrance aiming at each entrance; and determining the current parcel flow rate information corresponding to the inlet according to the scanning time corresponding to each parcel.
Specifically, for each entrance, the scanning time of each scanned package in the latest preset number of packages may be obtained from the scanning device, and the current package flow rate information corresponding to the entrance may be determined based on the scanning time corresponding to the latest scanned packages in the same number. For example, the scanning time interval between the first parcel and the last parcel in the most recently scanned preset number of parcels may be determined as the current parcel flow rate information corresponding to the entrance.
For example, determining the current parcel flow rate information for the portal according to the scan time corresponding to each parcel may include: determining the scanning time interval between every two adjacent parcels according to the scanning time corresponding to each parcel; and averaging each scanning time interval to obtain the current parcel flow rate information corresponding to the entrance.
Specifically, for the preset number of packages scanned most recently, the scanning time interval between every two adjacent packages can be obtained by subtracting the scanning time of the previous package from the scanning time of the next package. And adding all the obtained scanning time intervals, and dividing by the total number of the scanning time intervals to obtain a division result as the current parcel flow rate corresponding to the entrance. For example, the time interval between the kth portal scanning the ith parcel and the (i + 1) th parcel is
Then the current parcel flow rate for the kth inlet is:
n is a preset number. When the (N + 1) th parcel in the kth entrance is scanned, the current parcel flow rate corresponding to the kth entrance is updated as:
therefore, the accuracy of congestion prediction can be ensured by updating the parcel flow rate in real time. In the embodiment, the moving average value of the N parcels is used as the parcel flow rate corresponding to the inlet, so that the parcel flow rate can be represented more accurately, and the accuracy of congestion prediction is further ensured.
Example two
Fig. 2 is a flowchart of a congestion prediction method according to a second embodiment of the present invention, and in this embodiment, based on the foregoing embodiments, an ingress flow rate of a target monitoring node whose current congestion prediction result is a congestion state is adjusted, so as to avoid congestion occurring in the target monitoring node. Wherein explanations of the same or corresponding terms as those of the above embodiments are omitted.
Referring to fig. 2, the congestion prediction method provided in this embodiment specifically includes the following steps:
s210, determining current parcel flow rate information corresponding to each inlet of the sorting device.
S220, inputting the current parcel flow rate information into a preset congestion prediction model, and determining a current congestion prediction result corresponding to each monitoring node in the sorting device according to the output of the preset congestion prediction model.
And S230, taking the monitoring node with the current congestion prediction result in the congestion state as a target monitoring node.
The target monitoring node may be a monitoring node that currently needs to adjust the inlet flow rate to avoid a congestion condition. Specifically, in this embodiment, each monitoring node whose current congestion prediction result is a congestion state, that is, each monitoring node predicted to be congested, may be obtained, and any monitoring node may be used as a target monitoring node to adjust an inlet flow rate.
Illustratively, S230 may include: if at least two monitoring nodes with the current congestion prediction results in the congestion state exist, acquiring the congestion prediction probability corresponding to each monitoring node with the current congestion prediction results in the congestion state; and taking the monitoring node with the maximum congestion prediction probability as a target monitoring node.
Specifically, the monitoring node with the maximum congestion prediction probability is used as the target monitoring node, so that the monitoring node which is most likely to be congested can be preferentially adjusted to preferentially avoid congestion of the monitoring node, and therefore the sorting efficiency is effectively improved. If a plurality of monitoring nodes with the same congestion prediction probability exist, one monitoring node can be randomly selected as a target monitoring node.
S240, determining a weight value of congestion influence of each entrance on the target monitoring node.
The weighted value is used for representing the influence of congestion caused by the entrance to the target monitoring node.
The packages in this embodiment will typically have different destinations after the packages have been sorted from different entrances, and thus the packages will also have different flow directions in the sorting apparatus. Thus, although the flow rate of packages at the inlets is relatively fast, packages from the inlets to the sorting device will not pass through certain monitoring nodes, and thus congestion at the monitoring nodes will not be affected. Moreover, a plurality of entrances may cause congestion of the same monitoring node, but the influence is not necessarily the same, so that when a certain monitoring node is congested, flow rate regulation needs to be performed from the entrance capable of influencing the monitoring node, and regulation can be performed successively based on the influence degree, so that the congestion condition can be fundamentally solved, congestion of a subsequent target monitoring node is avoided, and sorting efficiency is effectively guaranteed.
Specifically, the preset congestion prediction model is a highly nonlinear complex model, but according to taylor series expansion, a linear component can be fitted in each local area, and the relation between each input dimension and each output dimension can be visually described, so that the embodiment can perform linear fitting by using a KernelSHAP method in interpretable machine learning, and determine the weight value of congestion influence of each entrance on the target monitoring node according to the fitting result.
Exemplarily, S240 may include: randomly generating parcel flow velocity sample information in the vicinity of each current parcel flow velocity information input into a preset congestion prediction model; the method comprises the steps of inputting wrapping flow rate sample information into a preset congestion prediction model, and obtaining a sample congestion prediction probability corresponding to a target monitoring node according to the output of the preset congestion prediction model; and performing linear fitting according to the package flow rate sample information and the corresponding sample congestion prediction probability, and determining the weight value of each inlet causing congestion influence on the target monitoring node according to the fitted linear model.
Specifically, the current input vector X ═ X of the preset congestion prediction model may be used as the input vector X1，x2，...，xM]As a center, a plurality of parcel flow velocity samples are randomly generated in a nearby area with a preset length as a radius, each parcel flow velocity sample is input into a preset congestion prediction model for congestion prediction, and a sample congestion prediction probability corresponding to a target monitoring node output by the preset congestion prediction model is obtained, so that the congestion prediction model can be generatedAnd obtaining sample data of the current parcel flow velocity local area. Carrying out linear fitting on each parcel flow velocity sample and the corresponding sample congestion prediction probability to obtain a linear model corresponding to a target monitoring node, namely y ═ sigmaiφiX(i)+φ0And the absolute value of the coefficient of each feature in the linear model represents the influence of the corresponding entrance on the target monitoring node. In the Kernel SHAP method,. phiiAnd i > 0 is the Shap value of the ith entry, and the absolute value of the Shap value is the weight value of the influence of the ith entry on the target monitoring node. By utilizing the linear fitting mode, the influence of each inlet of the sorting device on the congestion of the target monitoring node can be accurately evaluated.
And S250, adjusting the current package flow rate of the entrance according to the weight value corresponding to each entrance so as to enable the current congestion prediction result corresponding to the target monitoring node to be in a non-congestion state.
Specifically, the flow rate of the inlet causing large influence can be adjusted based on the weight value corresponding to each inlet, and the feeding rhythm is slowed down, so that congestion at the target monitoring node can be fundamentally avoided, and the sorting efficiency is effectively improved. Compared with the mode of manually dredging the monitoring nodes with congestion in the prior art, the method has the advantages that the fundamental problem of congestion can be solved by adjusting the inlet sorting rhythm, congestion is prevented from happening again, and sorting efficiency is effectively guaranteed.
Illustratively, S250 may include: determining a current regulation entrance according to the weight value corresponding to each entrance; and adjusting the current parcel flow rate of the current adjusting inlet according to the minimum parcel flow rate information corresponding to the current adjusting inlet so as to enable the current congestion prediction result corresponding to the target monitoring node to be in a non-congestion state.
The speed cannot be too slow due to certain time requirements when the vehicle is unloaded, so that each inlet corresponds to a minimum parcel flow rate, namely a lower limit value of the parcel flow rate. Specifically, one entry having a weight value greater than zero may be taken as the current adjustment entry. The method and the device can gradually reduce the current parcel flow rate of the current regulation inlet by a preset step length on the premise of ensuring that the current parcel flow rate of the current regulation inlet is greater than or equal to the minimum parcel flow rate, and input the reduced current parcel flow rate and the current parcel flow rates of other inlets into a preset congestion prediction model for carrying out congestion prediction again after reducing the current parcel flow rate of the current regulation inlet each time, and directly till the current congestion prediction result corresponding to the target monitoring node is in a non-congestion state, namely the probability of congestion of the target monitoring node is less than or equal to the preset probability. The flow rate of only the entrance with influence on the congestion of the target monitoring node is adjusted, and the unrelated entrance does not need to be adjusted, so that the fundamental problem of congestion can be solved, the congestion is prevented from happening again, and the sorting efficiency is effectively improved.
For example, determining the current adjustment entry according to the weight value corresponding to each entry may include: and sequencing the weight value corresponding to each entrance, and determining the entrance with the largest weight value as the current regulation entrance.
Specifically, all the entries may be sorted in the order of the weighted values from large to small, and the first entry after sorting is used as the current regulation entry, so that the flow rate regulation may be preferentially performed on the entry having the largest influence, thereby solving the predicted congestion problem of the target monitoring node as soon as possible and preventing the congestion condition of the target monitoring node from being predicted again.
Illustratively, adjusting the current parcel flow rate of the current adjusting entrance according to the minimum parcel flow rate information corresponding to the current adjusting entrance so that the current congestion prediction result corresponding to the target monitoring node is in a non-congestion state may include: and if the current package flow rate of the current regulation inlet is regulated to the corresponding minimum package flow rate, and the current congestion prediction result corresponding to the target monitoring node is still in a congestion state, determining a next regulation inlet, and regulating the current package flow rate of the next regulation inlet based on the minimum package flow rate information corresponding to the next regulation inlet until the congestion prediction result corresponding to the target monitoring node is in a non-congestion state.
Specifically, when the current parcel flow rate of the current regulation inlet is regulated to the corresponding minimum parcel flow rate, the current congestion prediction result corresponding to the target monitoring node is still in a congestion state (that is, the probability of congestion occurring at the target monitoring node is greater than the preset probability), the current parcel flow rate of the current regulation inlet can be regulated to the corresponding minimum parcel flow rate and kept unchanged, the second inlet is used as the next regulation inlet according to the inlet sorting, that is, the inlet which affects the target monitoring node the second time is used as the next regulation inlet, the current parcel flow rate of the next regulation inlet is regulated according to the similar regulation mode based on the minimum parcel flow rate information corresponding to the next regulation inlet, and so on until the congestion prediction result corresponding to the target monitoring node is in a non-congestion state.
It should be noted that, in an actual application environment, the preset congestion prediction model cannot guarantee complete accuracy, and a missed detection situation may occur, so that congestion detection may be performed on each monitoring node in the sorting device in a computer vision manner at the same time, so as to find out in time that the preset congestion prediction model predicts a monitoring node that is not congested but is actually congested. For such a situation, the currently congested monitoring node may be used as a target monitoring node, the current parcel flow rate of each entrance may be obtained to determine an input vector X, the label y (S) corresponding to the target monitoring node is set to 1, and the entrance flow rate operations in the steps S240 to S250 are performed, so that the fundamental problem of congestion can be solved, the subsequent congestion situation of the target monitoring node is avoided, and the sorting efficiency is effectively ensured.
According to the technical scheme, the weight value of congestion influence caused by the fact that each entrance has congestion on the target monitoring node of which the current congestion prediction result is in the congestion state is determined, the current wrapping flow rate of the entrance is adjusted according to the weight value corresponding to each entrance, the current congestion prediction result corresponding to the target monitoring node is in the non-congestion state, the problem of the root cause of congestion is solved by adjusting the sorting rhythm of the entrance, congestion is prevented from happening again, and sorting efficiency is effectively guaranteed.
The following is an embodiment of a congestion prediction apparatus provided in an embodiment of the present invention, which belongs to the same inventive concept as the congestion prediction methods in the above embodiments, and reference may be made to the above embodiment of the congestion prediction method for details that are not described in detail in the embodiment of the congestion prediction apparatus.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a congestion prediction apparatus according to a third embodiment of the present invention, where the present embodiment is applicable to a case where congestion conditions in sorting equipment are predicted in advance, the apparatus specifically includes: a current parcel flow rate information determination module 310 and a current congestion prediction result determination module 320.
The current parcel flow rate information determining module 310 is configured to determine current parcel flow rate information corresponding to each inlet of the sorting apparatus; the current congestion prediction result determining module 320 is configured to input information of each current parcel flow rate into a preset congestion prediction model, and determine a current congestion prediction result corresponding to each monitoring node in the sorting apparatus according to an output of the preset congestion prediction model; the preset congestion prediction model is obtained in advance based on sample data training.
Optionally, the current parcel flow rate information determination module 310 includes:
the scanning time acquisition unit is used for acquiring the scanning time corresponding to each parcel in a preset number of parcels recently scanned by the entrance aiming at each entrance;
and the current parcel flow rate information determining unit is used for determining current parcel flow rate information corresponding to the entrance according to the scanning time corresponding to each parcel.
Optionally, the current parcel flow rate information determining unit is specifically configured to: determining the scanning time interval between every two adjacent parcels according to the scanning time corresponding to each parcel; and averaging each scanning time interval to obtain the current parcel flow rate information corresponding to the entrance.
Optionally, the apparatus further comprises:
the target monitoring node determining module is used for determining a current congestion prediction result corresponding to each monitoring node in the sorting device, and then taking the monitoring node with the current congestion prediction result in a congestion state as a target monitoring node;
the weight value determining module is used for determining the weight value of each entrance which causes congestion influence on the target monitoring node;
and the flow rate adjusting module is used for adjusting the current package flow rate of the entrance according to the weight value corresponding to each entrance so as to enable the current congestion prediction result corresponding to the target monitoring node to be in a non-congestion state.
Optionally, the target monitoring node determining module is specifically configured to: if at least two monitoring nodes with the current congestion prediction results in the congestion state exist, acquiring the congestion prediction probability corresponding to each monitoring node with the current congestion prediction results in the congestion state; and taking the monitoring node with the maximum congestion prediction probability as a target monitoring node.
Optionally, the weight value determining module is specifically configured to: randomly generating parcel flow velocity sample information in the vicinity of each current parcel flow velocity information input into a preset congestion prediction model; the method comprises the steps of inputting wrapping flow rate sample information into a preset congestion prediction model, and obtaining a sample congestion prediction probability corresponding to a target monitoring node according to the output of the preset congestion prediction model; and performing linear fitting according to the package flow rate sample information and the corresponding sample congestion prediction probability, and determining the weight value of each inlet causing congestion influence on the target monitoring node according to the fitted linear model.
Optionally, the flow rate adjustment module comprises:
a current regulation entrance determining unit, configured to determine a current regulation entrance according to a weight value corresponding to each entrance;
and the flow rate adjusting unit is used for adjusting the current parcel flow rate of the current adjusting inlet according to the minimum parcel flow rate information corresponding to the current adjusting inlet so as to enable the current congestion prediction result corresponding to the target monitoring node to be in a non-congestion state.
Optionally, the current adjustment entry determining unit is specifically configured to: and sequencing the weight value corresponding to each entrance, and determining the entrance with the largest weight value as the current regulation entrance.
Optionally, the flow rate regulating unit is specifically configured to: and if the current package flow rate of the current regulation inlet is regulated to the corresponding minimum package flow rate, and the current congestion prediction result corresponding to the target monitoring node is still in a congestion state, determining a next regulation inlet, and regulating the current package flow rate of the next regulation inlet based on the minimum package flow rate information corresponding to the next regulation inlet until the congestion prediction result corresponding to the target monitoring node is in a non-congestion state.
The congestion prediction device provided by the embodiment of the invention can execute the congestion prediction method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of executing the congestion prediction method.
It should be noted that, in the embodiment of the congestion prediction apparatus, the units and modules included in the embodiment are merely divided according to the functional logic, but are not limited to the above division as long as the corresponding functions can be implemented; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
Example four
Fig. 4 is a schematic structural diagram of an electronic device according to a fourth embodiment 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. System 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 system 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, to implement a congestion prediction method provided by the embodiment of the present invention, the method includes:
determining current parcel flow rate information corresponding to each inlet of a sorting device;
inputting the current parcel flow velocity information into a preset congestion prediction model, and determining a current congestion prediction result corresponding to each monitoring node in the sorting device according to the output of the preset congestion prediction model;
the preset congestion prediction model is obtained in advance based on sample data training.
Of course, those skilled in the art will appreciate that the processor may also implement the technical solution of the congestion prediction method provided by any embodiment of the present invention.
EXAMPLE five
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a congestion prediction method as provided by any of the embodiments of the present invention, the method comprising:
determining current parcel flow rate information corresponding to each inlet of a sorting device;
inputting the current parcel flow velocity information into a preset congestion prediction model, and determining a current congestion prediction result corresponding to each monitoring node in the sorting device according to the output of the preset congestion prediction model;
the preset congestion prediction model is obtained in advance based on sample data training.
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. The computer-readable storage medium may be, for example but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. 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, wire, fiber optic 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 will be understood by those skilled in the art that the modules or steps of the invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented by program code executable by a computing device, such that it may be stored in a memory device and executed by a computing device, or it may be separately fabricated into various integrated circuit modules, or it may be fabricated by fabricating a plurality of modules or steps thereof into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
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 illustrated 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 (12)
1. A congestion prediction method, comprising:
determining current parcel flow rate information corresponding to each inlet of a sorting device;
inputting the current parcel flow velocity information into a preset congestion prediction model, and determining a current congestion prediction result corresponding to each monitoring node in the sorting device according to the output of the preset congestion prediction model;
the preset congestion prediction model is obtained in advance based on sample data training.
2. The method of claim 1, wherein determining current parcel flow rate information for each inlet of a sorting apparatus comprises:
acquiring scanning time corresponding to each parcel in a preset number of parcels recently scanned by an entrance aiming at each entrance;
and determining the current parcel flow rate information corresponding to the inlet according to the scanning time corresponding to each parcel.
3. The method of claim 2, wherein determining the current parcel flow rate information for the portal based on the scan time for each parcel comprises:
determining the scanning time interval between every two adjacent parcels according to the scanning time corresponding to each parcel;
and averaging each scanning time interval to obtain the current parcel flow rate information corresponding to the entrance.
4. The method according to any of claims 1-3, further comprising, after said determining a current congestion prediction result for each monitoring node in the sorting apparatus:
taking the monitoring node with the current congestion prediction result in a congestion state as a target monitoring node;
determining a weight value of each entrance causing congestion influence on the target monitoring node;
and adjusting the current parcel flow rate of the entrance according to the weight value corresponding to each entrance so as to enable the current congestion prediction result corresponding to the target monitoring node to be in a non-congestion state.
5. The method according to claim 4, wherein the step of using the monitoring node with the congestion state as the current congestion prediction result as the target monitoring node comprises the following steps:
if at least two monitoring nodes with the current congestion prediction results in the congestion state exist, acquiring the congestion prediction probability corresponding to each monitoring node with the current congestion prediction results in the congestion state;
and taking the monitoring node with the maximum congestion prediction probability as a target monitoring node.
6. The method of claim 4, wherein determining the weight value that each portal has a congestion impact on the target monitoring node comprises:
randomly generating parcel flow velocity sample information in the vicinity of each piece of current parcel flow velocity information input into the preset congestion prediction model;
inputting the package flow rate sample information into the preset congestion prediction model, and obtaining a sample congestion prediction probability corresponding to the target monitoring node according to the output of the preset congestion prediction model;
and performing linear fitting according to the package flow velocity sample information and the corresponding sample congestion prediction probability, and determining a weight value of each inlet causing congestion influence on the target monitoring node according to a fitted linear model.
7. The method of claim 4, wherein the adjusting the current parcel flow rate at an ingress according to the weight value corresponding to each ingress to make the current congestion prediction result corresponding to the target monitoring node a non-congestion state comprises:
determining a current regulation entrance according to the weight value corresponding to each entrance;
and adjusting the current parcel flow rate of the current adjusting entrance according to the minimum parcel flow rate information corresponding to the current adjusting entrance so as to enable the current congestion prediction result corresponding to the target monitoring node to be in a non-congestion state.
8. The method of claim 7, wherein determining the current adjustment entry according to the weight value corresponding to each entry comprises:
and sequencing the weight value corresponding to each entrance, and determining the entrance with the largest weight value as the current regulation entrance.
9. The method according to claim 7, wherein the adjusting the current parcel flow rate at the current regulation entrance according to the minimum parcel flow rate information corresponding to the current regulation entrance so that the current congestion prediction result corresponding to the target monitoring node is in a non-congestion state comprises:
and if the current package flow rate of the current regulation inlet is regulated to the corresponding minimum package flow rate, and the current congestion prediction result corresponding to the target monitoring node is still in a congestion state, determining a next regulation inlet, and regulating the current package flow rate of the next regulation inlet based on the minimum package flow rate information corresponding to the next regulation inlet until the congestion prediction result corresponding to the target monitoring node is in a non-congestion state.
10. A congestion prediction apparatus comprising:
the current parcel flow rate information determining module is used for determining current parcel flow rate information corresponding to each inlet of the sorting device;
the current congestion prediction result determining module is used for inputting the current parcel flow rate information into a preset congestion prediction model and determining a current congestion prediction result corresponding to each monitoring node in the sorting device according to the output of the preset congestion prediction model;
the preset congestion prediction model is obtained in advance based on sample data training.
11. An electronic device, characterized in that the electronic device comprises:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the congestion prediction method as recited in any one of claims 1-9.
12. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the congestion prediction method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110918699.XA CN113610304B (en) | 2021-08-11 | 2021-08-11 | Congestion prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110918699.XA CN113610304B (en) | 2021-08-11 | 2021-08-11 | Congestion prediction method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113610304A true CN113610304A (en) | 2021-11-05 |
| CN113610304B CN113610304B (en) | 2024-09-20 |
Family
ID=78340266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110918699.XA Active CN113610304B (en) | 2021-08-11 | 2021-08-11 | Congestion prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610304B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108346288A (en) * | 2018-02-12 | 2018-07-31 | 山东路科公路信息咨询有限公司 | Section operating status method for early warning, device and electronic equipment |
| CN109658697A (en) * | 2019-01-07 | 2019-04-19 | 平安科技（深圳）有限公司 | Prediction technique, device and the computer equipment of traffic congestion |
| CN109887283A (en) * | 2019-03-07 | 2019-06-14 | 东莞数汇大数据有限公司 | A kind of congestion in road prediction technique, system and device based on bayonet data |
| CN110298612A (en) * | 2019-05-21 | 2019-10-01 | 菜鸟智能物流控股有限公司 | Logistics object management system and logistics object management method |
| CN110641949A (en) * | 2019-08-22 | 2020-01-03 | 浙江百世技术有限公司 | Equipment and system for monitoring goods jam on conveyor belt |
| CN110728482A (en) * | 2019-10-22 | 2020-01-24 | 启东亦大通自动化设备有限公司 | Matrix confluence control system |
| CN110751828A (en) * | 2019-09-10 | 2020-02-04 | 平安国际智慧城市科技股份有限公司 | Road congestion measuring method and device, computer equipment and storage medium |
| US20200254490A1 (en) * | 2019-02-08 | 2020-08-13 | Advanced Technology & Research Corp. | Modular package sorting system |
| CN111710163A (en) * | 2020-07-13 | 2020-09-25 | 深圳市迅远科技有限公司 | Road congestion illegal parking monitoring system, method and medium based on RFID technology |
| WO2020259074A1 (en) * | 2019-06-28 | 2020-12-30 | 佛山科学技术学院 | Big data-based traffic congestion prediction system and method, and storage medium |
| CN112561126A (en) * | 2020-11-26 | 2021-03-26 | 浙江百世技术有限公司 | Auxiliary transportation method and device for assembly line articles |
| CN112862161A (en) * | 2021-01-18 | 2021-05-28 | 上海燕汐软件信息科技有限公司 | Goods sorting management method and device, electronic equipment and storage medium |
| CN113159457A (en) * | 2021-05-19 | 2021-07-23 | 北京邮电大学 | Intelligent path planning method and system and electronic equipment |
-
2021
- 2021-08-11 CN CN202110918699.XA patent/CN113610304B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108346288A (en) * | 2018-02-12 | 2018-07-31 | 山东路科公路信息咨询有限公司 | Section operating status method for early warning, device and electronic equipment |
| CN109658697A (en) * | 2019-01-07 | 2019-04-19 | 平安科技（深圳）有限公司 | Prediction technique, device and the computer equipment of traffic congestion |
| US20200254490A1 (en) * | 2019-02-08 | 2020-08-13 | Advanced Technology & Research Corp. | Modular package sorting system |
| CA3145951A1 (en) * | 2019-02-08 | 2021-02-18 | Advanced Technology & Research Corp. | Modular package sorting system |
| CN109887283A (en) * | 2019-03-07 | 2019-06-14 | 东莞数汇大数据有限公司 | A kind of congestion in road prediction technique, system and device based on bayonet data |
| CN110298612A (en) * | 2019-05-21 | 2019-10-01 | 菜鸟智能物流控股有限公司 | Logistics object management system and logistics object management method |
| WO2020259074A1 (en) * | 2019-06-28 | 2020-12-30 | 佛山科学技术学院 | Big data-based traffic congestion prediction system and method, and storage medium |
| CN110641949A (en) * | 2019-08-22 | 2020-01-03 | 浙江百世技术有限公司 | Equipment and system for monitoring goods jam on conveyor belt |
| CN110751828A (en) * | 2019-09-10 | 2020-02-04 | 平安国际智慧城市科技股份有限公司 | Road congestion measuring method and device, computer equipment and storage medium |
| CN110728482A (en) * | 2019-10-22 | 2020-01-24 | 启东亦大通自动化设备有限公司 | Matrix confluence control system |
| CN111710163A (en) * | 2020-07-13 | 2020-09-25 | 深圳市迅远科技有限公司 | Road congestion illegal parking monitoring system, method and medium based on RFID technology |
| CN112561126A (en) * | 2020-11-26 | 2021-03-26 | 浙江百世技术有限公司 | Auxiliary transportation method and device for assembly line articles |
| CN112862161A (en) * | 2021-01-18 | 2021-05-28 | 上海燕汐软件信息科技有限公司 | Goods sorting management method and device, electronic equipment and storage medium |
| CN113159457A (en) * | 2021-05-19 | 2021-07-23 | 北京邮电大学 | Intelligent path planning method and system and electronic equipment |
Non-Patent Citations (4)
| Title |
|---|
| GEORG MAIER , FLORIAN PFAFF等: "Experimental Evaluation of a Novel Sensor-Based Sorting Approach Featuring Predictive Real-Time Multiobject Tracking", IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 1 February 2021 (2021-02-01) * |
| 吴磊: "A分拣中心仿真与优化研究", 中国知网硕士电子期刊, no. 2021, 1 January 2021 (2021-01-01) * |
| 程山英;: "交通拥堵汽车流量准确预测仿真研究", 计算机仿真, no. 10, 15 October 2017 (2017-10-15) * |
| 赵云波;李天舒;汪钰皓;: "大批量订单整体分拣问题建模及其分布式并行方法", 高技术通讯, no. 06, 15 June 2020 (2020-06-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113610304B (en) | 2024-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112783195B (en) | Routing inspection route planning method and device for multiple unmanned aerial vehicles and computer equipment | |
| CN109471783B (en) | Method and device for predicting task operation parameters | |
| CN111368878B (en) | Optimization method based on SSD target detection, computer equipment and medium | |
| CN113283630A (en) | Air quality prediction method, device, equipment and computer readable storage medium | |
| CN113895460B (en) | Pedestrian trajectory prediction method, device and storage medium | |
| CN112183627B (en) | Method for generating prediction density map network and vehicle annual inspection number detection method | |
| CN112818792A (en) | Lane line detection method, lane line detection device, electronic device, and computer storage medium | |
| CN112445709B (en) | Method and device for solving AFL test model data imbalance through GAN | |
| CN116380438A (en) | Fault diagnosis method and device, electronic equipment and storage medium | |
| CN113282920B (en) | Log abnormality detection method, device, computer equipment and storage medium | |
| CN113936232A (en) | Screen fragmentation identification method, device, equipment and storage medium | |
| CN113610304B (en) | Congestion prediction method, device, equipment and storage medium | |
| US11295211B2 (en) | Multi-scale object detection with a trained neural network | |
| CN114693052A (en) | Risk prediction model training method and device, computing equipment and medium | |
| CN111627029A (en) | Method and device for acquiring image instance segmentation result | |
| CN117853573A (en) | Video processing method, device, electronic equipment and computer readable medium | |
| CN113051400B (en) | Labeling data determining method and device, readable medium and electronic equipment | |
| CN114581803A (en) | Article identification processing method and device | |
| CN113762308A (en) | Training method, classification method, device, medium and equipment of classification model | |
| CN114218504A (en) | Blocked road segment identification method and device, electronic equipment and storage medium | |
| CN113393453A (en) | Method, apparatus, device, medium and product for detecting self-bursting insulators | |
| CN115099371B (en) | LSTM anomaly detection method, device, equipment and storage medium | |
| CN105468871B (en) | A kind of momenttum wheel success Envelope Analysis and application process | |
| CN117478434B (en) | Edge node network traffic data processing method, device, equipment and medium | |
| CN110633596A (en) | Method and device for predicting vehicle direction angle |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |