CN109697531A - A kind of logistics park-hinterland Forecast of Logistics Demand method - Google Patents
A kind of logistics park-hinterland Forecast of Logistics Demand method Download PDFInfo
- Publication number
- CN109697531A CN109697531A CN201811584868.5A CN201811584868A CN109697531A CN 109697531 A CN109697531 A CN 109697531A CN 201811584868 A CN201811584868 A CN 201811584868A CN 109697531 A CN109697531 A CN 109697531A
- Authority
- CN
- China
- Prior art keywords
- logistics
- demand
- hinterland
- park
- forecast
- 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
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
- 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
- G06Q10/083—Shipping
- G06Q10/0838—Historical data
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to Logistics Predicting Technique fields, disclose a kind of logistics park-hinterland Forecast of Logistics Demand method, comprising: each Demand of Regional Logistics data construct sample set in acquisition logistics park-hinterland；Sample data is divided into training set and test set；Training set is used to obtain the support vector regression model of rationally description input relationship, and test set is for verifying forecast result of model；It brings parameters obtained into support vector regression, test sample is predicted, obtain prediction result, and compare with initial data, verify prediction effect；The logistics demand influence index in each region is brought into trained support vector regression, its Demand of Regional Logistics is predicted；The logistics demand of logistics park-hinterland is determined according to the Demand of Regional Logistics in each region；Logistics park-hinterland Forecast of Logistics Demand method provided by the invention, not only shows good fitting precision to Small Sample Database, also shows lesser error to independent test set, improves the generalization ability of prediction model.
Description
Technical field
The invention belongs to Logistics Predicting Technique fields, and in particular to a kind of logistics park-hinterland Forecast of Logistics Demand side
Method.
Background technique
Existing Forecast of Logistics Demand technique study includes: to use the prediction technique based on traditional statistics, and passing
Artificial intelligence is introduced on the basis of statistical prediction technique of uniting, the method predicted using prediction model.
Wherein, the prediction technique based on traditional statistics includes Grey Model, regression analysis, elastic coefficient method, gathers
Class method, input-output model, space-time multinomial probabilistic model etc., such methods are applied to exist in logistics subject and much be asked
Topic for example requires have biggish sample size, and real estate logistics demand data sample is less and is difficult to collect, this is to prediction
The verifying of method has a great impact；Furthermore these methods have the data of special characteristic in processing, such as have it is high-dimensional, in non-
When the data of the features such as normal distribution, effect is undesirable.These methods step when handling data lacks flexibility simultaneously, to institute
The processing etc. for thering are data to make no exception.
The Forecast of Logistics Demand algorithm for introducing artificial intelligence technology includes artificial neural network (ANN) and its modified,
Although such methods can make up the deficiency of conventional method, artificial neural network and its modified used in it to a certain extent
Prediction technique, also expose some disadvantages when in use: being for example unable to the generalization ability of collateral security prediction model；Learning
When limited sample size, learning process error easily converges on local minimum point, and study precision is difficult to ensure；Learning sample variable is very
When more, and fall into " dimension disaster "；What is relied primarily on is empirical risk minimization principle.
Summary of the invention
Aiming at the above defects or improvement requirements of the prior art, the present invention provides a kind of logistics park-hinterland logistics demands
Prediction technique, purpose realize the Accurate Prediction to Logistics Park logistics demand.
To achieve the above object, according to one aspect of the present invention, it is pre- to provide a kind of logistics park-hinterland logistics demand
Survey method, includes the following steps:
(1) each Demand of Regional Logistics data and historical data in logistics park-hinterland are acquired, sample set is constructed；
(2) sample data is divided into training set and test set；Training set is used to obtain the support of rationally description input relationship
Vector regression model, test set is for verifying forecast result of model；
(3) it brings parameters obtained into support vector regression, test sample is predicted, acquisition prediction result, and with
Initial data compares, and verifies prediction effect；
(4) the logistics demand influence index in each region is brought into trained support vector regression, to its region
Logistics demand is predicted；
(5) logistics demand of logistics park-hinterland is determined according to the Demand of Regional Logistics in each region.
Preferably, above-mentioned logistics park-hinterland Forecast of Logistics Demand method, the kernel function of support vector regression model are adopted
With Polynomial kernel function, radial basis function or Sigmoid function.
Preferably, above-mentioned logistics park-hinterland Forecast of Logistics Demand method, step (5) includes following sub-step:
(5.1) different administrative region i (i=1,2,3 ... n) occupied by the innerland of studied Logistics Park k are predicted
Demand of Regional Logistics b at a specified future datei(i=1,2,3 ... n)；I is administrative region number；
(5.2) the ratio r of different administrative regions shared by logistics park-hinterland k is determinedki；Wherein, k=1,2,3 ... n
(5.3) logistics demand on the innerland of Logistics Park k is obtained
Wherein, FkiFor the innerland logistics demand of Logistics Park k, rkiFor logistics park-hinterland k area in administrative region institute
The ratio accounted for.
Preferably, above-mentioned logistics park-hinterland Forecast of Logistics Demand method determines that support vector regression model punishes letter
Several and kernel functional parameter method, comprising:
(2.1) the genetic algorithm fortune for retaining number including initial population scale, crossing-over rate, aberration rate, optimum individual is determined
Row parameter；
(2.2) N × L matrix is established in a manner of binary coding as population, and generates initial population at random, and N is derived from L
So number；
(2.3) each individual in initial population is brought into support vector regression model and is calculated, output is tied
Fruit compares with initial data, calculates the mistake point rate of training sample, to obtain the fitness of each individual；
(2.4) genetic manipulation selected population, intersect, to make a variation generates next-generation population, and successive ignition；
(2.5) when meeting termination condition, stop iteration；Meet termination condition and obtains penalty, kernel functional parameter.
Preferably, above-mentioned logistics park-hinterland Forecast of Logistics Demand method, stopping criterion for iteration are to reach maximum evolution time
Several or fitness no longer changes；
In general, through the invention it is contemplated above technical scheme is compared with the prior art, can obtain down and show
Beneficial effect:
(1) logistics park-hinterland Forecast of Logistics Demand method provided by the invention, using genetic algorithm come to supporting vector
Regression machine punishment parameter and kernel functional parameter optimize, and avoid in the past through subjectivity or use caused by artificial judgment
Grid search bring is inefficient, to improve the forecasting efficiency and effect of support vector regression.
(2) logistics park-hinterland Forecast of Logistics Demand method provided by the invention, due to being to fully consider Logistic Park
On the basis of the mechanism of production of area innerland, the logistics demand of logistics park-hinterland and the logistics demand of innerland place administrative region are proposed
Ratio and its ratio on area corresponding relationship, so as to be readily able to obtain data administrative region logistics demand mapping
Onto the logistics demand for being not easy to obtain the logistics park-hinterland of data, the demand accuracy of logistics park-hinterland not only ensure that, but also
Improve the operability of Forecast of Logistics Demand.
Detailed description of the invention
Fig. 1 is the flow diagram for the logistics park-hinterland Forecast of Logistics Demand method that embodiment provides；
Fig. 2 is support vector regression kernel function schematic diagram；
Fig. 3 is the chromosome example in embodiment；
Fig. 4 is the crossover operation schematic diagram in embodiment；
Fig. 5 is mutation operator operation chart in embodiment.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.As long as in addition, technical characteristic involved in the various embodiments of the present invention described below
Not constituting a conflict with each other can be combined with each other.
Referring to Fig.1, the logistics park-hinterland Forecast of Logistics Demand method that embodiment provides, includes the following steps:
(1) each Demand of Regional Logistics data and historical data in logistics park-hinterland are acquired, sample set is constructed；Embodiment
In, Demand of Regional Logistics is indicated with the region volume of goods transported.In order to avoid being influenced in data handling procedure since the order of magnitude is excessive
Prediction result carries out unified dimension to initial data and handles.
(2) sample data is divided into training set and test set；
Training set is used to obtain the support vector regression model of rationally description input relationship, and test set is used for pre- to model
Effect is surveyed to be verified.
Using training set data, the penalty coefficient and kernel functional parameter of support vector regression are determined by genetic algorithm,
Obtain support vector regression model.
In embodiment, building is used to predict that the support vector regression of logistics demand is as follows:
s.t.yi-(ω·φ(xi)+b)≤ε+ξi
ω is weight vector in formula, and C is penalty, and b is threshold values, and () indicates inner product operation.Target be seek ω and
B minimizes structure risk under the premise of meeting ε-insensitive loss function, while introducing slack variable
In embodiment, kernel function to be selected is divided into three classes according to different inner product forms:
A, Polynomial kernel function: K (x, xi)=[(xxi)+1]q；Obtained is q rank multinomial classifier.
B, radial basis function (RBF):Here the corresponding branch of each Basis Function Center
Vector is held, they and output weight are automatically determined by algorithm.
C, Sigmoid function: K (x, xi)=tanh (v (xxi)+c)；What at this moment SVM was realized is exactly comprising a hidden layer
Multilayer perceptron, the number of hidden nodes is automatically determined by algorithm, there is no puzzlement neural network method local minimum point
Problem.
Kernel function is selected according to precision of prediction requirement, selection meets the kernel function of precision of prediction requirement.
Before support vector regression model solution, its penalty C and selected kernel functional parameter g is first determined.Implement
These parameters are optimized using genetic algorithm in example, are specifically comprised the following steps:
(2.1) it determines genetic algorithm operating parameter, determines that initial population scale, crossing-over rate, aberration rate, optimum individual retain
Number.
(2.2) initial population is generated
N × L matrix is established in a manner of binary coding as population, and generates initial population at random；N and L take natural number.
Embodiment selects binary-coded mode to encode individual (chromosome), chromosome example as shown in figure 3,
Wherein corresponding number of bits is 10, preceding 10 expression parameters C, rear 10 expression parameter g.
(2.3) fitness is calculated
Each individual in initial population is brought into support vector regression model and is calculated, by output result and original
Beginning data compare, and calculate the mistake point rate of training sample, to obtain the fitness size of each individual；Wherein fitness
Function is as follows:
E represents support vector machines in the sample mistake point rate of training stage, when the mistake of training sample divides rate very high, the individual
Fitness it is just very low, show that the Individual Quality is low；When sample mistake divides rate relatively low, the fitness of the individual is just very big, table
The bright individual is more high-quality.
(2.4) next-generation population and successive ignition are generated
It the genetic manipulations such as selected population, intersected, being made a variation, generating next-generation population.
Selection operator of the wheel disc bet method as model is selected in embodiment.By individual adaptation degree in entire group's fitness
In the shared ratio-dependent individual by select probability.If setting population number as N, the fitness of individual i is f (i), can be calculated
The probability P that individual i is selected outiWith the accumulated probability Q of the individuali, the accumulated probability and generate [0,1] between random number r ratio
Compared with decision, that individual participates in mating.Individual i select probability PiWith the accumulated probability Q of the individualiCalculation formula it is as follows:
If r < Q1, just select an individual；Otherwise i-th of individual is selected, i-th of individual meets Qi-1<r<Qi。
Select two-point crossover as the crossover operator of model in embodiment；So-called two-point crossover is exactly binary-coded
Two intersection points are randomly selected on individual, and two individual two are intersected into the part between point and are swapped, and are generated
New individual.Assuming that the two intersection points randomly selected are 3 and 14, specific crossover operation is referring to Fig. 4.
It is randomly assigned several in individual UVR exposure string according to mutation probability in embodiment to make a variation, then in the variation
Position changes encoded radio.When for binary coding, simple inversion operation i.e. 0 → 1 or 1 → 0 will appear as.Assuming that random become
Dystopy is 5, and mutation operator operation is referring to Fig. 5.
(2.5) when meeting termination condition, stop iteration；Termination condition in embodiment be reach maximum evolution number or
Fitness no longer changes；
(2.6) meet termination condition and obtain penalty C, kernel functional parameter σ.
(3) it brings parameters obtained into support vector regression, test sample is predicted, acquisition prediction result, and with
Initial data compares, and verifies prediction effect.
(4) the logistics demand influence index in each region is brought into trained support vector regression, to its region
Logistics demand is predicted；
(5) logistics demand of logistics park-hinterland is determined according to the Demand of Regional Logistics in each region；Specifically include following son
Step:
(5.1) different administrative region i (i=1,2,3 ... n) occupied by the innerland of studied Logistics Park k are predicted
Demand of Regional Logistics b at a specified future datei(i=1,2,3 ... n)；I is administrative region number；
(5.2) the ratio r of different administrative regions shared by logistics park-hinterland k is determinedki；Wherein, k=1,2,3 ... n
(5.3) logistics demand on the innerland of Logistics Park k is obtained
Wherein, FkiFor the innerland logistics demand of Logistics Park k, rkiFor the ratio of administrative region shared by logistics park-hinterland k
Example.
The above-mentioned logistics park-hinterland Forecast of Logistics Demand method that embodiment provides can effectively reduce empirical value prediction
Bring influences, the result of actual measurement shows that, this method not only shows good fitting precision to Small Sample Database, also to independent
Test set shows lesser error, improves the generalization ability of prediction model；And this method can handle various data class
Type, including high-dimensional, the data etc. of Non-Gaussian Distribution.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, not to
The limitation present invention, any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should all include
Within protection scope of the present invention.
Claims (5)
1. a kind of logistics park-hinterland Forecast of Logistics Demand method, which comprises the steps of:
(1) each Demand of Regional Logistics data and historical data in logistics park-hinterland are acquired, sample set is constructed；
(2) sample data is divided into training set and test set；Training set is used to obtain the support vector regression of description input relationship
Machine model, test set is for verifying forecast result of model；
(3) bring parameters obtained into support vector regression, test sample predicted, obtain prediction result, and with it is original
Data compare, and verify prediction effect；
(4) the logistics demand influence index in each region is brought into trained support vector regression, to its Regional Logistics
Demand is predicted；
(5) logistics demand of logistics park-hinterland is determined according to the Demand of Regional Logistics in each region.
2. logistics park-hinterland Forecast of Logistics Demand method as described in claim 1, which is characterized in that support vector regression
The kernel function of model uses Polynomial kernel function, radial basis function or Sigmoid function.
3. logistics park-hinterland Forecast of Logistics Demand method as claimed in claim 1 or 2, which is characterized in that determine support to
The method for measuring regression machine model penalty and kernel functional parameter, comprising:
(2.1) determine that the genetic algorithm for retaining number including initial population scale, crossing-over rate, aberration rate, optimum individual runs ginseng
Number；
(2.2) N × L matrix is established in a manner of binary coding as population, and generates initial population at random, and N and L are derived from so
Number；
(2.3) each individual in initial population is brought into support vector regression model and is calculated, will output result with
Initial data compares, and calculates the mistake point rate of training sample, to obtain the fitness of each individual；
(2.4) genetic manipulation selected population, intersect, to make a variation generates next-generation population, and successive ignition；
(2.5) when meeting termination condition, stop iteration；Meet termination condition and obtains penalty, kernel functional parameter.
4. logistics park-hinterland Forecast of Logistics Demand method as claimed in claim 3, which is characterized in that stopping criterion for iteration is
Reach maximum evolution number or fitness no longer changes.
5. logistics park-hinterland Forecast of Logistics Demand method as claimed in claim 1 or 2, which is characterized in that the step (5)
Including following sub-step:
(5.1) long term of different administrative region i (i=1,2,3 ... n) occupied by the innerland of studied Logistics Park k is predicted
Demand of Regional Logistics bi(i=1,2,3 ... n)；I is administrative region number；
(5.2) the ratio r of different administrative regions shared by logistics park-hinterland k is determinedki；Wherein, k=1,2,3 ... n
(5.3) logistics demand on the innerland of Logistics Park k is obtained
FkiFor the innerland logistics demand of Logistics Park k, rkiFor the ratio of administrative region shared by logistics park-hinterland k.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811584868.5A CN109697531A (en) | 2018-12-24 | 2018-12-24 | A kind of logistics park-hinterland Forecast of Logistics Demand method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811584868.5A CN109697531A (en) | 2018-12-24 | 2018-12-24 | A kind of logistics park-hinterland Forecast of Logistics Demand method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109697531A true CN109697531A (en) | 2019-04-30 |
Family
ID=66232738
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811584868.5A Pending CN109697531A (en) | 2018-12-24 | 2018-12-24 | A kind of logistics park-hinterland Forecast of Logistics Demand method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109697531A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242698A (en) * | 2020-01-20 | 2020-06-05 | 金华航大北斗应用技术有限公司 | Method and system for neural network model of commodity demand prediction |
| CN111507541A (en) * | 2020-04-30 | 2020-08-07 | 南京福佑在线电子商务有限公司 | Goods quantity prediction model construction method, goods quantity measurement device and electronic equipment |
| US11887045B2 (en) | 2020-02-12 | 2024-01-30 | Maersk A/S | Determining resource requirements |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617459A (en) * | 2013-12-06 | 2014-03-05 | 李敬泉 | Commodity demand information prediction method under multiple influence factors |
| CN104537382A (en) * | 2015-01-12 | 2015-04-22 | 杭州电子科技大学 | Electromyographic signal gait recognition method for optimizing support vector machine based on genetic algorithm |
-
2018
- 2018-12-24 CN CN201811584868.5A patent/CN109697531A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103617459A (en) * | 2013-12-06 | 2014-03-05 | 李敬泉 | Commodity demand information prediction method under multiple influence factors |
| CN104537382A (en) * | 2015-01-12 | 2015-04-22 | 杭州电子科技大学 | Electromyographic signal gait recognition method for optimizing support vector machine based on genetic algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 孙逊: ""基于GA－SVM的物流园区物流需求预测及分析"", 《中国市场》 * |
| 彭京平 等: ""物流园区物流需求预测方法研究"", 《物流工程与管理》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242698A (en) * | 2020-01-20 | 2020-06-05 | 金华航大北斗应用技术有限公司 | Method and system for neural network model of commodity demand prediction |
| US11887045B2 (en) | 2020-02-12 | 2024-01-30 | Maersk A/S | Determining resource requirements |
| CN111507541A (en) * | 2020-04-30 | 2020-08-07 | 南京福佑在线电子商务有限公司 | Goods quantity prediction model construction method, goods quantity measurement device and electronic equipment |
| CN111507541B (en) * | 2020-04-30 | 2021-01-29 | 南京福佑在线电子商务有限公司 | Goods quantity prediction model construction method, goods quantity measurement device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111738512B (en) | Short-term power load prediction method based on CNN-IPSO-GRU hybrid model | |
| Tian | Short-term wind speed prediction based on LMD and improved FA optimized combined kernel function LSSVM | |
| CN111563706A (en) | Multivariable logistics freight volume prediction method based on LSTM network | |
| CN110544011B (en) | Intelligent system combat effectiveness evaluation and optimization method | |
| CN106650920A (en) | Prediction model based on optimized extreme learning machine (ELM) | |
| CN110059867B (en) | Wind speed prediction method combining SWLSTM and GPR | |
| CN111861013B (en) | Power load prediction method and device | |
| He et al. | Research on a novel combination system on the basis of deep learning and swarm intelligence optimization algorithm for wind speed forecasting | |
| CN109697531A (en) | A kind of logistics park-hinterland Forecast of Logistics Demand method | |
| CN110232461A (en) | More interconnection vector machine water quality prediction methods based on quantum genetic algorithm optimization | |
| CN113887916A (en) | Dynamic quantitative evaluation method and system for line loss of power distribution network | |
| CN116596044B (en) | Power generation load prediction model training method and device based on multi-source data | |
| Li et al. | A novel approach based on the Gauss-v SVR with a new hybrid evolutionary algorithm and input vector decision method for port throughput forecasting | |
| CN116187835A (en) | Data-driven-based method and system for estimating theoretical line loss interval of transformer area | |
| Wang et al. | Short-term load forecasting with LSTM based ensemble learning | |
| Mahmoodi et al. | A developed stock price forecasting model using support vector machine combined with metaheuristic algorithms | |
| Zeng et al. | Short-term load forecasting of smart grid systems by combination of general regression neural network and least squares-support vector machine algorithm optimized by harmony search algorithm method | |
| Almutairi et al. | An intelligent deep learning based prediction model for wind power generation | |
| CN116799796A (en) | Photovoltaic power generation power prediction method, device, equipment and medium | |
| Salazar et al. | Fair-fate: Fair federated learning with momentum | |
| CN114004153A (en) | Penetration depth prediction method based on multi-source data fusion | |
| CN113762591A (en) | Short-term electric quantity prediction method and system based on GRU and multi-core SVM counterstudy | |
| CN111724004B (en) | Reservoir available water supply amount forecasting method based on improved quantum wolf algorithm | |
| Wang | Analysis of bank credit risk evaluation model based on BP neural network | |
| Subhasree et al. | Forecasting vegetable price using time series data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190430 |
|
| RJ01 | Rejection of invention patent application after publication |