CN110827091A - Industrial raw material price prediction method - Google Patents
Industrial raw material price prediction method Download PDFInfo
- Publication number
- CN110827091A CN110827091A CN201911103073.2A CN201911103073A CN110827091A CN 110827091 A CN110827091 A CN 110827091A CN 201911103073 A CN201911103073 A CN 201911103073A CN 110827091 A CN110827091 A CN 110827091A
- Authority
- CN
- China
- Prior art keywords
- price
- industrial raw
- raw materials
- data
- predicted
- 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
- 239000002994 raw material Substances 0.000 title claims abstract description 154
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000007613 environmental effect Effects 0.000 claims abstract description 46
- 238000004519 manufacturing process Methods 0.000 claims abstract description 32
- 238000010801 machine learning Methods 0.000 claims abstract description 9
- 238000005311 autocorrelation function Methods 0.000 claims description 48
- 238000003062 neural network model Methods 0.000 claims description 44
- 230000000306 recurrent effect Effects 0.000 claims description 44
- 238000012549 training Methods 0.000 claims description 34
- 238000012545 processing Methods 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 3
- 230000006403 short-term memory Effects 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000008676 import Effects 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- 230000010354 integration Effects 0.000 claims 1
- 230000007787 long-term memory Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 27
- 230000006872 improvement Effects 0.000 description 9
- 230000000694 effects Effects 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 6
- 230000004913 activation Effects 0.000 description 5
- 230000007774 longterm Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- LYCAIKOWRPUZTN-UHFFFAOYSA-N Ethylene glycol Chemical compound OCCO LYCAIKOWRPUZTN-UHFFFAOYSA-N 0.000 description 3
- OKKJLVBELUTLKV-UHFFFAOYSA-N Methanol Chemical compound OC OKKJLVBELUTLKV-UHFFFAOYSA-N 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 239000011135 tin Substances 0.000 description 3
- 229910052718 tin Inorganic materials 0.000 description 3
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- 229920000742 Cotton Polymers 0.000 description 2
- 235000010469 Glycine max Nutrition 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 240000008467 Oryza sativa Japonica Group Species 0.000 description 2
- 235000019482 Palm oil Nutrition 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 2
- PPBRXRYQALVLMV-UHFFFAOYSA-N Styrene Chemical compound C=CC1=CC=CC=C1 PPBRXRYQALVLMV-UHFFFAOYSA-N 0.000 description 2
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 2
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 229910052782 aluminium Inorganic materials 0.000 description 2
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003245 coal Substances 0.000 description 2
- 229910052802 copper Inorganic materials 0.000 description 2
- 239000010949 copper Substances 0.000 description 2
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 229910052759 nickel Inorganic materials 0.000 description 2
- 239000002540 palm oil Substances 0.000 description 2
- -1 polyethylene Polymers 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000010959 steel Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 229910052725 zinc Inorganic materials 0.000 description 2
- 239000011701 zinc Substances 0.000 description 2
- 229920002261 Corn starch Polymers 0.000 description 1
- 229910000519 Ferrosilicon Inorganic materials 0.000 description 1
- 244000068988 Glycine max Species 0.000 description 1
- 244000043261 Hevea brasiliensis Species 0.000 description 1
- 241000220225 Malus Species 0.000 description 1
- 239000004698 Polyethylene Substances 0.000 description 1
- 239000004743 Polypropylene Substances 0.000 description 1
- 229920001131 Pulp (paper) Polymers 0.000 description 1
- 235000019779 Rapeseed Meal Nutrition 0.000 description 1
- 235000019764 Soybean Meal Nutrition 0.000 description 1
- CZMRCDWAGMRECN-UGDNZRGBSA-N Sucrose Chemical compound O[C@H]1[C@H](O)[C@@H](CO)O[C@@]1(CO)O[C@@H]1[C@H](O)[C@@H](O)[C@H](O)[C@@H](CO)O1 CZMRCDWAGMRECN-UGDNZRGBSA-N 0.000 description 1
- 229930006000 Sucrose Natural products 0.000 description 1
- XSQUKJJJFZCRTK-UHFFFAOYSA-N Urea Chemical compound NC(N)=O XSQUKJJJFZCRTK-UHFFFAOYSA-N 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 239000010426 asphalt Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004202 carbamide Substances 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 238000004939 coking Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 239000008120 corn starch Substances 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 229920001971 elastomer Polymers 0.000 description 1
- 239000011094 fiberboard Substances 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 239000000295 fuel oil Substances 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 229920003052 natural elastomer Polymers 0.000 description 1
- 229920001194 natural rubber Polymers 0.000 description 1
- 239000011120 plywood Substances 0.000 description 1
- 229920000573 polyethylene Polymers 0.000 description 1
- 229920001155 polypropylene Polymers 0.000 description 1
- 229920000915 polyvinyl chloride Polymers 0.000 description 1
- 239000004800 polyvinyl chloride Substances 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 239000004456 rapeseed meal Substances 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 239000005060 rubber Substances 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 239000004455 soybean meal Substances 0.000 description 1
- 235000012424 soybean oil Nutrition 0.000 description 1
- 239000003549 soybean oil Substances 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 235000019583 umami taste Nutrition 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Finance (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of industrial decision analysis, and particularly relates to a method for predicting prices of industrial raw materials. The invention comprises the following steps: acquiring environmental data to be predicted and historical data of industrial raw materials to be predicted; and inputting the environmental data to be predicted and the historical data of the industrial raw materials to be predicted into a preset price prediction model to obtain the predicted price of the current industrial raw materials to be predicted. The method adopts the price prediction model trained based on the machine learning algorithm to predict the future price of the industrial raw material concerned by the enterprise, can effectively improve the prediction accuracy of the price of the industrial raw material, reduces the cost of enterprise market environment analysis, provides effective data support for the enterprise to make a production decision, improves the quality of an analysis result in a market environment analysis report, has high practicability, and is suitable for popularization and use.
Description
Technical Field
The invention belongs to the technical field of industrial decision analysis, and particularly relates to a method for predicting prices of industrial raw materials.
Background
Currently, some enterprises generally analyze market environments and current operation conditions when making operation decisions, wherein the most important data is the prediction of prices of some industrial raw materials; the following analysis is generally performed in the prior art:
1) analyzing the market environment based on a macroscopic level, wherein common methods comprise PEST analysis and SWOT analysis, and the market environment is subjectively analyzed by utilizing a multi-dimensional visual angle in a macroscopic analysis mode;
2) the method is characterized in that the influence of market environment on the inside and the outside of an enterprise is researched on the basis of a microscopic level, common methods comprise a strategic management analysis strategy method, a basic competition strategy method, a value chain analysis method, a five-force model method, an STP marketing analysis method and a 4P marketing theory analysis method, and the market environment condition of the enterprise is evaluated on the basis of the microscopic level;
3) the method is characterized in that the market conditions such as enterprise operation conditions, market environments and the like are analyzed based on statistics, and the future operation conditions of the enterprises are effectively predicted by adopting a prediction method based on statistics.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
a. based on the analysis method of the macro and micro level, although the enterprise research report can be provided as the output, only the analysis visual angle is provided, no specific quantitative index exists, the subjective analysis varies from person to person, and the quality of the analysis result is good and uneven;
b. although the analysis method based on statistics can effectively quantify market environment and enterprise operation conditions to a certain extent, the market environment influence factors are numerous, the quantification capability is limited, the established model is usually predicted only for a single target object, numerous objects are difficult to link, and the quality of an analysis result cannot be guaranteed;
c. the analysis method has no uniform analysis dimension and standard, so that the error is large when the price of the industrial raw material is predicted, and the formed analysis result has little reference significance to enterprises.
Disclosure of Invention
The present invention aims to solve at least one of the above technical problems to a certain extent.
Therefore, the invention aims to provide an industrial raw material price prediction method, which can enable the price prediction of industrial raw materials required by enterprises to be more accurate.
The technical scheme adopted by the invention is as follows:
a method for predicting the price of industrial raw materials comprises the following steps:
acquiring environmental data to be predicted and historical data of industrial raw materials to be predicted;
inputting the environmental data to be predicted and the historical data of the industrial raw materials to be predicted into a preset price prediction model to obtain the predicted price of the current industrial raw materials to be predicted, wherein the price prediction model is obtained based on an environmental data training set and a historical data training set of the industrial raw materials.
Preferably, the price prediction model is obtained by:
acquiring a plurality of historical environmental data as an environmental data training set, and acquiring a plurality of historical data of industrial raw materials as a historical data training set of the industrial raw materials;
acquiring the latest price of the industrial raw materials, taking an environmental data training set and a historical data training set of the industrial raw materials as training data, and taking the latest price of the industrial raw materials as verification data;
inputting training data into a machine learning algorithm to respectively obtain a time sequence model and a recurrent neural network model;
respectively calculating the weight of the time series model and the weight of the recurrent neural network model based on the check data;
and (4) integrating the time series model and the corresponding weight thereof with the recurrent neural network model and the corresponding weight thereof to obtain a price prediction model.
Preferably, when the training data is input into a machine learning algorithm to obtain a time series model, the specific steps are as follows:
processing an environmental data training set and a historical data training set of industrial raw materials to obtain time sequence data;
judging whether the current time sequence data are stable time sequence data or not, if so, establishing an autocorrelation function and a partial autocorrelation function, and if not, performing difference-based smoothing on the non-stable time sequence data to obtain stable time sequence data, and then establishing the autocorrelation function and the partial autocorrelation function;
and establishing a corresponding time series model according to the states of the autocorrelation function and the partial autocorrelation function.
Preferably, when the corresponding time series model is established according to the states of the autocorrelation function and the partial autocorrelation function, the specific steps are as follows:
judging the states of the autocorrelation function and the partial autocorrelation function;
when the partial autocorrelation function is in a truncated state and the autocorrelation function is in a trailing state, an Autoregressive model (AR model) is established as shown in formula 1:
when the partial autocorrelation function is in a tail state and the autocorrelation function is in a truncated state, a Moving Average model (MA model) as shown in formula 2 is established:
Xt＝μ+Ut+θ1Ut-1+θ2Ut-2+…+θpUt-q
equation 2
When the partial autocorrelation function and the autocorrelation function are both in a trailing state, a differential Integrated Moving Average Autoregressive model (ARIMA model) as shown in formula 3 is established:
in the formula of UtIs a white noise sequence, δ is a constant, WtIs XtOf (2) a difference operator, XtIndicates the value of the t-th stage.
Preferably, the recurrent neural network model is a long short Term Memory-based temporal recurrent neural network model (LSTM model).
Preferably, when the weights of the time series model and the weights of the recurrent neural network model are calculated based on the check data, the specific steps are as follows:
obtaining a first check price of the latest period of the industrial raw materials through a time series model, and then comparing the first check price with check data to obtain a first difference value between the first check price and the check data;
obtaining a second check price of the industrial raw material in the latest period through a recurrent neural network model, and then comparing the second check price with the check data to obtain a second difference value between the second check price and the check data;
calculating the weight of the time series model:
calculating weights of the recurrent neural network model:
in the formula, valuetimeIs the absolute value of a first difference between the first check price and the check data, valuelstmIs the absolute value of a second difference between the second check price and the check data, wtimeIs a weight of the time series model, wlstmAre weights of the recurrent neural network model.
Preferably, when the future first-stage price of the current industrial raw material to be predicted is obtained, the specific steps are as follows:
respectively inputting environmental data to be predicted and historical data of industrial raw materials to be predicted into a time series model and a recurrent neural network model to obtain a first predicted price based on the time series model and a second predicted price based on the recurrent neural network model;
calculating a predicted price for the future period of the industrial raw material according to the first predicted price and the second predicted price:
prediction＝wtime*predictiontime+wlstm*predictionlstm
equation 6
Wherein the prediction is the future first-stage predicted price of the industrial raw materialtimeFor the first predicted price based on a time series model, predictiontstmIs a second predicted price based on the recurrent neural network model.
Preferably, the environmental data to be predicted and the historical environmental data both comprise overall market environmental data and industrial market environmental data; the overall market environment data includes a total domestic production value; the industrial market environmental data includes a procurement manager index and a producer price index.
Preferably, the historical data of the industrial raw materials includes exchange rate of the main industrial raw materials imported country currency to RMB currency, historical price of the industrial raw materials, historical future price of the main industrial raw materials, historical price of the associated industrial raw materials and historical future price of the associated industrial raw materials.
Preferably, after the environmental data to be predicted and the historical data of the industrial raw materials to be predicted are input into a preset price prediction model, the historical price of the main industrial raw materials obtains a first predicted price based on the time series model through the time series model, and the domestic total production value, the purchasing manager index, the producer price index, the exchange rate of the money of the imported state of the main industrial raw materials for exchanging the Renminbi, the historical price of the main industrial raw materials, the historical future price of the main industrial raw materials, the historical price of the associated industrial raw materials and the historical future price of the associated industrial raw materials obtain a second predicted price based on the recurrent neural network model through the recurrent neural network model.
The invention has the beneficial effects that:
the method adopts the price prediction model trained based on the machine learning algorithm, realizes the real-time prediction of the prices of the main industrial raw materials and the associated industrial raw materials required by the production of enterprises, can effectively improve the prediction accuracy of the prices of the industrial raw materials, reduces the cost of the market environment analysis of the enterprises, provides effective data support for the enterprises to make production decisions, improves the quality of analysis results in the market environment analysis reports, has high practicability, and is suitable for popularization and use.
Other advantageous effects of the present invention will be described in detail in the detailed description.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a block flow diagram of embodiment 1.
FIG. 2 is a schematic illustration of overall market environmental data, industrial market environmental data, and historical data of industrial raw materials.
FIG. 3 is a schematic diagram of the structure of the LSTM model.
FIG. 4 is a schematic illustration of a price prediction model used to predict the overall market environment data, industrial market environment data, and historical data of industrial raw materials from FIG. 2.
Detailed Description
The invention is further described with reference to the following figures and specific embodiments. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. Functional details disclosed herein are merely illustrative of example embodiments of the invention. This invention may, however, be embodied in many alternate forms and should not be construed as limited to the embodiments set forth herein.
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments of the invention. When the terms "comprises," "comprising," "includes," and/or "including" are used herein, they specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, numbers, steps, operations, elements, components, and/or groups thereof.
It should also be noted that, in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed substantially concurrently, or the figures may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
It should be understood that specific details are provided in the following description to facilitate a thorough understanding of example embodiments. However, it will be understood by those of ordinary skill in the art that the example embodiments may be practiced without these specific details. For example, systems may be shown in block diagrams in order not to obscure the examples in unnecessary detail. In other instances, well-known processes, structures and techniques may be shown without unnecessary detail in order to avoid obscuring example embodiments.
Example 1:
as shown in fig. 1, the present embodiment provides a method for predicting prices of industrial raw materials, including the following steps:
acquiring environmental data to be predicted and historical data of industrial raw materials to be predicted;
inputting the environmental data to be predicted and the historical data of the industrial raw materials to be predicted into a preset price prediction model to obtain the predicted price of the current industrial raw materials to be predicted, wherein the price prediction model is obtained based on an environmental data training set and a historical data training set of the industrial raw materials.
Example 2
The technical solution provided by this embodiment is a further improvement on the basis of the technical solution of embodiment 1, and the technical features of this embodiment that are different from those of embodiment 1 are:
in this embodiment, the price prediction model is obtained by the following steps:
acquiring a plurality of historical environmental data as an environmental data training set, and acquiring a plurality of historical data of industrial raw materials as a historical data training set of the industrial raw materials;
acquiring the latest price of the industrial raw materials, taking an environmental data training set and a historical data training set of the industrial raw materials as training data, and taking the latest price of the industrial raw materials as verification data;
inputting training data into a machine learning algorithm to respectively obtain a time sequence model and a recurrent neural network model;
respectively calculating the weight of the time series model and the weight of the recurrent neural network model based on the check data;
collecting the time series model and the corresponding weight thereof and the recurrent neural network model and the corresponding weight thereof to obtain a price prediction model; the time series model is one of the commonly used time series data prediction analysis methods, and the prediction effect on the time series data under certain assumed conditions is ideal.
In the embodiment, the time series model and the recurrent neural network model thereof are effectively integrated, the prices of main industrial raw materials and related industrial raw materials required by industrial enterprise production are reasonably predicted, and support is provided for company production and operation decisions.
Example 3
The technical solution provided by this embodiment is a further improvement on the basis of the technical solution of embodiment 2, and the technical features of this embodiment that are different from those of embodiment 2 are as follows:
in this embodiment, when the training data is input into the machine learning algorithm to obtain the time series model, the specific steps are as follows:
processing an environmental data training set and a historical data training set of industrial raw materials to obtain time sequence data;
and judging whether the current time sequence data are stable time sequence data, if so, establishing an autocorrelation function and a partial autocorrelation function, otherwise, performing difference-based smoothing on the non-stable time sequence data to obtain stable time sequence data, and then establishing the autocorrelation function and the partial autocorrelation function.
Example 4
The technical solution provided by this embodiment is a further improvement on the basis of the technical solution of embodiment 3, and the technical features of this embodiment that are different from those of embodiment 3 are:
in this embodiment, a corresponding time series model is established according to the states of the autocorrelation function and the partial autocorrelation function; when a corresponding time series model is established according to the states of the autocorrelation function and the partial autocorrelation function, the specific steps are as follows:
judging the states of the autocorrelation function and the partial autocorrelation function;
when the partial autocorrelation function is in a truncated state and the autocorrelation function is in a trailing state, an Autoregressive model (AR model) is established as shown in formula 1:
when the partial autocorrelation function is in a tail state and the autocorrelation function is in a truncated state, a Moving Average model (MA model) as shown in formula 2 is established:
Xt＝μ+Ut+θ1Ut-1+θ2Ut-2+…+θpUt-q
equation 2
When the partial autocorrelation function and the autocorrelation function are both in a trailing state, a differential Integrated Moving Average Autoregressive model (ARIMA model) as shown in formula 3 is established:
in the formula of UtIs a white noise sequence, δ is a constant, WtIs XtOf (2) a difference operator, XtValue indicating t-th period。
Example 5
The technical solution provided by this embodiment is a further improvement made on the basis of any one of the technical solutions of embodiments 2 to 4, and the technical features of this embodiment that are different from any one of embodiments 2 to 4 are as follows:
in this embodiment, the recurrent neural network model is a Long Short Term Memory-based time recurrent neural network model (LSTM model).
The LSTM model is one of the classic models in the field of machine learning, and is also one of the most representative models in the recurrent neural network model, and is often used for the prediction analysis research of the time series model.
Under the condition of inputting specification data, the LSTM model can effectively process long-term time sequence data and effectively avoid the common long-term dependence problem of the model, and the specific structural diagram of the LSTM model is shown in FIG. 3. The LSTM model makes flexible selection on the input and output results of data and the updating of the states of all parts mainly through the design of a forgetting gate, an input gate and an output gate. During the process of forgetting to remember the door, the hidden state h is readt-1And time-series data XtOutputting a value to determine each of the at-cell states Ct-1Information that the data in (1) needs to be discarded; determining and updating the cell state C based on the forgoing information of the forgetting gate during the process of the input gatet-1Newly created cell state C using Tanh activation functiontThen the updated cell state Ct-1Information binding to cell State CtIn (1), output cell state CtThe update result of (2); during the processing of the output gate, the cell state C is determined by using a Sigmoid activation functiontThe output information of (2) is then used to integrate the cell state C by means of the Tanh activation functiont-1And finally, multiplying the two parts of output information to obtain a final output result which is obtained by predicting the LSTM model based on the time series data. The Tanh activation function is shown in equation 7 and the Sigmoid activation function is shown in equation 8.
Wherein x represents time-series data, exIs an exponential function with e as the base.
Example 6
The technical solution provided by this embodiment is a further improvement made on the basis of any one of the technical solutions of embodiments 2 to 5, and the technical features of this embodiment that are different from any one of embodiments 2 to 5 are as follows:
in this embodiment, when the weights of the time series model and the weights of the recurrent neural network model are calculated based on the check data, the specific steps are as follows:
obtaining a first check price of the latest period of the industrial raw materials through a time series model, and then comparing the first check price with check data to obtain a first difference value between the first check price and the check data;
obtaining a second check price of the industrial raw material in the latest period through a recurrent neural network model, and then comparing the second check price with the check data to obtain a second difference value between the second check price and the check data;
calculating the weight of the time series model:
calculating weights of the recurrent neural network model:
in the formula, valuetimeIs the absolute value of a first difference between the first check price and the check data, valuelstmIs the absolute value of a second difference between the second check price and the check data, wtimeIs a weight of the time series model, wlstmAre weights of the recurrent neural network model.
Example 7
The technical solution provided by this embodiment is a further improvement on the basis of the technical solution of embodiment 6, and the technical features of this embodiment that are different from those of embodiment 6 are:
in this embodiment, when the future first-stage price of the current industrial raw material to be predicted is obtained, the specific steps are as follows:
respectively inputting environmental data to be predicted and historical data of industrial raw materials to be predicted into a time series model and a recurrent neural network model to obtain a first predicted price based on the time series model and a second predicted price based on the recurrent neural network model;
calculating a predicted price for the future period of the industrial raw material according to the first predicted price and the second predicted price:
prediction＝wtime*predictiontime+wlstm*predictionlstm
equation 6
Wherein the prediction is the future first-stage predicted price of the industrial raw materialtimeFor the first predicted price based on a time series model, predictionlstmIs a second predicted price based on the recurrent neural network model.
Example 8
The technical solution provided by this embodiment is a further improvement made on the basis of any one of embodiments 1 to 7, and the technical features of this embodiment that are different from any one of embodiments 1 to 7 are as follows:
in this embodiment, the environmental data to be predicted and the historical environmental data both include overall market environmental data and industrial market environmental data; the overall market environment data includes a total domestic production value; the industrial market environmental data includes a procurement manager index and a producer price index.
The basis of model training is the rationality of data selection. The invention selects the proper market evaluation index from three aspects of overall market environment, industrial market environment and enterprise production environment (namely historical data of industrial raw materials). The evaluation of the overall market environment needs to measure the economic condition of the overall market environment of an economic body, the domestic total production value acceleration rate is selected as an evaluation index, the development state of the national economy in the previous period can be intuitively reflected, the domestic total production value acceleration rate is a parameter reflecting the change speed, and the model learning at the later stage is influenced by the inconsistency of the dimensions of input data considering that the historical data of the industrial market environment and industrial raw materials are selected as specific numerical parameters, so that the domestic total production value belonging to the numerical parameters is selected as the index for evaluating the overall market environment, and the domestic total production value is the market value of all final products produced by the society by using production elements in a certain period; in the embodiment, the total domestic production value disclosed by the national statistical bureau is used as data for evaluating the overall market environment.
The evaluation index of the industrial market environment needs to be capable of comprehensively measuring the overall economic condition of the industrial industry, the factory price index of an industrial producer and the purchase price index of the industrial producer are selected, the factory price index of the industrial producer reflects the relative number of the variation trend and the degree of the total factory price level of all industrial products in a certain period, the relative number comprises various products sold by the industrial enterprise to all units except the enterprise and products directly sold to residents for living consumption, and the influence of the factory price variation on the total industrial value and the added value can be observed; the purchase price index of the industrial producer reflects the production input of the industrial enterprise, and the statistical index of the price level fluctuation trend and degree paid when purchasing industrial raw materials, fuel and power products from the material trade market and the industrial raw material production enterprise is an important basis for deducting the influence of price fluctuation in the material consumption cost of the industrial enterprise, so the present embodiment adopts the factory price index (i.e. purchase manager index) of the industrial producer and the purchase price index (i.e. producer price index) of the industrial producer disclosed by the national statistical bureau as data for evaluating the industrial market environment.
Example 9
The technical solution provided by this embodiment is a further improvement on the basis of the technical solution of embodiment 8, and the technical features of this embodiment that are different from those of embodiment 8 are as follows:
in the present embodiment, as shown in fig. 2, the historical data of the industrial raw materials includes the exchange rate of the money of the importer of the main industrial raw materials to the renminbi, the historical price of the industrial raw materials, the historical future price of the main industrial raw materials, the historical price of the associated industrial raw materials (complements and substitutes), and the historical future price of the associated industrial raw materials (complements and substitutes).
Production element factors such as production element price produced by an enterprise, production element cost combination based on the production element price, substitution and complementarity among the production elements and the like are important for enterprise production activity decision, so that the evaluation index of the enterprise production environment can accurately reflect the current situation of the enterprise production element market environment, the market environment of the production elements is often influenced by factors such as exchange rate, historical prices of industrial raw materials, future market price and associated industrial raw material price, the exchange rate of the industrial raw material imported state currency and the RMB and the historical prices of the industrial raw materials are directly associated with the prices of the industrial raw materials, the market situations of complementary products and substitute materials related to the industrial raw materials are ignored, in addition, the future price of the industrial raw materials can objectively reflect the potential market value of the industrial raw materials and is an important factor for reflecting the market situations of the industrial raw materials, therefore, the exchange rate of the money of the import country of the main industrial raw materials required by the enterprise production to the Renminbi, the historical price of the industrial raw materials, the historical future price of the main industrial raw materials, the historical price of the associated industrial raw materials and the historical future price of the associated industrial raw materials are selected as the evaluation indexes of the enterprise production environment; the relevant industrial raw materials refer to complements and substitutes of industrial raw materials.
As a preferred embodiment, the historical futures prices of the main industrial raw materials and the historical futures price data of the related industrial raw materials are from the domestic Zhengzhou commercial exchange, Dalian commercial exchange and Shanghai commercial exchange, so the predicted industrial raw materials are limited to white sugar, power coal, cotton, PTA, cotton yarn, methanol, Umami, glass, Qiangmai, ferrosilicon, early indica, manganesium, late indica, urea, apple, japonica rice, rapeseed meal, red date, corn of the Dalian commercial exchange, polyethylene, corn starch, polyvinyl chloride, soybean, polypropylene, soybean meal, coke, soybean oil, coking coal, palm oil, iron ore, fiberboard, ethylene glycol, plywood, styrene, egg, japonica rice, copper, lead, aluminum, nickel, zinc, tin, screw steel, Ume, copper of the Shanghai commercial exchange, lead, aluminum, nickel, zinc, tin, thread steel, soy, and palm oil, Stainless steel, wire rods, hot rolled coils, gold, silver, crude oil, natural rubber, fuel oil, No. 20 rubber, asphalt and paper pulp.
Example 10
The technical solution provided by this embodiment is a further improvement made on the basis of the technical solution of embodiment 9, and the technical features of this embodiment that are different from those of embodiment 9 are:
in this embodiment, as shown in fig. 4, after the environmental data to be predicted and the historical data of the industrial raw materials to be predicted are input into the preset price prediction model, the historical price of the main industrial raw materials obtains a first predicted price based on the time series model through the time series model, and the domestic total production value, the purchase management index, the producer price index, the exchange rate of the money of the imported state of the main industrial raw materials to the renminbi, the historical price of the main industrial raw materials, the historical future price of the main industrial raw materials, the historical price of the associated industrial raw materials and the historical future price of the associated industrial raw materials obtain a second predicted price based on the recurrent neural network model through the recurrent neural network model.
For the price prediction of industrial raw materials and related industrial raw materials, taking the price prediction of industrial raw materials as an example, on the premise of a certain assumption, the time series model predicts the price of the industrial raw materials in the future period based on the historical price of the industrial raw materials, the prediction effect is generally ideal, but the price fluctuation of the industrial raw materials is easily interfered by market factors, and the price prediction effect of the industrial raw materials and the related industrial raw materials is easily influenced by strict assumption conditions and uncertain factors such as delay of data collection. While the LSTM model is good at processing long-term time sequence data based on a certain time interval, can effectively avoid the problem of long-term dependence, the prediction effect of the long-term time series data is ideal under the common condition, and the LSTM model carries out price prediction through other data influencing the price change of industrial raw materials, so that the influence of the time series model on the excessive dependence of single data can be effectively avoided, however, the establishment of the LSTM model requires the use of a plurality of index data reflecting the overall market environment, the industrial market environment and the enterprise production environment, the data relate to a wide range of fields, the dimensions of the features are different, the time intervals are different, which may reduce the accuracy of the prediction of the industrial raw materials in the future, therefore, in order to effectively improve the accuracy of predicting the future first-stage price of the industrial raw materials, the integrated price prediction model which can effectively combine the advantages of the time series model and the LSTM model is adopted to predict the price of the industrial raw materials.
The embodiments described above are merely illustrative, and may or may not be physically separate, if referring to units illustrated as separate components; if reference is made to a component displayed as a unit, it may or may not be a physical unit, and may be located in one place or distributed over a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: modifications of the technical solutions described in the embodiments or equivalent replacements of some technical features may still be made. And such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
The present invention is not limited to the above-described alternative embodiments, and various other forms of products can be obtained by anyone in light of the present invention. The above detailed description should not be taken as limiting the scope of the invention, which is defined in the claims, and which the description is intended to be interpreted accordingly.
Claims (10)
1. A method for predicting the price of industrial raw materials is characterized by comprising the following steps: the method comprises the following steps:
acquiring environmental data to be predicted and historical data of industrial raw materials to be predicted;
inputting the environmental data to be predicted and the historical data of the industrial raw materials to be predicted into a preset price prediction model to obtain the predicted price of the current industrial raw materials to be predicted, wherein the price prediction model is obtained based on an environmental data training set and a historical data training set of the industrial raw materials.
2. The method for predicting the price of industrial raw material according to claim 1, wherein: the price prediction model is obtained by the following steps:
acquiring a plurality of historical environmental data as an environmental data training set, and acquiring a plurality of historical data of industrial raw materials as a historical data training set of the industrial raw materials;
acquiring the latest price of the industrial raw materials, taking an environmental data training set and a historical data training set of the industrial raw materials as training data, and taking the latest price of the industrial raw materials as verification data;
inputting training data into a machine learning algorithm to respectively obtain a time sequence model and a recurrent neural network model;
respectively calculating the weight of the time series model and the weight of the recurrent neural network model based on the check data;
and (4) integrating the time series model and the corresponding weight thereof with the recurrent neural network model and the corresponding weight thereof to obtain a price prediction model.
3. The method for predicting the price of industrial raw material according to claim 2, wherein: when training data is input into a machine learning algorithm to obtain a time series model, the specific steps are as follows:
processing an environmental data training set and a historical data training set of industrial raw materials to obtain time sequence data;
judging whether the current time sequence data are stable time sequence data or not, if so, establishing an autocorrelation function and a partial autocorrelation function, and if not, performing difference-based smoothing on the non-stable time sequence data to obtain stable time sequence data, and then establishing the autocorrelation function and the partial autocorrelation function;
and establishing a corresponding time series model according to the states of the autocorrelation function and the partial autocorrelation function.
4. The method for predicting the price of industrial raw material according to claim 3, wherein: when a corresponding time series model is established according to the states of the autocorrelation function and the partial autocorrelation function, the specific steps are as follows:
judging the states of the autocorrelation function and the partial autocorrelation function;
when the partial autocorrelation function is in a truncated state and the autocorrelation function is in a trailing state, establishing an autoregressive model as shown in formula 1:
when the partial autocorrelation function is in a tail state and the autocorrelation function is in a truncated state, a moving average model as shown in formula 2 is established:
Xt＝μ+Ut+θ1Ut-1+θ2Ut-2+…+θpUt-q
equation 2
When the partial autocorrelation function and the autocorrelation function are both in a trailing state, a difference integration moving average autoregressive model shown in formula 3 is established:
in the formula of UtIs a white noise sequence, δ is a constant, WtIs XtDifference calculation ofSeed, XtIndicates the value of the t-th stage.
5. The method for predicting the price of industrial raw material according to claim 4, wherein: the recurrent neural network model is a time recurrent neural network model based on long-term and short-term memory.
6. The method for predicting the price of industrial raw material according to claim 5, wherein: when the weight of the time series model and the weight of the recurrent neural network model are respectively calculated based on the check data, the specific steps are as follows:
obtaining a first check price of the latest period of the industrial raw materials through a time series model, and then comparing the first check price with check data to obtain a first difference value between the first check price and the check data;
obtaining a second check price of the industrial raw material in the latest period through a recurrent neural network model, and then comparing the second check price with the check data to obtain a second difference value between the second check price and the check data;
calculating the weight of the time series model:
calculating weights of the recurrent neural network model:
in the formula, valuetimeIs the absolute value of a first difference between the first check price and the check data, valuelstmIs the absolute value of a second difference between the second check price and the check data, wtimeIs a weight of the time series model, wlstmAre weights of the recurrent neural network model.
7. The method for predicting the price of industrial raw material according to claim 6, wherein: when the future first-stage price of the current industrial raw materials to be predicted is obtained, the method comprises the following specific steps:
respectively inputting environmental data to be predicted and historical data of industrial raw materials to be predicted into a time series model and a recurrent neural network model to obtain a first predicted price based on the time series model and a second predicted price based on the recurrent neural network model;
calculating a predicted price for the future period of the industrial raw material according to the first predicted price and the second predicted price:
prediction＝wtime*predictiontime+wlstm*predictionlstm
equation 6
Wherein the prediction is the future first-stage predicted price of the industrial raw materialtimeFor the first predicted price based on a time series model, predictionlstmIs a second predicted price based on the recurrent neural network model.
8. The method for predicting prices of industrial raw materials according to any one of claims 1 to 7, wherein: the environmental data to be predicted and the historical environmental data comprise overall market environmental data and industrial market environmental data; the overall market environment data includes a total domestic production value; the industrial market environmental data includes a procurement manager index and a producer price index.
9. The method for predicting the price of industrial raw material according to claim 8, wherein: the historical data of the industrial raw materials comprises the exchange rate of the money of the importer of the main industrial raw materials to the Renminbi, the historical price of the main industrial raw materials, the historical future price of the main industrial raw materials, the historical price of the related industrial raw materials and the historical future price of the related industrial raw materials.
10. The method for predicting the price of industrial raw material according to claim 9, wherein: after the environmental data to be predicted and the historical data of the industrial raw materials to be predicted are input into a preset price prediction model, the historical price of the main industrial raw materials obtains a first predicted price based on the time series model through the time series model, and the domestic total production value, the purchasing manager index, the producer price index, the exchange rate of the money of the import country of the main industrial raw materials for exchanging the Renminbi, the historical price of the main industrial raw materials, the historical future price of the main industrial raw materials, the historical price of the associated industrial raw materials and the historical future price of the associated industrial raw materials obtain a second predicted price based on the recurrent neural network model through the recurrent neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911103073.2A CN110827091A (en) | 2019-11-12 | 2019-11-12 | Industrial raw material price prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911103073.2A CN110827091A (en) | 2019-11-12 | 2019-11-12 | Industrial raw material price prediction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110827091A true CN110827091A (en) | 2020-02-21 |
Family
ID=69554367
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911103073.2A Pending CN110827091A (en) | 2019-11-12 | 2019-11-12 | Industrial raw material price prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110827091A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507767A (en) * | 2020-04-17 | 2020-08-07 | 无锡雪浪数制科技有限公司 | Iron and steel raw material purchasing and supplying optimization method |
| CN111563774A (en) * | 2020-05-08 | 2020-08-21 | 上海腾暨物联网科技有限公司 | Method and system for constructing coal price index prediction and supply-demand relation index |
| CN112488496A (en) * | 2020-11-27 | 2021-03-12 | 山东浪潮通软信息科技有限公司 | Financial index prediction method and device |
| CN113095604A (en) * | 2021-06-09 | 2021-07-09 | 平安科技（深圳）有限公司 | Fusion method, device and equipment of product data and storage medium |
-
2019
- 2019-11-12 CN CN201911103073.2A patent/CN110827091A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111507767A (en) * | 2020-04-17 | 2020-08-07 | 无锡雪浪数制科技有限公司 | Iron and steel raw material purchasing and supplying optimization method |
| CN111563774A (en) * | 2020-05-08 | 2020-08-21 | 上海腾暨物联网科技有限公司 | Method and system for constructing coal price index prediction and supply-demand relation index |
| CN112488496A (en) * | 2020-11-27 | 2021-03-12 | 山东浪潮通软信息科技有限公司 | Financial index prediction method and device |
| CN113095604A (en) * | 2021-06-09 | 2021-07-09 | 平安科技（深圳）有限公司 | Fusion method, device and equipment of product data and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110827091A (en) | Industrial raw material price prediction method | |
| CN112034789B (en) | Health assessment method, system and assessment terminal for key parts and complete machine of numerical control machine tool | |
| Clements et al. | Forecasting economic and financial time-series with non-linear models | |
| Decaluwé et al. | Measuring poverty and inequality in a computable general equilibrium model | |
| US11900255B2 (en) | Multi-mode smelting method based on the classification system of molten iron | |
| He et al. | Forecasting energy consumption in Anhui province of China through two Box-Cox transformation quantile regression probability density methods | |
| CN102855634A (en) | Image detection method and image detection device | |
| CN108875118B (en) | Method and device for evaluating accuracy of prediction model of silicon content of blast furnace molten iron | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| CN115660724A (en) | Electricity price prediction method coupled with carbon price | |
| CN105825290A (en) | Electric quantity prediction method based on industrial chain product output | |
| JP6955287B2 (en) | Fraudulent Stock Trading Detection Program | |
| CN117422374A (en) | Canteen intelligent purchasing method based on big data technology, electronic equipment and medium | |
| Pourmousavi et al. | Evaluating the performance of feature selection techniques and machine learning algorithms on future residential water demand | |
| CN107679659A (en) | Infant industry electricity demand forecasting method | |
| CN111985714A (en) | Pork price prediction method and system based on correlation analysis and machine learning | |
| Härting et al. | Cost-benefit considerations for data analytics-an SME-oriented framework enhanced by a management perspective and the process of idea generation | |
| CN114169730A (en) | Machine learning-based urban garbage classification work evaluation method and system | |
| CN113779391A (en) | Intelligent lock unlocking recommendation method, system and device based on modeling and storage medium | |
| TW202213239A (en) | A predicting the trend of stock prices and trade advising system based on neural networks of analyzing multiple technical analysis indicators | |
| CN113011748A (en) | Recommendation effect evaluation method and device, electronic equipment and readable storage medium | |
| Editya et al. | Effect of Kernel in Support Vector Regression Method to Predict Surabaya Consumer Price Index Trend | |
| CN102034211A (en) | Statistical method for displaying inversion point of stock data by combining computer platform with Hurst model | |
| CN115222113B (en) | CNN-LSTM-based railway area freight volume short-term prediction method | |
| CN108009924A (en) | A kind of finance Real-time Decision transaction AI robots |
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: 20200221 |
|
| RJ01 | Rejection of invention patent application after publication |