CN112819220A - Manufacturing green transformation gradient propulsion prediction method, device, equipment and medium - Google Patents
Manufacturing green transformation gradient propulsion prediction method, device, equipment and medium Download PDFInfo
- Publication number
- CN112819220A CN112819220A CN202110118439.4A CN202110118439A CN112819220A CN 112819220 A CN112819220 A CN 112819220A CN 202110118439 A CN202110118439 A CN 202110118439A CN 112819220 A CN112819220 A CN 112819220A
- Authority
- CN
- China
- Prior art keywords
- gradient
- variance
- distribution rule
- data
- mean
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 183
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 84
- 230000009466 transformation Effects 0.000 title claims abstract description 61
- 230000008569 process Effects 0.000 claims abstract description 129
- 238000009826 distribution Methods 0.000 claims abstract description 77
- 230000008859 change Effects 0.000 claims abstract description 42
- 238000004458 analytical method Methods 0.000 claims abstract description 39
- 230000007704 transition Effects 0.000 claims description 31
- 238000004590 computer program Methods 0.000 claims description 11
- 238000007476 Maximum Likelihood Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000008901 benefit Effects 0.000 abstract description 9
- 230000004927 fusion Effects 0.000 abstract description 7
- 230000010354 integration Effects 0.000 abstract description 7
- 238000006243 chemical reaction Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000005654 stationary process Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000005309 stochastic process Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Computational Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Educational Administration (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Mathematical Analysis (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Manufacturing & Machinery (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Algebra (AREA)
Abstract
The application discloses a manufacturing green transformation gradient propulsion prediction method, a device, equipment and a medium, comprising the following steps: acquiring index data of a first time stage of a gradient propulsion process capable of reflecting green transformation of manufacturing industry to obtain target data; determining a first distribution rule of the gradient propulsion process in a first time stage based on the target data, and predicting a second distribution rule of the gradient propulsion process in a second time stage by using a preset prediction model; analyzing the first distribution rule and the second distribution rule to obtain an analysis result representing the trend change of the gradient propulsion process; the gradient advancement process is evaluated based on the analysis results. According to the method, the nonlinear modeling is carried out on the nonlinear problem of green transformation gradient propulsion of the manufacturing industry, so that the gradient propulsion process of the manufacturing industry is predicted and evaluated, accurate description is established on the green transformation gradient propulsion of the manufacturing industry on the basis, and regional integration and regional innovation benefit fusion are realized.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method, a device, equipment and a medium for predicting green transformation gradient propulsion in manufacturing industry.
Background
The green transformation is an important means for realizing the upgrading of the manufacturing industry and the performance improvement of enterprises under the background of promoting the double circulation and constructing a complete internal requirement system. The industrial gradient and the economic gradient exist in different countries or regions, the technical and economic potential difference exists when the gradients exist, and the space lapse of the productivity is formed by the power of the technical and economic lapse. The trend of economic development is to move from developed areas to less developed areas and then to laggard areas, and industries in high-gradient areas will spontaneously move to areas on lower gradients. In the green transformation process, public policies are formulated according to economic development levels of different regions, and the policies are classified and differentially and gradiently promoted and implemented. Specifically, the advantages of labor cost are brought into play, a specific industry is developed, and an absolute gradient is formed; exerting comparative advantages, developing special agriculture and forming relative gradient; the indirect gradient is formed by comprehensive development and intrinsic endowment of elements.
Therefore, the accurate description is established for the green transformation gradient promotion process of the manufacturing industry, and only if the accurate description is established for the gradient promotion important process, the regional integration can be better realized, a more reasonable regional development mode is created, a new innovative development mode is created, the growth linkage is realized, the regional innovation benefit fusion is realized, and the enterprise is integrated into the global green trend. In the prior art, linear models are mostly adopted for analysis, but the nonlinear problem of green transformation gradient propulsion in the manufacturing industry cannot be accurately fitted with the linear models, so that the analysis result has deviation from the actual propulsion process.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, a device, and a storage medium for predicting a green transformation gradient advancement in manufacturing industry, which can perform a nonlinear modeling on a nonlinear problem of the green transformation gradient advancement in manufacturing industry so as to predict and evaluate a gradient advancement process of the manufacturing industry, and on the basis, establish an accurate description on the green transformation gradient advancement in manufacturing industry, thereby implementing regional integration and regional innovation benefit fusion. The specific scheme is as follows:
a first aspect of the present application provides a manufacturing green transition gradient prediction method, including:
acquiring index data of a first time stage of a gradient propulsion process capable of reflecting green transformation of manufacturing industry to obtain target data;
determining a first distribution rule of the gradient propulsion process in the first time stage based on the target data, and predicting a second distribution rule of the gradient propulsion process in a second time stage by using a preset prediction model;
analyzing the first distribution rule and the second distribution rule to obtain an analysis result representing the trend change of the gradient propulsion process;
evaluating the gradient advancement process based on the analysis result.
Optionally, the obtaining of the first time stage index data reflecting the gradient advancing process of the green transition of the manufacturing industry to obtain the target data includes:
determining an index capable of reflecting a gradient advancing process of green transformation of manufacturing industry, and acquiring first time stage index data corresponding to the index;
decomposing the first time stage index data through wavelet transformation, and determining middle-order and/or low-order data of the decomposed first time stage index data as target data.
Optionally, the determining, based on the target data, a first distribution rule of the gradient propulsion process in the first time period, and predicting, by using a preset prediction model, a second distribution rule of the gradient propulsion process in a second time period includes:
calculating the mean value and the variance of the target data to obtain a first mean value and a first variance;
and determining the mean and the variance of the gradient advancing process in the second time phase by utilizing a hidden Markov model to obtain a second mean and a second variance.
Optionally, the determining, by using a hidden markov model, a mean and a variance of the gradient advance process in the second time period to obtain a second mean and a second variance includes:
estimating target parameters in a Markov model by a maximum likelihood estimation method, and determining the transition probability according to the estimation of the target parameters;
a second mean and a second variance of the gradient advance over a second time period are calculated based on the transition probabilities.
Optionally, the predicting a second distribution rule of the gradient propulsion process in a second time phase by using a preset prediction model includes:
and predicting a second mean and a second variance of the gradient propulsion process in a second time phase by using a prediction model constructed based on the BP neural network.
Optionally, the analyzing the first distribution rule and the second distribution rule to obtain an analysis result representing a trend change of the gradient advancing process includes:
and inputting the first mean value, the second mean value, the first variance and the second variance into a mean variance double-variable-point model so that the mean variance double-variable-point model outputs mean variable-point data and variance variable-point data for representing the trend change of the gradient propulsion process.
Optionally, the evaluating the gradient advancing process based on the analysis result includes:
and evaluating the gradient propulsion process based on the mean variable point data and/or the variance variable point data.
A second aspect of the present application provides a manufacturing green transition gradient advancement prediction device, including:
the system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for acquiring first time stage index data of a gradient propulsion process capable of reflecting green transformation of the manufacturing industry so as to obtain target data;
the determining module is used for determining a first distribution rule of the gradient propulsion process in the first time stage based on the target data and predicting a second distribution rule of the gradient propulsion process in the second time stage by using a preset prediction model;
the analysis module is used for analyzing the first distribution rule and the second distribution rule to obtain an analysis result representing the trend change of the gradient propulsion process;
and the evaluation module is used for evaluating the gradient propulsion process based on the analysis result.
A third aspect of the application provides an electronic device comprising a processor and a memory; wherein the memory is used for storing a computer program which is loaded and executed by the processor to realize the manufacturing green transition gradient advancing prediction method.
A fourth aspect of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored, and when being loaded and executed by a processor, the computer-executable instructions implement the foregoing manufacturing green transition gradient advancement prediction method.
According to the method, index data of a first time stage of a gradient propulsion process capable of reflecting green transformation of the manufacturing industry are firstly obtained to obtain target data, then a first distribution rule of the gradient propulsion process in the first time stage is determined based on the target data, a second distribution rule of the gradient propulsion process in a second time stage is predicted by utilizing a preset prediction model, the first distribution rule and the second distribution rule are analyzed finally to obtain an analysis result representing trend change of the gradient propulsion process, and the gradient propulsion process is evaluated based on the analysis result. According to the method, the nonlinear modeling is carried out on the nonlinear problem of green transformation gradient propulsion of the manufacturing industry, so that the gradient propulsion process of the manufacturing industry is predicted and evaluated, accurate description is established on the green transformation gradient propulsion of the manufacturing industry on the basis, and regional integration and regional innovation benefit fusion are realized.
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 embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
FIG. 1 is a flow chart of a method for predicting a green transformation gradient advancement in manufacturing industry according to the present application;
FIG. 2 is a schematic diagram of a gradient push prediction method for green transformation in manufacturing industry according to an embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a green transformation gradient measurement process based on wavelet transform according to the present application;
FIG. 4 is a schematic structural diagram of a green transition gradient propulsion prediction apparatus for manufacturing industry according to the present application;
FIG. 5 is a block diagram of a manufacturing green transition gradient advancement prediction electronics configuration provided by the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the prior art, a linear model is mostly adopted to analyze the gradient propulsion process, but the linear model cannot be accurately fitted to the nonlinear problem of green transformation gradient propulsion in the manufacturing industry, so that the analysis result has deviation from the actual propulsion process. Aiming at the technical defects, the method can perform nonlinear modeling aiming at the nonlinear problem of green transformation gradient propulsion of the manufacturing industry so as to predict and evaluate the gradient propulsion process of the manufacturing industry, and on the basis, accurate description is established for the green transformation gradient propulsion of the manufacturing industry, so that regional integration and regional innovation benefit fusion are realized.
Fig. 1 is a flowchart of a gradient advancement prediction for green transformation in manufacturing industry according to an embodiment of the present application. Referring to fig. 1, the manufacturing green transition gradient advance prediction method includes:
s11: and acquiring index data of a first time stage of a gradient propulsion process capable of reflecting green transformation of the manufacturing industry to obtain target data.
In this embodiment, the first time stage index data of the gradient advancing process that can reflect the green transformation of the manufacturing industry is obtained to obtain the target data. It is understood that there are many indexes that can reflect the gradient advancement process of green transformation in manufacturing industry, and the scheme only selects one index that can meet the analysis requirement to describe the gradient advancement of green transformation in manufacturing industry, and the selection of the index is not limited in this embodiment. After acquiring the first-time-stage index data, if the first-time-stage index data is more standard and can meet the analysis requirement, directly determining the first-time-stage index data as the target data, but if the first-time-stage index data is more dispersed and disordered or has a higher requirement on the accuracy of a prediction and analysis result, filtering the first-time-stage index data to obtain data more meeting the analysis requirement, and determining the filtered first-time-stage index data as the target data.
S12: and determining a first distribution rule of the gradient propulsion process in the first time stage based on the target data, and predicting a second distribution rule of the gradient propulsion process in a second time stage by using a preset prediction model.
In this embodiment, after the target data is acquired, based on the target data, a first distribution rule of the gradient propulsion process in the first time period is determined, and a second distribution rule of the gradient propulsion process in the second time period is predicted by using a preset prediction model. The data analysis of the gradient advancement of the green transformation of the manufacturing industry essentially searches for the change of statistics in the data to judge the green transformation process, so that the first distribution rule and the second distribution rule are essentially statistical rules of the gradient advancement of the green transformation of the manufacturing industry, and in the field of statistics, the mathematical quantities reflecting the statistical rules are many, including but not limited to mean values, variances, standard deviations, covariances and the like, as long as the distribution rules of the gradient advancement of the green transformation of the manufacturing industry can be reflected. It should be noted that the mathematical quantity used to represent the first distribution rule should be consistent with the mathematical quantity used to represent the second distribution rule, for example, when the first distribution rule is represented by a mean value, the second distribution rule should also be represented by a mean value. In addition, simple random variables may be subjected to temporal distribution or spatial distribution, but in the analysis of the green conversion gradient advancing process, both the temporal dimension and the spatial dimension need to be considered.
S13: and analyzing the first distribution rule and the second distribution rule to obtain an analysis result representing the trend change of the gradient propulsion process.
S14: evaluating the gradient advancement process based on the analysis result.
In this embodiment, the first distribution rule and the second distribution rule are analyzed to obtain an analysis result representing a trend change of the gradient propulsion process. The first distribution rule and the second distribution rule are analyzed, namely the change points of the first distribution rule and the change points of the second distribution rule are analyzed, the change points can also be called abnormal points, and the change points refer to the points where some quantity or some quantities in some lines of data change suddenly, and the change points can better reflect the essence of things than the stable statistic quantity. And analyzing the first distribution rule and the second distribution rule to obtain a change point in the trend change of the gradient propulsion process, and evaluating the gradient propulsion process by utilizing the change point and integrating the green transformation objective development condition and a corresponding policy.
It can be seen that, in the embodiment of the application, first time stage index data of a gradient propulsion process capable of reflecting green transformation of manufacturing industry is obtained to obtain target data, then, based on the target data, a first distribution rule of the gradient propulsion process in the first time stage is determined, a second distribution rule of the gradient propulsion process in the second time stage is predicted by using a preset prediction model, and finally, the first distribution rule and the second distribution rule are analyzed to obtain an analysis result representing trend change of the gradient propulsion process, and the gradient propulsion process is evaluated based on the analysis result. According to the method, the nonlinear modeling is carried out on the nonlinear problem of green transformation gradient propulsion of the manufacturing industry, so that the gradient propulsion process of the manufacturing industry is predicted and evaluated, accurate description is established on the green transformation gradient propulsion of the manufacturing industry on the basis, and regional integration and regional innovation benefit fusion are realized.
Fig. 2 is a flowchart of a specific gradient advancement prediction method for green transformation in manufacturing industry according to an embodiment of the present application. Referring to fig. 2, the manufacturing green transition gradient advance prediction method includes:
s21: determining an index capable of reflecting a gradient advancing process of green transformation of manufacturing industry, and acquiring first time stage index data corresponding to the index.
In this embodiment, the total amount of green patent conversion in the manufacturing industry is used as an index that can reflect the gradient propulsion process of green conversion in the manufacturing industry, and the green patent refers to an invention, a utility model, and an appearance design patent that take green technologies such as resource saving, energy efficiency improvement, pollution prevention and control as the subject of the invention. And then acquiring first time stage index data corresponding to the index, wherein the index data is the total green patent conversion amount, and it should be noted that when only the time dimension is considered, the total green patent conversion amount of the same region in the first time stage can be acquired, but if the space dimension is considered at the same time, the total green patent conversion amount of different regions in the first time stage needs to be acquired to perform multiple analysis.
S22: decomposing the first time stage index data through wavelet transformation, and determining middle-order and/or low-order data of the decomposed first time stage index data as target data.
In this embodiment, in the prediction process, a wavelet transform method may be used to filter the first time stage index data, specifically, the first time stage index data is decomposed by the wavelet transform, and the middle-order and/or low-order data of the decomposed first time stage index data is determined as target data, that is, the change of the statistic in the data is found by the wavelet transform, so as to determine the green transformation process. For the change of green performance, which may be influenced by many external factors, in this embodiment, wavelet transform is used to decompose data, process high-order parts, and process and analyze data using low-order parts. The wavelet in the wavelet transform is also called as a wavelet, has faster attenuation and volatility, and is expressed by a formula:
wherein a is a scale factor, a ≠ 0, b is a time shift factor, and h (t) is a mother wavelet. In the above formula:
wherein h isa,b(t) is the wavelet basis function. For example, the total amount of green patent conversions in each region in recent years can be used as a column of a matrix, the matrix is integrated, wavelet filtering is performed, and the search is performedThe specific process of low order change is shown in fig. 3.
S23: and calculating the mean and the variance of the target data to obtain a first mean and a first variance.
S24: and determining the mean and the variance of the gradient advancing process in the second time phase by utilizing a hidden Markov model to obtain a second mean and a second variance.
In this embodiment, the mean and the variance are used as statistics that can reflect the distribution rule of the gradient advancement process of the green transition in the manufacturing industry, and the mean and the variance of the target data are calculated to obtain a first mean and a first variance. And determining the mean and the variance of the gradient propulsion process in a second time phase by using a hidden Markov model based on the target data to obtain a second mean and a second variance. Based on the hidden Markov process, the modeling of green transformation gradient propulsion of the manufacturing industry can be better realized.
Hidden Markov Models (HMMs) are statistical models, which are a type of Markov chain, that describe a Markov process with Hidden unknown parameters, whose states cannot be observed directly, but can be observed through a sequence of observation vectors, each of which is represented as a state by some probability density distribution, each of which is generated from a sequence of states with a corresponding probability density distribution. The difficulty in hidden markov models is therefore a dual stochastic process with a hidden markov chain of a certain number of states and a set of display stochastic functions, in determining the hidden parameters of the process from the observable parameters and then using these parameters for further analysis, such as pattern recognition. In simple markov models, such as markov chains, the states are directly visible observers, and therefore the state transition probabilities are the only parameters. In hidden markov models, states are not directly visible, but the output depends on the state, each state having a possible probability distribution by means of possible output tokens. Thus, the generation of a sequence of labels by an HMM provides information about some sequence of states. It is noted that "hidden" means that the sequence of states through which the model is passed is not visible, rather than the parameters of the model being hidden, and we refer to the model as a "hidden" markov model even if the parameters are precisely known. Hidden markov models have been generalized to pairwise markov models and triplet markov models, allowing for more complex data structure considerations and non-stationary data modeling.
The specific steps of determining the mean and the variance of the gradient advance process in the second time period by using the hidden markov model to obtain the second mean and the second variance are as follows, firstly estimating a target parameter in the markov model by using a maximum likelihood estimation method, determining a transition probability according to the estimation of the target parameter, then calculating the second mean and the second variance of the gradient advance in the second time period based on the transition probability, and calculating the mean and the variance according to the probability is a conventional method, which is not described in detail in this embodiment. It should be noted that, in this embodiment, the maximum likelihood function is used to estimate parameters in the hidden markov model process, and compared with the least square method, the minimum variance unbiased estimation can be achieved under the gaussian error, and the robustness of the maximum likelihood method is far better than that of the least square estimation method. The maximum likelihood method is a relatively general probability estimation method, and the basic idea is to construct a function for linking unknown parameters and observed data, namely a likelihood function. When the function reaches a maximum at a certain parameter value, an estimate of this parameter is obtained. The basic principle can be briefly described as follows:
let the observed value y be a random variable whose probability density p depends on the unknown parameter θ. To estimate θ from y, a value of θ is selected that maximizes the likelihood function L (y/θ) ═ p (y/θ). Namely existence of
Is the maximum value of L (y/theta), then
The probability of being an accurate value is greatest, and the scale is called
Is a maximum likelihood estimate of theta.
Setting the observed value y ∈ RmAnd random noise epsilon ∈ RmWhen { ε (k) } has a sequence of m-dimensional independent Gaussian distributions with the same covariance Σ, then the likelihood function is:
setting the residual error between the predicted value and the measurement as
The covariance thereof:
setting the observed value y ∈ RmAnd the prediction error w ∈ RmWhen { w (k) } has a sequence of m-dimensional independent gaussian distributions with the same covariance Σ, then the likelihood function is:
namely, it is
When the sigma is unknown, firstly, the least square estimation is used for obtaining
Further obtain
To find
A maximum likelihood estimate is obtained where θ can be set to the coefficients of Zernike polynomials, the basis of which is selected to be a sine function type for medium and high frequency errors. The basic property of the maximum likelihood estimation can be obtained, the equation (1) can achieve the same progressive variance no matter whether the error distribution is Gaussian or not, namely, the robustness of the maximum likelihood method is far better than that of the least square estimation method.
Further, a prediction model constructed based on the BP neural network may also be used to predict a second mean and a second variance of the gradient push process in a second time period. And taking the existing state as input, and taking the green transformation effect in the next time period as output, namely inputting the index data in the first time period to the prediction model constructed based on the BP neural network, wherein the prediction model directly outputs the second mean value and the second variance. The basic characteristic of machine learning is that the internal rules are summarized from a large amount of existing data, and the internal rules are successfully applied to new sample data outside a training set for prediction and classification. From the perspective of the method, the method can be divided into a linear model and a nonlinear model, and the nonlinear model can be divided into a traditional support vector machine, an artificial neural network, a decision tree and the like and a deep learning model. A multi-hidden-layer neural network can be established, and for a full-connection type neural network corresponding to a hidden-layer network structure, 90% of data are randomly selected as a training set and the rest 10% of data are selected as a verification set during training. In this embodiment, the hidden markov model is used to determine the mean and variance of the gradient propulsion process in the second time phase, or the BP neural network is used to determine the mean and variance of the gradient propulsion process in the second time phase, which are complementary to each other, the hidden markov model is a rule-driven model, which is suitable for the case of less data, and the neural network method is data-driven, which is suitable for the case of more data accumulation.
S25: and inputting the first mean value, the second mean value, the first variance and the second variance into a mean variance double-variable-point model so that the mean variance double-variable-point model outputs mean variable-point data and variance variable-point data for representing the trend change of the gradient propulsion process.
S26: and evaluating the gradient propulsion process based on the mean variable point data and/or the variance variable point data.
In this embodiment, the solution of the change point is based on a "mean variance double change point" model suitable for green transformation gradient propulsion, and the first mean, the second mean, the first variance and the second variance are input into a mean variance double change point model, so that the mean variance double change point model outputs mean change point data and variance change point data for representing the trend change of the gradient propulsion process. In previous researches, mostly, a correlation error model of a stationary process is adopted, and gradient boosting is a very typical 'mean variance double-change-point' problem, and a change-point model is a simple hypothesis test which can be expressed as 'whether to change'. Let X1，X2，…，XnIndependent of each other and subject to variance σ2Normal distribution of (a), original hypothesis H: EX1＝EX2＝…＝EXnAnd DX1＝DX2＝…＝DXn(ii) a The opposite assumption K: EX1＝…＝EXm-1＝a1， EX2＝…＝EXn＝a2And a is1≠a2Or
And sigma1≠σ2Where m is referred to as a change point, i.e., a point at which it changes abruptly, when there are multiple change points, the sequence can be piecewise modeled using dichotomy.
Therefore, the method and the device determine the total green patent conversion sum as index data capable of reflecting the gradient propulsion process of green conversion in the manufacturing industry, acquire the medium-low order data of the total green patent conversion sum by utilizing wavelet transformation, determine the variable point data of the mean value and the variance by using a hidden Markov model and a mean variance bilateral point model on the basis, and evaluate the gradient propulsion process of green conversion in the manufacturing industry based on the variable point data. By the method, the green transformation gradient propulsion process of the manufacturing industry is predicted and evaluated, the accuracy of a prediction result is improved, and the green transformation gradient propulsion process of the manufacturing industry can be accurately controlled.
Referring to fig. 4, the embodiment of the present application further discloses a manufacturing green transition gradient advancement prediction apparatus, which includes:
the acquisition module 11 is configured to acquire first time stage index data that can reflect a gradient propulsion process of green transformation in manufacturing industry, so as to obtain target data;
a determining module 12, configured to determine, based on the target data, a first distribution rule of the gradient propulsion process in the first time period, and predict, by using a preset prediction model, a second distribution rule of the gradient propulsion process in a second time period;
the analysis module 13 is configured to analyze the first distribution rule and the second distribution rule to obtain an analysis result representing a trend change of the gradient propulsion process;
an evaluation module 14 for evaluating the gradient propulsion process based on the analysis result.
It can be seen that, in the embodiment of the application, first time stage index data of a gradient propulsion process capable of reflecting green transformation of manufacturing industry is obtained to obtain target data, then, based on the target data, a first distribution rule of the gradient propulsion process in the first time stage is determined, a second distribution rule of the gradient propulsion process in the second time stage is predicted by using a preset prediction model, and finally, the first distribution rule and the second distribution rule are analyzed to obtain an analysis result representing trend change of the gradient propulsion process, and the gradient propulsion process is evaluated based on the analysis result. According to the method, the nonlinear modeling is carried out on the nonlinear problem of green transformation gradient propulsion of the manufacturing industry, so that the gradient propulsion process of the manufacturing industry is predicted and evaluated, accurate description is established on the green transformation gradient propulsion of the manufacturing industry on the basis, and regional integration and regional innovation benefit fusion are realized.
In some specific embodiments, the obtaining module 11 specifically includes:
the index unit is used for determining an index capable of reflecting the gradient propulsion process of green transformation of the manufacturing industry and acquiring first time stage index data corresponding to the index;
and the decomposition unit is used for decomposing the first time stage index data through wavelet transformation and determining middle-order and/or low-order data of the decomposed first time stage index data as target data.
In some specific embodiments, the determining module 12 specifically includes:
the first determining unit is used for calculating the mean value and the variance of the target data to obtain a first mean value and a first variance;
the second determining unit is used for determining the mean value and the variance of the gradient propulsion process in a second time phase by utilizing a hidden Markov model so as to obtain a second mean value and a second variance; or predicting a second mean and a second variance of the gradient advancing process in a second time phase by using a prediction model constructed based on the BP neural network.
In some embodiments, the analysis module 13 is specifically configured to input the first mean, the second mean, the first variance and the second variance into a mean-variance-bivariate model, so that the mean-variance-bivariate model outputs mean-variance data and variance-variance data for characterizing a trend change of the gradient thrust process;
correspondingly, the evaluation module 14 is specifically configured to evaluate the gradient propulsion process based on the mean value change point data and/or the variance change point data.
Further, the embodiment of the application also provides electronic equipment. FIG. 5 is a block diagram illustrating an electronic device 20 according to an exemplary embodiment, and the contents of the diagram should not be construed as limiting the scope of use of the present application in any way.
Fig. 5 is a schematic structural diagram of an electronic device 20 according to an embodiment of the present disclosure. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input output interface 25, and a communication bus 26. Wherein, the memory 22 is used for storing a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the manufacturing green transition gradient advancing prediction method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in the present embodiment may be specifically a portable computer.
In this embodiment, the power supply 23 is configured to provide a working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and an external device, and a communication protocol followed by the communication interface is any communication protocol applicable to the technical solution of the present application, and is not specifically limited herein; the input/output interface 25 is configured to obtain external input data or output data to the outside, and a specific interface type thereof may be selected according to specific application requirements, which is not specifically limited herein.
In addition, the storage 22 is used as a carrier for resource storage, and may be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., and the resources stored thereon may include the operating system 221, the computer program 222, the index data 223, etc., and the storage manner may be a transient storage or a permanent storage.
The operating system 221 is used for managing and controlling each hardware device and the computer program 222 on the electronic device 20, so as to realize the operation and processing of the processor 21 on the mass index data 223 in the memory 22, and may be Windows Server, Netware, Unix, Linux, or the like. The computer program 222 may further include a computer program that can be used to perform other specific tasks in addition to the computer program that can be used to perform the manufacturing green transition gradient advancement prediction method performed by the electronic device 20 disclosed in any of the foregoing embodiments. Data 223 may include metric data collected by electronic device 20.
Further, the embodiment of the present application also discloses a storage medium, in which a computer program is stored, and when the computer program is loaded and executed by a processor, the steps of the manufacturing green transition gradient push prediction method disclosed in any of the foregoing embodiments are implemented.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The method, the apparatus, the device and the storage medium for predicting the green transformation gradient advancement in manufacturing industry provided by the present invention are described in detail above, and the principle and the implementation manner of the present invention are explained in this document by applying specific examples, and the description of the above examples is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A manufacturing green transition gradient advancement prediction method, comprising:
acquiring index data of a first time stage of a gradient propulsion process capable of reflecting green transformation of manufacturing industry to obtain target data;
determining a first distribution rule of the gradient propulsion process in the first time stage based on the target data, and predicting a second distribution rule of the gradient propulsion process in a second time stage by using a preset prediction model;
analyzing the first distribution rule and the second distribution rule to obtain an analysis result representing the trend change of the gradient propulsion process;
evaluating the gradient advancement process based on the analysis result.
2. The manufacturing green transition gradient prediction method according to claim 1, wherein the obtaining of the first time period index data reflecting the gradient advancing process of the manufacturing green transition to obtain the target data comprises:
determining an index capable of reflecting a gradient advancing process of green transformation of manufacturing industry, and acquiring first time stage index data corresponding to the index;
decomposing the first time stage index data through wavelet transformation, and determining middle-order and/or low-order data of the decomposed first time stage index data as target data.
3. The manufacturing green transition gradient prediction method of claim 2, wherein the determining a first distribution rule of the gradient advancement process in the first time period based on the target data and predicting a second distribution rule of the gradient advancement process in a second time period by using a preset prediction model comprises:
calculating the mean value and the variance of the target data to obtain a first mean value and a first variance;
and determining the mean and the variance of the gradient advancing process in the second time phase by utilizing a hidden Markov model to obtain a second mean and a second variance.
4. The manufacturing green transition gradient boost prediction method of claim 3, wherein said determining the mean and variance of said gradient boost process in the second time period using hidden Markov models to obtain a second mean and second variance comprises:
estimating target parameters in a Markov model by a maximum likelihood estimation method, and determining the transition probability according to the estimation of the target parameters;
a second mean and a second variance of the gradient advance over a second time period are calculated based on the transition probabilities.
5. The manufacturing green transition gradient prediction method of claim 2, wherein the predicting the second distribution rule of the gradient advancement process in the second time phase by using a preset prediction model comprises:
and predicting a second mean and a second variance of the gradient propulsion process in a second time phase by using a prediction model constructed based on the BP neural network.
6. The manufacturing green transition gradient prediction method according to any one of claims 3 to 5, wherein the analyzing the first distribution rule and the second distribution rule to obtain an analysis result representing a trend change of the gradient advancing process comprises:
and inputting the first mean value, the second mean value, the first variance and the second variance into a mean variance double-variable-point model so that the mean variance double-variable-point model outputs mean variable-point data and variance variable-point data for representing the trend change of the gradient propulsion process.
7. The manufacturing green transition gradient prediction method of claim 6, wherein the evaluating the gradient advancement process based on the analysis result comprises:
and evaluating the gradient propulsion process based on the mean variable point data and/or the variance variable point data.
8. A gradient advancement prediction device for green-turning in manufacturing industry, comprising:
the system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for acquiring first time stage index data of a gradient propulsion process capable of reflecting green transformation of the manufacturing industry so as to obtain target data;
the determining module is used for determining a first distribution rule of the gradient propulsion process in the first time stage based on the target data and predicting a second distribution rule of the gradient propulsion process in the second time stage by using a preset prediction model;
the analysis module is used for analyzing the first distribution rule and the second distribution rule to obtain an analysis result representing the trend change of the gradient propulsion process;
and the evaluation module is used for evaluating the gradient propulsion process based on the analysis result.
9. An electronic device, comprising a processor and a memory; wherein the memory is for storing a computer program that is loaded and executed by the processor to implement the manufacturing green transition gradient advancement prediction method as defined in any one of claims 1 to 7.
10. A computer-readable storage medium storing computer-executable instructions that, when loaded and executed by a processor, perform the gradient push prediction method for green transition in manufacturing industry according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110118439.4A CN112819220A (en) | 2021-01-28 | 2021-01-28 | Manufacturing green transformation gradient propulsion prediction method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110118439.4A CN112819220A (en) | 2021-01-28 | 2021-01-28 | Manufacturing green transformation gradient propulsion prediction method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112819220A true CN112819220A (en) | 2021-05-18 |
Family
ID=75859904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110118439.4A Pending CN112819220A (en) | 2021-01-28 | 2021-01-28 | Manufacturing green transformation gradient propulsion prediction method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112819220A (en) |
-
2021
- 2021-01-28 CN CN202110118439.4A patent/CN112819220A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10387768B2 (en) | Enhanced restricted boltzmann machine with prognosibility regularization for prognostics and health assessment | |
| Wen et al. | Stock market trend prediction using high-order information of time series | |
| Sangiorgio et al. | Robustness of LSTM neural networks for multi-step forecasting of chaotic time series | |
| Xu et al. | Accurate and interpretable bayesian mars for traffic flow prediction | |
| US8180664B2 (en) | Methods and systems for forecasting with model-based PDF estimates | |
| Ye et al. | Monte Carlo co-ordinate ascent variational inference | |
| Yang et al. | Modified grey model predictor design using optimal fractional-order accumulation calculus | |
| Nam et al. | The uncertainty of storm season changes: quantifying the uncertainty of autocovariance changepoints | |
| Baur et al. | Explainability and interpretability in electric load forecasting using machine learning techniques–A review | |
| Chen et al. | Gaussian processes with skewed Laplace spectral mixture kernels for long-term forecasting | |
| Singhania et al. | Forecasting the United States unemployment rate by using recurrent neural networks with Google Trends data | |
| CN116861373A (en) | Query selectivity estimation method, system, terminal equipment and storage medium | |
| Li et al. | A multiple long short-term model for product sales forecasting based on stage future vision with prior knowledge | |
| CN112819220A (en) | Manufacturing green transformation gradient propulsion prediction method, device, equipment and medium | |
| Wang et al. | A variational inference-based heteroscedastic Gaussian process approach for simulation metamodeling | |
| Poulos | Determining the Stationarity distance via a reversible stochastic process | |
| Pletnev et al. | Graph neural networks for model recommendation using time series data | |
| CN114674511A (en) | Bridge modal anomaly early warning method for eliminating time-varying environmental factor influence | |
| Manouchehri et al. | Periodic autoregressive models with closed skew-normal innovations | |
| US11562110B1 (en) | System and method for device mismatch contribution computation for non-continuous circuit outputs | |
| Duncan et al. | Nowcasting with numerous candidate predictors | |
| Araujo et al. | A morphological-rank-linear approach for software development cost estimation | |
| CN116402184A (en) | Prediction method and prediction system for diesel oil yield | |
| Biron-Lattes et al. | Automatic regenerative simulation via non-reversible simulated tempering | |
| CN117875094B (en) | Precision evaluation method and device for engine simulation model and electronic equipment |
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 |