CN112200443A - Logistics node layout optimization method and system based on agricultural product cold-chain logistics demand - Google Patents
Logistics node layout optimization method and system based on agricultural product cold-chain logistics demand Download PDFInfo
- Publication number
- CN112200443A CN112200443A CN202011064782.7A CN202011064782A CN112200443A CN 112200443 A CN112200443 A CN 112200443A CN 202011064782 A CN202011064782 A CN 202011064782A CN 112200443 A CN112200443 A CN 112200443A
- Authority
- CN
- China
- Prior art keywords
- agricultural product
- predicted
- chain logistics
- product cold
- variable
- 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 74
- 238000005457 optimization Methods 0.000 title claims abstract description 32
- 238000013528 artificial neural network Methods 0.000 claims abstract description 33
- 238000012417 linear regression Methods 0.000 claims abstract description 24
- 238000012216 screening Methods 0.000 claims abstract description 24
- 230000015654 memory Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 16
- 238000000513 principal component analysis Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 5
- 235000012055 fruits and vegetables Nutrition 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000007306 turnover Effects 0.000 claims description 2
- 238000003062 neural network model Methods 0.000 description 7
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 235000013601 eggs Nutrition 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 235000013336 milk Nutrition 0.000 description 2
- 239000008267 milk Substances 0.000 description 2
- 210000004080 milk Anatomy 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000012271 agricultural production Methods 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000000556 factor analysis Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 235000021022 fresh fruits Nutrition 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000012628 principal component regression Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000002945 steepest descent method Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 235000013311 vegetables 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
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- 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
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Primary Health Care (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Animal Husbandry (AREA)
- Educational Administration (AREA)
- Agronomy & Crop Science (AREA)
- Game Theory and Decision Science (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a logistics node layout optimization method and a logistics node layout optimization system based on agricultural product cold-chain logistics requirements, wherein the logistics node layout optimization method comprises the following steps: carrying out variable screening on the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted, and screening out a plurality of variables; predicting each variable to obtain predicted values of all variables; obtaining a first agricultural product cold-chain logistics demand predicted value based on all variable predicted values and a multiple linear regression model; obtaining a cold-chain logistics demand predicted value of a second agricultural product based on all variable predicted values and a pre-trained BP neural network; weighting and summing the first agricultural product cold-chain logistics demand predicted value and the second agricultural product cold-chain logistics demand predicted value to obtain a final agricultural product cold-chain logistics demand predicted value; and obtaining a scale optimization scheme of the logistics node based on a final agricultural product cold-chain logistics demand prediction value of the area to be predicted, the scale of the existing logistics node and the distance between the existing logistics node and the area to be predicted.
Description
Technical Field
The application relates to the technical field of logistics demand prediction, in particular to a logistics node layout optimization method and system based on agricultural product cold-chain logistics demand.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
In the twenty-first century today, people's change of concept and flourishing market economy gradually push out a new agricultural product circulation system, and an agricultural product market focusing on high-quality and high-efficiency agricultural product transportation and benign economy in scale has gradually formed. The traditional links of agricultural product transportation, circulation and the like can not meet the modern agricultural product market and the pursuit of people on the quality of agricultural products.
The rapid development of cold-chain logistics puts forward the increasing demands of people on products such as eggs, milk, fresh fruits, fruits and vegetables, but the inventor knows that the existing cold-chain logistics demand prediction lacks a reasonable prediction method, the prediction result is inaccurate, the production and development of the logistics industry cannot be effectively guided, and particularly the problem of site selection of logistics nodes of agricultural product cold-chain logistics and the problem of scale optimization of the existing logistics nodes cannot be scientifically and reasonably solved.
Disclosure of Invention
In order to solve the defects of the prior art, the application provides a logistics node layout optimization method and a logistics node layout optimization system based on agricultural product cold-chain logistics requirements;
in a first aspect, the application provides a logistics node layout optimization method based on agricultural product cold-chain logistics requirements;
a logistics node layout optimization method based on agricultural product cold-chain logistics requirements comprises the following steps:
carrying out variable screening on the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted, and screening out a plurality of variables;
predicting each variable to obtain predicted values of all variables;
obtaining a first agricultural product cold-chain logistics demand predicted value based on all variable predicted values and a multiple linear regression model; obtaining a cold-chain logistics demand predicted value of a second agricultural product based on all variable predicted values and a pre-trained BP neural network;
weighting and summing the first agricultural product cold-chain logistics demand predicted value and the second agricultural product cold-chain logistics demand predicted value to obtain a final agricultural product cold-chain logistics demand predicted value;
and obtaining a scale optimization scheme of the logistics node based on a final agricultural product cold-chain logistics demand prediction value of the area to be predicted, the scale of the existing logistics node and the distance between the existing logistics node and the area to be predicted.
In a second aspect, the application provides a logistics node layout optimization system based on agricultural product cold-chain logistics requirements;
logistics node layout optimization system based on agricultural product cold chain logistics demand includes:
a variable screening module configured to: carrying out variable screening on the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted, and screening out a plurality of variables;
a variable prediction module configured to: predicting each variable to obtain predicted values of all variables;
a demand prediction module configured to: obtaining a first agricultural product cold-chain logistics demand predicted value based on all variable predicted values and a multiple linear regression model; obtaining a cold-chain logistics demand predicted value of a second agricultural product based on all variable predicted values and a pre-trained BP neural network;
a weighting module configured to: weighting and summing the first agricultural product cold-chain logistics demand predicted value and the second agricultural product cold-chain logistics demand predicted value to obtain a final agricultural product cold-chain logistics demand predicted value;
an output module configured to: and obtaining a scale optimization scheme of the logistics node based on a final agricultural product cold-chain logistics demand prediction value of the area to be predicted, the scale of the existing logistics node and the distance between the existing logistics node and the area to be predicted.
In a third aspect, the present application further provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein a processor is connected to the memory, the one or more computer programs are stored in the memory, and when the electronic device is running, the processor executes the one or more computer programs stored in the memory, so as to make the electronic device execute the method according to the first aspect.
In a fourth aspect, the present application also provides a computer-readable storage medium for storing computer instructions which, when executed by a processor, perform the method of the first aspect.
In a fifth aspect, the present application also provides a computer program (product) comprising a computer program for implementing the method of any of the preceding first aspects when run on one or more processors.
Compared with the prior art, the beneficial effects of this application are:
the method comprises the steps of performing dimensionality reduction on various indexes by using principal component analysis, predicting each principal component score by using a time sequence, constructing a multivariate linear regression model and a neural network model on the basis of the principal component analysis to predict the cold-chain logistics requirements of agricultural products in a certain province, and comparing a combined prediction model of the models, so that partial reference and decision basis can be provided for the development of the cold-chain logistics industry of the agricultural products to a certain extent; the problem of site selection of the logistics nodes and the problem of scale optimization of the existing logistics nodes can be scientifically and reasonably solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a flow chart of the method of the first embodiment.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and it should be understood that the terms "comprises" and "comprising", and any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Example one
The embodiment provides a logistics node layout optimization method based on agricultural product cold-chain logistics requirements;
as shown in fig. 1, a logistics node layout optimization method based on agricultural product cold-chain logistics demand includes:
s101: carrying out variable screening on the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted, and screening out a plurality of variables;
s102: predicting each variable to obtain predicted values of all variables;
s103: obtaining a first agricultural product cold-chain logistics demand predicted value based on all variable predicted values and a multiple linear regression model;
obtaining a cold-chain logistics demand predicted value of a second agricultural product based on all variable predicted values and a pre-trained BP neural network;
s104: carrying out weighted summation on the first agricultural product cold-chain logistics demand predicted value and the second agricultural product cold-chain logistics demand predicted value to obtain a final agricultural product cold-chain logistics demand predicted value of an area to be predicted;
s105: and obtaining a scale optimization scheme of the logistics node based on a final agricultural product cold-chain logistics demand prediction value of the area to be predicted, the scale of the existing logistics node and the distance between the existing logistics node and the area to be predicted.
As one or more embodiments, the S101: performing principal component analysis on the acquired agricultural product cold-chain logistics basic data in the historical time range of the area to be predicted, and screening out a plurality of key principal components; the method also comprises the following steps of:
s100: acquiring basic data of agricultural product cold-chain logistics within the historical time range of an area to be predicted;
preprocessing the acquired basic data of the agricultural product cold-chain logistics; the pretreatment comprises the following steps: denoising processing and missing value completion processing.
Further, the agricultural product cold-chain logistics basic data comprises: the method comprises the following steps of population of the perennial population of the area to be predicted, total retail of social consumer goods, production price index of agricultural products, fruit and vegetable yield, annual freight volume of the area to be predicted and annual turnover volume of the area to be predicted.
Further, the denoising process refers to: and calculating an average value, and removing the data beyond the set range of the average value as noise data.
Further, the missing value completion processing means: the mean value is filled into the missing value data positions.
As one or more embodiments, the S101: carrying out variable screening on the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted, and screening out a plurality of variables; the method specifically comprises the following steps:
and performing variable screening on the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted by adopting a principal component analysis algorithm to screen out a plurality of variables.
It should be understood that the principal component analysis is a dimensionality reduction algorithm that can convert multiple indexes into a few principal components that are linear combinations of the original indexes, and that replaces more variables with fewer variables, which makes the data more usable, reduces the computational complexity of the algorithm, removes portions of noisy data, and also makes the results more understandable.
The selected indexes influencing the prediction of the agricultural product cold-chain logistics in the area to be predicted are more, and the indexes have stronger correlation, so that the indexes with more quantity can be simplified by using principal component analysis, and the subsequent model construction is facilitated. By means of the factor analysis function in the SPSS software, the ten influence indexes are standardized and subjected to principal component analysis, and the effect of reducing the dimension is achieved.
TABLE 1 Total variance interpretation
As can be seen from the figure, there are two main components with the characteristic value greater than 1, and the cumulative contribution rate reaches 86.17%, which indicates that the effect is better when the original variable information of more than 85% is covered. And further combining with a lithotripsy chart, the extraction of the two main components is reasonable.
TABLE 2 component score coefficient matrix
The relationship between the principal component and each influencing factor can be seen from the component score coefficient matrix, using F1、F2Respectively representing the two extracted principal components.
In SPSS, the normalized scores of the two principal components are back-calculated using the component score coefficients:
TABLE 3 principal Components score
| Year of year | 2003 | 2004 | 2005 | 2006 | 2007 | 2008 | 2009 | 2010 | 2011 |
| F1 | -1.67117 | -1.54841 | -1.25106 | -0.99801 | -1.03035 | -0.60076 | -0.23983 | 0.028 | 0.37284 |
| F2 | -0.65351 | -0.26168 | -0.79649 | -0.14402 | -0.15746 | 0.4948 | 0.00337 | 2.63746 | 1.90062 |
| Year of year | 2012 | 2013 | 2014 | 2015 | 2016 | 2017 | 2018 | 2019 | |
| F1 | 0.56321 | 0.46184 | 0.65012 | 0.77493 | 0.96865 | 1.23368 | 1.16652 | 1.11979 | |
| F2 | 0.84915 | 0.04558 | -0.6762 | -0.93328 | -0.71974 | -0.99468 | -0.6684 | 0.07447 |
As one or more embodiments, the S102: predicting each variable to obtain predicted values of all variables; the method comprises the following specific steps:
and predicting each variable based on the time series prediction to obtain the predicted values of all the variables.
The time series prediction method is to compile and analyze time series, and analogize or extend the time series according to the development process, direction and trend reflected by the time series, so as to predict the level which can be reached in the next period of time or in the following years.
The time series model is built by using an expert modeler in the SPSS, the main component data between 2003 and 2019 are predicted, the expert modeler can automatically search a best fit model of each dependent sequence, the expert modeler considers an exponential smoothing model and an ARIMA model, and the results are as follows:
TABLE 4 time series model
| Model ID | REGR factor score 1for analysis 1 | Model _1 | ARIMA(0,1,0) |
| Model ID | REGR factor score 2for analysis 2 | Model _2 | ARIMA(1,0,0) |
The expert modeler selects ARIMA (0,1,0) and ARIMA (1.0,0) as time sequence prediction models respectively, the ARIMA model regards a data sequence formed by a prediction object along with the time as a random sequence, and a certain mathematical model is used for approximately describing the sequence. The prediction results of SPSS for two principal components are as follows:
TABLE 5 time series prediction results
| Model (model) | 2020 | 2021 | 2022 |
| REGR factor score 1for analysis 1-model _1 | 1.29422 | 1.46866 | 1.64309 |
| REGR factor score 2for analysis 2-model _2 | 0.04396 | 0.02595 | 0.01532 |
As one or more embodiments, the S103: obtaining a first agricultural product cold-chain logistics demand predicted value based on all variable predicted values and a multiple linear regression model; the method comprises the following specific steps:
and inputting all the variable predicted values into a multiple linear regression model to obtain a first agricultural product cold-chain logistics demand predicted value.
The multiple regression analysis prediction method is a method for establishing a prediction model for prediction by correlation analysis of two or more independent variables and one dependent variable. Establishing agricultural production of to-be-predicted area by means of SPSS softwareTotal quantity Y and principal component F of product cold chain logistics demand1、F2The result of the multiple linear regression equation of (1) is as follows:
TABLE 6 Linear regression coefficients
The principal component regression equation obtained from the above solution is as follows:
the normalization equation: y is 0.983F1-0.095F2+c
Non-standardized equation: 132.141F1-12.745F2+c
Estimating c to 4167.757 by the past year data
TABLE 7 Linear regression error
| Model (model) | R | R side | Adjusted R square | Error of standard estimation |
| 1 | 0.994a | 0.987 | 0.985 | 15.4042894300 |
Further analyzing the output table of the multiple regression model, the goodness of fit R2 of the model is 0.987, the adjusted R2 is 0.985>0.9, and the model fitting is good.
Substituting the predicted value of the main component obtained by time series prediction into a multiple regression equation to obtain the predicted value of the cold chain demand of the agricultural products in the area to be predicted in the next three years:
TABLE 8 regression prediction
| Time of day | Y (ten thousand tons) |
| 2018 | 4354.75 |
| 2019 | 4364.71 |
| 2020 | 4338.22 |
| 2021 | 4361.50 |
| 2022 | 4384.68 |
As one or more embodiments, the S103: obtaining a cold-chain logistics demand predicted value of a second agricultural product based on all variable predicted values and a pre-trained BP neural network; the method comprises the following specific steps:
and inputting all the variable predicted values into a pre-trained BP neural network to obtain a cold-chain logistics demand predicted value of a second agricultural product.
Further, the training step of the pre-trained BP neural network comprises:
constructing a BP neural network; constructing a training set; the training set is agricultural product cold chain logistics basic data with known logistics demand;
and inputting the training set into a BP neural network, and training the BP neural network to obtain the trained BP neural network.
The BP neural network is a multi-layer feedforward network trained according to an error inverse propagation algorithm, and is one of the most widely applied neural network models at present. The BP network can learn and store a large number of input-output pattern mappings without prior disclosure of mathematical equations describing such mappings. The learning rule is that the steepest descent method is used, and the weight and the threshold value of the network are continuously adjusted through back propagation, so that the error square sum of the network is minimum.
Because the cold-chain logistics demand of agricultural products is influenced by a plurality of factors and the relation among the factors is complex, the cold-chain logistics demand forecasting model is not a simple linear system, and in order to enable the cold-chain logistics demand forecasting model result of the agricultural products in the area to be forecasted to be more scientific and accurate, on the basis of principal component analysis, a BP neural network forecasting model is established.
The input layer of the neural network model is two, namely two principal components extracted after principal component analysis, the output layer is one, and the number of neurons is ten.
In order to ensure the accuracy of the BP neural network model and improve the neural network efficiency, data are divided into a training set, a verification set and a test set. The training set is used for data samples of model fitting, the verification set is a sample set reserved in the model training process, and the test set is used for evaluating the generalization capability of the model final model. The proportions of the training set, validation set and test set were 70%, 15% and 15%, respectively.
Through multiple times of training, the iteration times are 357, the error is small, and the training effect of the neural network model is good. The cold chain logistics demand prediction value of the agricultural products in the area to be predicted is obtained by Matlab as follows:
TABLE 9 neural network prediction results
| Time of day | Y (ten thousand tons) |
| 2018 | 4351.5 |
| 2019 | 4359.5 |
| 2020 | 4404.04 |
| 2021 | 4447.62 |
| 2022 | 4489.54 |
As one or more embodiments, the S104: weighting and summing the first agricultural product cold-chain logistics demand predicted value and the second agricultural product cold-chain logistics demand predicted value to obtain a final agricultural product cold-chain logistics demand predicted value; the method comprises the following specific steps:
and weighting and summing the weight obtained by the inverse variance method on the first agricultural product cold-chain logistics demand predicted value and the second agricultural product cold-chain logistics demand predicted value to obtain a final agricultural product cold-chain logistics demand predicted value.
As one or more embodiments, the S105: obtaining a scale optimization scheme of the logistics node based on a final agricultural product cold-chain logistics demand prediction value of the area to be predicted, the scale of the existing logistics node and the distance between the existing logistics node and the area to be predicted; the method comprises the following specific steps:
and obtaining a scale optimization scheme of the logistics nodes by adopting an optimization algorithm based on the final agricultural product cold-chain logistics demand prediction value of the area to be predicted, the scale of the existing logistics nodes and the distance between the existing logistics nodes and the area to be predicted.
The scale optimization scheme for obtaining the logistics nodes by adopting the optimization algorithm includes:
establishing a corresponding objective function based on a final agricultural product cold-chain logistics demand predicted value of an area to be predicted;
establishing a constraint condition based on the scale of the existing logistics node and the distance between the existing logistics node and the area to be predicted;
and solving the objective function and the constraint condition by using an ant colony algorithm or a genetic algorithm to obtain an optimal value of the amplification area of the existing logistics node or solve an optimal value of the position of the candidate logistics node.
The principal component analysis is used as a common dimension reduction method, can reduce dimensions of a plurality of index data and convert the index data into a small number of principal components, and is beneficial to next data prediction. A multiple linear regression model and a neural network model are constructed based on principal component indexes and agricultural product cold-chain logistics demand data, and a combined prediction model formed by combining the principal component indexes and the agricultural product cold-chain logistics demand data not only considers the scientificity and simplicity of linear regression, but also considers the accuracy and reliability of the neural network. The application of time series prediction also enables the prediction of the principal component to be more accurate, and further achieves the purpose of predicting by using the principal component.
And (3) using the number of the permanent population of the area to be predicted and the consumption of the per-capita agricultural products as the demand of the cold-chain logistics of the agricultural products of the area to be predicted, wherein the consumption of the per-capita agricultural products mainly comprises the sum of the demands of main agricultural products such as fruits, vegetables, meat, eggs, aquatic products, milk and the like.
The combined prediction model can combine a plurality of single prediction models through a certain combination strategy or method, so that the defects of single model prediction in certain aspects are made up to a certain extent, and the prediction capability of the combined model is improved through a scientific and reasonable combination mode. In reality, the agricultural product cold-chain logistics system is complex, the factors influencing the requirements of the agricultural product cold-chain logistics system are more, and the single prediction model for prediction is often in a certain one-sidedness, so that the influence factors of the agricultural product cold-chain logistics are comprehensively considered by the aid of the combined prediction model of multiple regression and the neural network, the one-sidedness of the single prediction model is reduced, and a better prediction effect is expected to be achieved.
The combined prediction model based on the multiple linear regression and the BP neural network is more scientific and reasonable, and on one hand, the characteristics of simple calculation, science and reasonability are realized by means of the multiple linear regression model; on the other hand, by combining the advantages of accurate prediction and small error of the BP neural network, the characteristics of simple, convenient, scientific and reasonable construction of the multiple linear regression model can be realized, and the BP neural network model can be used for deep fitting, so that the reliability and the accuracy of the model are improved, and the accuracy and the reasonability of the prediction of the combined model are facilitated.
There are many methods for determining the weights of the combined model, among which the following are simpler and more widely used: arithmetic mean, reciprocal variance, reciprocal mean square error, simple weighted mean, and the like. The arithmetic mean method is also called as an equal weight mean method, and the principle is that all the single prediction models are considered equally, so that the weight coefficients of all the methods are equal; the inverse variance method is to calculate a weight coefficient according to the square sum of the prediction errors, the larger the numerical value of the inverse variance method is, the lower the prediction accuracy of the prediction model is, the smaller the weight coefficient given to the prediction model is, and conversely, the larger the weight coefficient is; the mean square error reciprocal method is also based on the principle that the larger the numerical value of the error square sum of the monomial prediction model is, the smaller the weighting coefficient of the monomial prediction model is; the simple weighted average method is to sort the square sum of the prediction errors of the single-term models, and the more the order is, the smaller the weighting coefficient in the combined prediction is.
TABLE 10 Combined model comparison
As can be seen from the above table, the combined prediction models using different methods to determine weights have respective differences, and from the viewpoint of the mean absolute error and the sum of squared errors, the minimum error is the inverse variance method, and then the inverse mean square error method and the simple weighted average method are performed, so that the combined model using the inverse variance method has the best effect.
According to the method, Spss, Matlab and other software are utilized, principal component analysis and time sequence prediction are combined, and on the basis, multi-linear regression and a neural network are utilized to predict the cold-chain logistics demand of the agricultural products in the area to be predicted more scientifically and accurately. According to the method, research and practice are combined in the selection of data indexes, after a plurality of factors influencing the agricultural product cold-chain logistics in the area to be predicted are considered, a demand prediction index system is established from all angles, principal component analysis is used as a common dimension reduction method, the data indexes with more categories are converted into the principal components with less number, and the method is favorable for prediction of multiple linear regression and a neural network. The combined model of the multiple linear regression and the neural network not only considers the scientificity and simplicity of the linear regression, but also considers the accuracy and reliability of the neural network. Results of various prediction models show that the cold chain demand of agricultural products shows an obvious rising trend during the 2020 and 2022 years of the area to be predicted, which indicates that the area to be predicted has important opportunities to be developed in the field of agricultural product cold chain logistics, and the development of the agricultural product cold chain logistics has strong power.
Example two
The embodiment provides a logistics node layout optimization system based on agricultural product cold-chain logistics requirements;
logistics node layout optimization system based on agricultural product cold chain logistics demand includes:
a variable screening module configured to: carrying out variable screening on the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted, and screening out a plurality of variables;
a variable prediction module configured to: predicting each variable to obtain predicted values of all variables;
a demand prediction module configured to: obtaining a first agricultural product cold-chain logistics demand predicted value based on all variable predicted values and a multiple linear regression model; obtaining a cold-chain logistics demand predicted value of a second agricultural product based on all variable predicted values and a pre-trained BP neural network;
a weighting module configured to: weighting and summing the first agricultural product cold-chain logistics demand predicted value and the second agricultural product cold-chain logistics demand predicted value to obtain a final agricultural product cold-chain logistics demand predicted value;
an output module configured to: and obtaining a scale optimization scheme of the logistics node based on a final agricultural product cold-chain logistics demand prediction value of the area to be predicted, the scale of the existing logistics node and the distance between the existing logistics node and the area to be predicted.
It should be noted here that the variable screening module, the variable prediction module, the demand prediction module, the weighting module and the output module correspond to steps S101 to S105 in the first embodiment, and the modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the disclosure in the first embodiment. It should be noted that the modules described above as part of a system may be implemented in a computer system such as a set of computer-executable instructions.
In the foregoing embodiments, the descriptions of the embodiments have different emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The proposed system can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the above-described modules is merely a logical functional division, and in actual implementation, there may be other divisions, for example, multiple modules may be combined or integrated into another system, or some features may be omitted, or not executed.
EXAMPLE III
The present embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, a processor is connected with the memory, the one or more computer programs are stored in the memory, and when the electronic device runs, the processor executes the one or more computer programs stored in the memory, so as to make the electronic device execute the method according to the first embodiment.
It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and so on. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may include both read-only memory and random access memory, and may provide instructions and data to the processor, and a portion of the memory may also include non-volatile random access memory. For example, the memory may also store device type information.
In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software.
The method in the first embodiment may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor. The software modules may be located in ram, flash, rom, prom, or eprom, registers, among other storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor. To avoid repetition, it is not described in detail here.
Those of ordinary skill in the art will appreciate that the various illustrative elements, i.e., algorithm steps, described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
Example four
The present embodiments also provide a computer-readable storage medium for storing computer instructions, which when executed by a processor, perform the method of the first embodiment.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A logistics node layout optimization method based on agricultural product cold-chain logistics requirements is characterized by comprising the following steps:
carrying out variable screening on the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted, and screening out a plurality of variables;
predicting each variable to obtain predicted values of all variables;
obtaining a first agricultural product cold-chain logistics demand predicted value based on all variable predicted values and a multiple linear regression model; obtaining a cold-chain logistics demand predicted value of a second agricultural product based on all variable predicted values and a pre-trained BP neural network;
weighting and summing the first agricultural product cold-chain logistics demand predicted value and the second agricultural product cold-chain logistics demand predicted value to obtain a final agricultural product cold-chain logistics demand predicted value;
and obtaining a scale optimization scheme of the logistics node based on a final agricultural product cold-chain logistics demand prediction value of the area to be predicted, the scale of the existing logistics node and the distance between the existing logistics node and the area to be predicted.
2. The method as claimed in claim 1, wherein the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted is subjected to principal component analysis, and a plurality of key principal components are screened out; the method also comprises the following steps of:
acquiring basic data of agricultural product cold-chain logistics within the historical time range of an area to be predicted;
preprocessing the acquired basic data of the agricultural product cold-chain logistics; the pretreatment comprises the following steps: denoising processing and missing value completion processing.
3. The method of claim 2, wherein said agricultural product cold chain logistics base data comprises: the method comprises the following steps of (1) acquiring the annual population, the total retail volume of social consumer goods, the production price index of agricultural products, the yield of fruits and vegetables, the annual freight volume of an area to be predicted and the annual turnover volume of the area to be predicted at the end of the year in the area to be predicted;
the denoising processing refers to: calculating an average value, and taking the data beyond the set range of the average value as noise data to be eliminated;
the missing value completion processing means: the mean value is filled into the missing value data positions.
4. The method as claimed in claim 1, wherein the basic data of the agricultural product cold-chain logistics within the historical time range of the obtained area to be predicted is subjected to variable screening to screen out a plurality of variables; the method specifically comprises the following steps:
and performing variable screening on the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted by adopting a principal component analysis algorithm to screen out a plurality of variables.
5. The method of claim 1, wherein each variable is predicted to obtain predicted values for all variables; the method comprises the following specific steps:
and predicting each variable based on the time series prediction to obtain the predicted values of all the variables.
6. The method of claim 1, wherein the first agricultural product cold chain logistics demand forecast value is obtained based on all variable forecast values and a multiple linear regression model; the method comprises the following specific steps:
and inputting all the variable predicted values into a multiple linear regression model to obtain a first agricultural product cold-chain logistics demand predicted value.
7. The method of claim 1, wherein the second agricultural product cold chain logistics demand forecast value is obtained based on all variable forecast values and a pre-trained BP neural network; the method comprises the following specific steps:
inputting all variable prediction values into a pre-trained BP neural network to obtain a cold-chain logistics demand prediction value of a second agricultural product;
the training step of the pre-trained BP neural network comprises the following steps:
constructing a BP neural network; constructing a training set; the training set is agricultural product cold chain logistics basic data with known logistics demand;
and inputting the training set into a BP neural network, and training the BP neural network to obtain the trained BP neural network.
8. Logistics node layout optimization system based on agricultural product cold chain logistics demand, characterized by includes:
a variable screening module configured to: carrying out variable screening on the obtained basic data of the agricultural product cold-chain logistics in the historical time range of the area to be predicted, and screening out a plurality of variables;
a variable prediction module configured to: predicting each variable to obtain predicted values of all variables;
a demand prediction module configured to: obtaining a first agricultural product cold-chain logistics demand predicted value based on all variable predicted values and a multiple linear regression model; obtaining a cold-chain logistics demand predicted value of a second agricultural product based on all variable predicted values and a pre-trained BP neural network;
a weighting module configured to: weighting and summing the first agricultural product cold-chain logistics demand predicted value and the second agricultural product cold-chain logistics demand predicted value to obtain a final agricultural product cold-chain logistics demand predicted value;
an output module configured to: and obtaining a scale optimization scheme of the logistics node based on a final agricultural product cold-chain logistics demand prediction value of the area to be predicted, the scale of the existing logistics node and the distance between the existing logistics node and the area to be predicted.
9. An electronic device, comprising: one or more processors, one or more memories, and one or more computer programs; wherein a processor is connected to the memory, the one or more computer programs being stored in the memory, the processor executing the one or more computer programs stored in the memory when the electronic device is running, to cause the electronic device to perform the method of any of the preceding claims 1-7.
10. A computer-readable storage medium storing computer instructions which, when executed by a processor, perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011064782.7A CN112200443A (en) | 2020-09-30 | 2020-09-30 | Logistics node layout optimization method and system based on agricultural product cold-chain logistics demand |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011064782.7A CN112200443A (en) | 2020-09-30 | 2020-09-30 | Logistics node layout optimization method and system based on agricultural product cold-chain logistics demand |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112200443A true CN112200443A (en) | 2021-01-08 |
Family
ID=74012674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011064782.7A Pending CN112200443A (en) | 2020-09-30 | 2020-09-30 | Logistics node layout optimization method and system based on agricultural product cold-chain logistics demand |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112200443A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112836880A (en) * | 2021-02-08 | 2021-05-25 | 贵州电网有限责任公司 | RMSE-based model fusion method for power grid defect material demand accuracy |
| CN114565138A (en) * | 2022-02-14 | 2022-05-31 | 中国科学院地理科学与资源研究所 | Agricultural product supply network node identification method and device and electronic equipment |
| CN115860645A (en) * | 2023-02-23 | 2023-03-28 | 深圳市鸿鹭工业设备有限公司 | Logistics storage management method and system based on big data |
| CN116739627A (en) * | 2022-10-25 | 2023-09-12 | 荣耀终端有限公司 | Product sales prediction method and electronic equipment |
| CN116976675A (en) * | 2023-08-09 | 2023-10-31 | 南京龟兔赛跑软件研究院有限公司 | Cold chain transportation risk early warning method and system based on data monitoring of Internet of things |
| CN117113608A (en) * | 2023-10-23 | 2023-11-24 | 四川港投新通道物流产业投资集团有限公司 | Cold-chain logistics network node layout method and equipment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190385098A1 (en) * | 2018-06-13 | 2019-12-19 | Hitachi Transport System, Ltd. | Logistics prediction system and prediction method |
| CN111008870A (en) * | 2019-12-09 | 2020-04-14 | 金陵科技学院 | Regional logistics demand prediction method based on PCA-BP neural network model |
-
2020
- 2020-09-30 CN CN202011064782.7A patent/CN112200443A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190385098A1 (en) * | 2018-06-13 | 2019-12-19 | Hitachi Transport System, Ltd. | Logistics prediction system and prediction method |
| CN111008870A (en) * | 2019-12-09 | 2020-04-14 | 金陵科技学院 | Regional logistics demand prediction method based on PCA-BP neural network model |
Non-Patent Citations (3)
| Title |
|---|
| 冯永岩: "北京市农产品冷链物流需求预测研究", 《中国优秀博硕士学位论文全文数据库(硕士) 经济与管理科学辑》 * |
| 张文峰: "广东省生鲜农产品产后环节布局研究", 《2013年中国农业资源与区划学会学术年会论文集 中国农业资源与区划学会 会议论文集》 * |
| 朱建平: "《经济预测与决策》" * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112836880A (en) * | 2021-02-08 | 2021-05-25 | 贵州电网有限责任公司 | RMSE-based model fusion method for power grid defect material demand accuracy |
| CN114565138A (en) * | 2022-02-14 | 2022-05-31 | 中国科学院地理科学与资源研究所 | Agricultural product supply network node identification method and device and electronic equipment |
| CN116739627A (en) * | 2022-10-25 | 2023-09-12 | 荣耀终端有限公司 | Product sales prediction method and electronic equipment |
| CN116739627B (en) * | 2022-10-25 | 2024-06-07 | 荣耀终端有限公司 | Product sales prediction method and electronic equipment |
| CN115860645A (en) * | 2023-02-23 | 2023-03-28 | 深圳市鸿鹭工业设备有限公司 | Logistics storage management method and system based on big data |
| CN115860645B (en) * | 2023-02-23 | 2023-06-02 | 深圳市鸿鹭工业设备有限公司 | Logistics storage management method and system based on big data |
| CN116976675A (en) * | 2023-08-09 | 2023-10-31 | 南京龟兔赛跑软件研究院有限公司 | Cold chain transportation risk early warning method and system based on data monitoring of Internet of things |
| CN116976675B (en) * | 2023-08-09 | 2024-04-05 | 南京龟兔赛跑软件研究院有限公司 | Cold chain transportation risk early warning method and system based on data monitoring of Internet of things |
| CN117113608A (en) * | 2023-10-23 | 2023-11-24 | 四川港投新通道物流产业投资集团有限公司 | Cold-chain logistics network node layout method and equipment |
| CN117113608B (en) * | 2023-10-23 | 2024-02-13 | 四川港投新通道物流产业投资集团有限公司 | Cold-chain logistics network node layout method and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112200443A (en) | Logistics node layout optimization method and system based on agricultural product cold-chain logistics demand | |
| Abdella et al. | Sustainability assessment and modeling based on supervised machine learning techniques: The case for food consumption | |
| Shafiullah et al. | The role of export composition in export-led growth in Australia and its regions | |
| Koopman et al. | A non-Gaussian panel time series model for estimating and decomposing default risk | |
| CN108764520B (en) | Water quality parameter prediction method based on multilayer cyclic neural network and D-S evidence theory | |
| Stepashko et al. | Construction and research of the generalized iterative GMDH algorithm with active neurons | |
| CN104899451A (en) | Time sequence prediction model selecting method based on statistical signal process | |
| CN104949936A (en) | Sample component determination method based on optimizing partial least squares regression model | |
| CN113822499B (en) | Train spare part loss prediction method based on model fusion | |
| Zhou et al. | Comparison of time series forecasting based on statistical ARIMA model and LSTM with attention mechanism | |
| CN108399434B (en) | Analysis and prediction method of high-dimensional time series data based on feature extraction | |
| CN115587666A (en) | Load prediction method and system based on seasonal trend decomposition and hybrid neural network | |
| CN113610552A (en) | User loss prediction method and device | |
| CN117788041A (en) | Commodity sales predicting method, system and equipment based on multi-scale time sequence model | |
| Claveria et al. | A self-organizing map analysis of survey-based agents׳ expectations before impending shocks for model selection: The case of the 2008 financial crisis | |
| CN111415008B (en) | Ship flow prediction method based on VMD-FOA-GRNN | |
| CN111476418A (en) | Stock data fluctuation prediction method based on deep neural network and multitask learning | |
| Yang et al. | A carbon price hybrid forecasting model based on data multi-scale decomposition and machine learning | |
| Tanamal et al. | House price prediction model using random forest in surabaya city | |
| CN117273799A (en) | SARIMA-LSSVM-based steel product demand prediction method | |
| Prasetyowati et al. | Dataset feasibility analysis method based on enhanced adaptive LMS method with Min-max normalization and fuzzy intuitive sets | |
| CN109784417B (en) | Black hair pork image identification method | |
| CN108363830B (en) | Functional clothes hanger-oriented principle scheme non-cooperative game decision method | |
| Bulgakova et al. | Numerical study of the generalized iterative algorithm GIA GMDH with active neurons | |
| CN115187312A (en) | Customer loss prediction method and system based on deep learning |
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 |