CN116402444A - Wine warehouse management system based on environment refined partition - Google Patents
Wine warehouse management system based on environment refined partition Download PDFInfo
- Publication number
- CN116402444A CN116402444A CN202310643791.9A CN202310643791A CN116402444A CN 116402444 A CN116402444 A CN 116402444A CN 202310643791 A CN202310643791 A CN 202310643791A CN 116402444 A CN116402444 A CN 116402444A
- Authority
- CN
- China
- Prior art keywords
- wine
- data
- environment
- average
- storage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 235000014101 wine Nutrition 0.000 title claims abstract description 168
- 238000005192 partition Methods 0.000 title claims abstract description 22
- 238000012549 training Methods 0.000 claims description 49
- 230000007613 environmental effect Effects 0.000 claims description 47
- 238000010801 machine learning Methods 0.000 claims description 28
- 238000005286 illumination Methods 0.000 claims description 25
- 238000000034 method Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 17
- 238000013480 data collection Methods 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 9
- 238000004321 preservation Methods 0.000 claims description 7
- 235000013334 alcoholic beverage Nutrition 0.000 claims description 3
- 238000007726 management method Methods 0.000 description 19
- 239000004973 liquid crystal related substance Substances 0.000 description 4
- 235000019993 champagne Nutrition 0.000 description 2
- 235000020095 red wine Nutrition 0.000 description 2
- 235000019992 sake Nutrition 0.000 description 2
- 235000015041 whisky Nutrition 0.000 description 2
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 235000019645 odor Nutrition 0.000 description 1
- 238000000275 quality assurance Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 239000003566 sealing material Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009423 ventilation Methods 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/087—Inventory or stock management, e.g. order filling, procurement or balancing against orders
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Abstract
The invention discloses an environment-refined partition-based wine storage management system, which relates to the technical field of wine storage management.
Description
Technical Field
The invention belongs to the technical field of wine warehouse management, and particularly relates to a wine warehouse management system based on an environment refined partition.
Background
In the wine storage management process, it is important to ensure the quality and quality guarantee period of the wine, however, the traditional storage management method generally does not fully consider the influence of environmental factors on the quality of the wine, manages the wine only based on physical positions, and lacks careful consideration of the environmental factors;
in the prior art, the warehouse management generally only considers single factors such as temperature or humidity, lacks comprehensively considering factors such as the price and quality guarantee duration of wine, and the like, and only makes a warehouse strategy based on simple warehouse division or temperature control, and the method cannot provide personalized warehouse environments for different wine products due to the lack of fine management on environmental factors and comprehensive consideration on environmental data and price of the wine products, and causes larger quality and price loss of different wine products due to unsuitable environmental influence in the warehouse process;
therefore, there is a need for an wine warehouse management system based on an environment refined partition, which realizes intelligent refined partition of warehouse positions according to environment data, and establishes a warehouse strategy comprehensively considering the price and quality guarantee duration of wine after the partition so as to reduce the quality loss of the wine in the warehouse process and ensure the benefits of dealers;
therefore, the invention provides an wine warehouse management system based on the environment refined partition.
Disclosure of Invention
The invention aims to at least solve one of the technical problems in the prior art, and therefore, the invention provides an wine warehouse management system based on the environment refined partition, which reduces the quality loss of wine in the warehouse process and ensures the benefits of dealers.
To achieve the above objective, an embodiment according to a first aspect of the present invention provides an wine warehouse management system based on an environment refinement partition, including a training data collection module, a fresh-keeping duration prediction model training module, a warehouse data collection module, a fresh-keeping duration prediction module, and a warehouse management module; wherein, each module is connected by a wired and/or wireless network mode;
the training data collection module is mainly used for collecting a plurality of groups of historical training data in advance;
the history training data comprises a storage environment data set and a wine label data set, wherein the storage environment data set and the wine label data set are obtained in the history storage process of the storage space for each wine type;
the wines are divided according to different brewing modes, including but not limited to red wine, champagne, whiskey, sake, white spirit and the like;
the storage environment data comprise average temperature, average humidity, average illumination intensity and average airflow speed in a storage space; the temperature, the humidity, the illumination intensity and the air flow speed can be obtained in real time by using a temperature sensor, a humidity sensor, an illumination intensity and an air flow speed sensor respectively; the average temperature, the average humidity, the average illumination intensity and the average airflow speed are the average values of the temperature, the humidity, the illumination intensity and the airflow speed in the storage space in a preset storage period;
the wine label data comprise the quality guarantee duration of each wine type in each group of storage environment data;
the training data collection module sends the collected historical training data to the fresh-keeping duration prediction model training module;
the fresh-keeping duration prediction model training module is mainly used for training a machine learning model for predicting the preservation duration of each wine type by using historical training data;
the mode of training a machine learning model for predicting the preservation time of each wine type is as follows:
the number of the wine type is marked asWill->The storage environment data set of the seed wine type is marked as +.>Warehouse Environment data set->The number of each group of warehouse environment data is marked as +.>The method comprises the steps of carrying out a first treatment on the surface of the Will be->The wine label data set corresponding to the storage environment data set of the seed wine type is marked as +.>;
For the firstWine type, combining each group of warehouse environment data into a characteristic vector form, wherein elements in the characteristic vector comprise average temperature, average humidity, average illumination intensity and average air flow speed; the set of all feature vectors is used as input to a machine learning model that outputs wine label data predicted for each set of warehouse environment data, for +.>Group warehouse Environment data +.>The wine label data is used as a prediction target, and the sum of the prediction accuracy of all the predicted wine label data is minimized to be used as a training target; the calculation formula of the prediction accuracy is as follows; />Wherein->For prediction accuracy, < >>Is->Predicted wine label data corresponding to group warehouse environment data,/-for>Is->Wine label data set corresponding to group storage environment data>Middle->Wine label data; training the machine learning model until the sum of prediction accuracy reaches convergence, and stopping training;
the fresh-keeping duration prediction model training module sends the trained machine learning model to the fresh-keeping duration prediction module;
the warehouse data collection module is mainly used for collecting warehouse data of warehouse spaces to be managed;
the storage data comprise wine base data and storage space division data;
the wine base data comprise the quantity of brand wine to be stored, the size of occupied space of each bottle of wine and the price of each bottle of wine, wherein the quantity of brand wine to be stored corresponds to all wine types; the brands of wine are different brands and different wine corresponding to each wine type, for example, the white spirit can be divided into a plurality of brands and various series, and the price and occupied space of each brand and series are different;
the storage space division data are divided according to storage environment distribution data;
the storage environment distribution data comprise storage environment data in each subspace, wherein the storage environment data comprise a plurality of subspaces which are divided for storage spaces to be managed in advance; the size and the number of subspaces divided by the warehouse space are determined empirically according to the actual size, the actual position, the actual building layout and the specific conditions of the actual environment of the warehouse space;
the number of each subspace is denoted as k, and the average temperature, average humidity, average illumination intensity and average airflow velocity in the kth subspace are denoted as dk, ek, fk and gk, respectively; the spatial size of each subspace is denoted Sk;
calculating an environment weight hk of the kth subspace, wherein the calculation formula of the environment weight hk is as followsThe method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>And->Respectively preset proportional coefficients;
presetting N environmental levels, and marking the number of the environmental levels as N; setting an environment weight lower limit value hn for the nth environment level, wherein the damage coefficient range of the damage degree level of the nth level is between hn and h (n+1); it can be understood that the warehouse space is divided into areas according to the similar environmental data by setting the environmental level;
according to the environment weight hk of the kth subspace, matching the environment grade corresponding to the kth subspace;
marking a set of subspace numbers matched by the nth environmental level as Kn;
the storage space division data comprise a set of corresponding subspace numbers under all environment levels, storage environment data of each subspace and space size of each subspace;
the storage data collection module sends storage space division data to the fresh-keeping duration prediction module and the storage management module;
the fresh-keeping duration prediction module is mainly used for predicting the duration of quality guarantee of each wine type under different environmental levels based on machine learning models and storage space division data;
the method for predicting the quality guarantee time of each wine type under different environmental levels is as follows:
calculating average warehouse environment data of each environment level; the average warehouse environment data comprise an average temperature average value, an average humidity average value, an average illumination intensity average value and an average airflow speed average value, and are respectively marked as dkn, ekn, fkn and gkn;
the mean warehouse environment data for each environment level is calculated by:
for the nth environmental class:
Taking the average warehouse environment data of the nth area as the input of a jth machine learning model to obtain the prediction of the quality guarantee period of the jth wine type in the nth area, which is output by the jth machine learning model; marking Mjn the predicted quality guarantee period of the jth alcoholic beverage type in the nth region;
the fresh-keeping duration prediction module sends all predicted quality guarantee durations to the warehouse management module;
the fresh-keeping duration prediction module is mainly used for distributing storage positions of all wine types based on storage space division data and predicted quality guarantee duration;
the way of distributing the storage positions of all the wines is as follows:
calculating the total space size On of the nth environmental level; wherein, the calculation formula of the total space size On is that;
The number of the jth wine type brand wine is marked as rj, the number of the jth brand wine is marked as Trj, the occupied space of each bottle of the jth brand wine is marked as Urj, and the price of each bottle of the jth brand wine is marked as Vrj;
setting a distribution variable xrjn for rj brands of wine; the distribution variable xrjn refers to the quantity of rj brands distributed to the nth environmental grade;
designing an optimization objective function Y;
wherein the objective function is optimizedThe method comprises the steps of carrying out a first treatment on the surface of the It will be appreciated that the optimization is targetedIn the function Y, when the price of the rj brand wine is higher or the quality guarantee period is longer, the contribution of the larger quantity divided for the rj brand wine to the optimization objective function is larger, so that in order to obtain the larger optimization objective function, the price and the quality guarantee period are considered to be taken as important reference targets when the brand wine is distributed;
designing a constraint target set Z, wherein the constraint target set Z comprises:
wherein, the liquid crystal display device comprises a liquid crystal display device,the quantity of rj brands of wine to be dispensed is not greater than the quantity thereof;for limiting the space allocated to each environmental level to be no greater than the total space size of that environmental level; />Is a positive limit; />Refers to any->Similarly->Refers to any->,/>Refers to any->Optionally->;
Taking a minimized optimization objective function Y as an optimization objective of the linear programming problem, taking a constraint objective set Z as a constraint objective set of the linear programming problem, and solving the integer programming problem by using a linear programming solving tool to obtain a solution set; from each allocation variable in the solution setSetting the number of rj brands assigned to the nth environmental class to the value of xrij; the specific allocation position in the nth environmental level is randomly selected according to the actual situation.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, a plurality of groups of historical training data are collected in advance, then a machine learning model for predicting the preservation time of each wine type is trained by utilizing the historical training data, a storage space to be managed is divided into a plurality of subspaces, storage environment data are collected for each subspace, different environment grades are set for the storage environment, and average storage environment data under each environment grade are calculated, so that the time of quality guarantee of different types of wine under different storage environments can be obtained by utilizing the machine learning model, a linear programming model comprehensively considering the price and the quality guarantee time of the brand wine is established, and a storage strategy for distributing storage positions of all wine types is obtained by solving the optimal solution of the linear programming model; the intelligent refined partition of the storage position according to the environmental data is realized, the storage strategy of comprehensively considering the price and the quality guarantee period of the wine is formulated after the partition, the quality loss of the wine in the storage process is reduced, and the benefits of distributors are ensured.
Drawings
FIG. 1 is a block diagram of the wine warehouse management system based on the refined partition of the environment in embodiment 1 of the present invention.
Detailed Description
The technical solutions of the present invention will be clearly and completely described in connection with the embodiments, and it is obvious that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in fig. 1, the wine warehousing management system based on the environment refined partition comprises a training data collection module, a fresh-keeping duration prediction model training module, a warehousing data collection module, a fresh-keeping duration prediction module and a warehousing management module; wherein, each module is connected by a wired and/or wireless network mode;
the training data collection module is mainly used for collecting a plurality of groups of historical training data in advance;
the history training data comprises a storage environment data set and a wine label data set, wherein the storage environment data set is obtained in the history storage process of a storage space for each wine type;
wine types are divided according to different brewing modes, including but not limited to red wine, champagne, whiskey, sake, white spirit, and the like;
in a preferred embodiment, the warehouse environmental data includes average temperature, average humidity, average light intensity, and average airflow rate in the warehouse space; the temperature, the humidity, the illumination intensity and the air flow speed can be obtained in real time by using a temperature sensor, a humidity sensor, an illumination intensity and an air flow speed sensor respectively; the average temperature, the average humidity, the average illumination intensity and the average airflow speed are the average values of the temperature, the humidity, the illumination intensity and the airflow speed in the storage space in a preset storage period; the storage period can be one day, one week or one month, and the specific length is determined according to the actual storage requirement;
it will be appreciated that for different wines: the temperature, humidity, illumination intensity and air flow speed all have influence on the quality of the wine; specific:
proper storage temperature is the key to maintaining wine quality;
proper humidity is helpful for maintaining the tightness of the wine bottle, preventing alcohol in the wine from evaporating, and preventing the wine label and the sealing material from being affected with damp;
the wine should avoid long-time exposure to direct sunlight;
proper ventilation helps to diffuse and exclude odors and gases in the wine, and helps to maintain the freshness of the wine;
the wine label data comprise the quality guarantee time of each wine type in each group of storage environment data; it can be understood that the time length is obtained when the evaluation is quality deterioration by performing professional quality evaluation on the wine at intervals of preset data acquisition time length;
the training data collection module sends the collected historical training data to the fresh-keeping duration prediction model training module;
the fresh-keeping duration prediction model training module is mainly used for training a machine learning model for predicting the preservation duration of each wine type by using historical training data;
the mode of training a machine learning model for predicting the preservation time of each wine type is as follows:
the number of the wine type is marked asWill->The storage environment data set of the seed wine type is marked as +.>Warehouse Environment data set->The number of each group of warehouse environment data is marked as +.>The method comprises the steps of carrying out a first treatment on the surface of the Will be->The wine label data set corresponding to the storage environment data set of the seed wine type is marked as +.>The method comprises the steps of carrying out a first treatment on the surface of the It will be appreciated that the wine tag data set +.>Middle->The individual wine label data corresponds to->Individual warehouse environmental data;
for the firstWine type, combining each group of warehouse environment data into a characteristic vector form, wherein elements in the characteristic vector comprise average temperature, average humidity, average illumination intensity and average air flow speed; the set of all feature vectors is used as input of a machine learning model which takes as output wine label data predicted for each group of warehouse environment data, for +.>Group warehouse Environment data +.>The wine label data is used as a prediction target, and the sum of the prediction accuracy of all the predicted wine label data is minimized to be used as a training target; the calculation formula of the prediction accuracy is as follows; />Wherein->For prediction accuracy, < >>Is->Predicted wine label data corresponding to group warehouse environment data,/-for>Is the firstWine label data set corresponding to group storage environment data>Middle->Wine label data; training the machine learning model until the sum of prediction accuracy reaches convergence, and stopping training; preferably, the machine learning model is any one of a deep neural network model or a deep belief network model;
it should be noted that, other model parameters of the machine learning model, such as the depth of the network model, the number of neurons in each layer, the activation function used by the network model, the convergence condition, the verification set proportion of the training set test set, the loss function and the like are all realized through actual engineering, and are obtained after experimental tuning is continuously performed;
the fresh-keeping duration prediction model training module sends the machine learning model after training to the fresh-keeping duration prediction module;
the warehouse data collection module is mainly used for collecting warehouse data of a warehouse space to be managed;
in a preferred embodiment, the warehouse data includes wine base data and warehouse space division data;
the wine base data comprise the quantity of brand wine to be stored, the size of the occupied space of each bottle of wine and the price of each bottle of wine, wherein the quantity of all wine type brands of wine to be stored corresponds to the wine base data; brands of wine are different brands and different wine corresponding to each wine type, for example, white spirit can be divided into a plurality of brands and various series, and the price and occupied space of each brand and series are different;
the storage space division data are divided according to storage environment distribution data;
the storage environment distribution data comprises the steps of dividing a plurality of subspaces for storage spaces to be managed in advance, and collecting storage environment data in each subspace; the size and the number of subspaces divided by the warehouse space are determined empirically according to the actual size, the actual position, the actual building layout and the specific conditions of the actual environment of the warehouse space;
the number of each subspace is denoted as k, and the average temperature, average humidity, average illumination intensity and average airflow velocity in the kth subspace are denoted as dk, ek, fk and gk, respectively; the spatial size of each subspace is denoted Sk;
calculating an environment weight hk of the kth subspace, wherein the calculation formula of the environment weight hk is as followsThe method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>And->Respectively preset proportional coefficients;
presetting N environmental levels, and marking the number of the environmental levels as N; setting an environment weight lower limit value hn for the nth environment level, wherein the damage coefficient range of the damage degree level of the nth level is between hn and h (n+1); it can be understood that the warehouse space is divided into areas according to the similar environmental data by setting the environmental level;
according to the environment weight hk of the kth subspace, matching the environment grade corresponding to the kth subspace; it will be appreciated that each environmental level will be matched by several subspaces;
marking a set of subspace numbers matched by the nth environmental level as Kn;
the storage space division data comprise a set of corresponding subspace numbers under all environment levels, storage environment data of each subspace and space size of each subspace;
the storage data collection module sends storage space division data to the fresh-keeping duration prediction module and the storage management module;
the fresh-keeping duration prediction module is mainly used for predicting the duration of quality guarantee of each wine type under different environmental levels based on machine learning models and storage space division data;
in a preferred embodiment, the duration of quality assurance for each wine type at different environmental levels is estimated by:
calculating average warehouse environment data of each environment level; the average warehouse environment data comprise an average temperature average value, an average humidity average value, an average illumination intensity average value and an average airflow speed average value, and are respectively marked as dkn, ekn, fkn and gkn;
the mean warehouse environment data for each environment level is calculated by:
for the nth environmental class:
Taking the average warehouse environment data of the nth area as the input of a jth machine learning model to obtain the prediction of the quality guarantee period of the jth wine type in the nth area, which is output by the jth machine learning model; marking Mjn the predicted quality guarantee period of the jth alcoholic beverage type in the nth region;
the fresh-keeping duration prediction module sends all the predicted quality guarantee duration to the warehouse management module;
in a preferred embodiment, the fresh-keeping duration prediction module is mainly used for distributing storage positions of all wine types based on storage space division data and predicted quality guarantee duration;
in a preferred embodiment, the distribution of the storage locations for all wine types is performed in the following manner:
calculating the total space size On of the nth environmental level; wherein, the calculation formula of the total space size On is that
The number of the jth wine type brand wine is marked as rj, the number of the jth brand wine is marked as Trj, the occupied space of each bottle of the jth brand wine is marked as Urj, and the price of each bottle of the jth brand wine is marked as Vrj;
setting a distribution variable xrjn for rj brands of wine; the allocation variable xrjn refers to the number of rj brands allocated to the nth environmental class;
designing an optimization objective function Y;
wherein the objective function is optimizedThe method comprises the steps of carrying out a first treatment on the surface of the It can be understood that in the objective optimization function Y, when the price of the rj-th brand wine is higher or the quality guarantee period is longer, the larger the number of the brands is, the larger the contribution to the optimization objective function is, so that in order to obtain the larger optimization objective function, the price and the quality guarantee period are considered to be important reference targets when the brands are distributed;
designing a constraint target set Z, wherein the constraint target set Z comprises:
wherein, the liquid crystal display device comprises a liquid crystal display device,the quantity of rj brands of wine to be dispensed is not greater than the quantity thereof;for limiting the space allocated to each environmental level to be no greater than the total space size of that environmental level; />Is a positive limit; />Refers to any->Similarly->Refers to any->,/>Refers to any->Optionally->;
Taking a minimized optimization objective function Y as an optimization objective of the linear programming problem, taking a constraint objective set Z as a constraint objective set of the linear programming problem, and solving the integer programming problem by using a linear programming solving tool to obtain a solution set; from each allocation variable in the solution setSetting the number of rj brands assigned to the nth environmental class to the value of xrij; the specific allocation position in the nth environmental level is randomly selected according to the actual situation.
The above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas which are obtained by acquiring a large amount of data and performing software simulation to obtain the closest actual situation, and preset parameters and preset thresholds in the formulas are set by a person skilled in the art according to the actual situation or are obtained by simulating a large amount of data.
The above embodiments are only for illustrating the technical method of the present invention and not for limiting the same, and it should be understood by those skilled in the art that the technical method of the present invention may be modified or substituted without departing from the spirit and scope of the technical method of the present invention.
Claims (8)
1. The wine warehousing management system based on the environment refined partition is characterized by comprising a training data collection module, a fresh-keeping duration prediction model training module, a warehousing data collection module, a fresh-keeping duration prediction module and a warehousing management module; wherein, each module is connected by a wired and/or wireless network mode;
the training data collection module is used for pre-collecting a plurality of groups of historical training data and sending the collected historical training data to the fresh-keeping duration prediction model training module;
the fresh-keeping time length prediction model training module is used for training a machine learning model for predicting the preservation time length of each wine type by utilizing the historical training data and transmitting the trained machine learning model to the fresh-keeping time length prediction module;
the storage data collection module is used for collecting storage data of storage space to be managed and sending storage space division data to the fresh-keeping duration prediction module and the storage management module;
the fresh-keeping duration prediction module predicts the duration of each wine type for quality guarantee under different environmental levels based on the machine learning model and the storage space division data, and sends all the predicted quality guarantee duration to the storage management module;
and the fresh-keeping duration prediction module is used for distributing storage positions of all wine types based on storage space division data and predicted quality guarantee duration.
2. The wine warehousing management system based on the environment refinement partition according to claim 1, wherein the history training data includes a warehousing environment data set and a wine label data set obtained during the history storage of the warehousing space for each wine type;
the storage environment data comprise average temperature, average humidity, average illumination intensity and average airflow speed in a storage space; the average temperature, the average humidity, the average illumination intensity and the average airflow speed are the average values of the temperature, the humidity, the illumination intensity and the airflow speed in a storage space in a preset storage period;
the wine label data includes a length of time each wine type is stored in each set of storage environment data.
3. The system for wine warehousing management based on the refined partition of the environment according to claim 2, wherein the machine learning model for predicting the preservation time of each wine type is trained in the following manner:
the number of the wine type is marked asWill->The storage environment data set of the seed wine type is marked as +.>Warehouse Environment data set->The number of each group of warehouse environment data is marked as +.>The method comprises the steps of carrying out a first treatment on the surface of the Will be->The wine label data set corresponding to the storage environment data set of the seed wine type is marked as +.>;
For the firstWine type, combining each group of warehouse environment data into a characteristic vector formThe elements in the feature vector include average temperature, average humidity, average illumination intensity, and average airflow velocity; the set of all feature vectors is used as input to a machine learning model that outputs wine label data predicted for each set of warehouse environment data, for the firstGroup warehouse Environment data +.>The wine label data is used as a prediction target, and the sum of the prediction accuracy of all the predicted wine label data is minimized to be used as a training target; the calculation formula of the prediction accuracy is as follows; />Wherein->For prediction accuracy, < >>Is->Predicted wine label data corresponding to group warehouse environment data,/-for>Is->Wine label data set corresponding to group storage environment data>Middle->Wine label data; training a machine learning model until the prediction is accurateStopping training when the sum of the degrees reaches convergence.
4. The wine warehousing management system based on the environment refinement partition according to claim 3, wherein the warehousing data includes wine base data and warehousing space division data;
the wine base data comprise the quantity of brand wine to be stored, the size of occupied space of each bottle of wine and the price of each bottle of wine, wherein the quantity of brand wine to be stored corresponds to all wine types;
the storage space division data are divided according to storage environment distribution data.
5. The wine warehousing management system based on the environment refinement partition according to claim 4, wherein the way in which the warehousing space division data is divided according to the warehousing environment distribution data is:
the storage environment distribution data comprise storage environment data in each subspace, wherein the storage environment data comprise a plurality of subspaces which are divided for storage spaces to be managed in advance;
the number of each subspace is denoted as k, and the average temperature, average humidity, average illumination intensity and average airflow velocity in the kth subspace are denoted as dk, ek, fk and gk, respectively; the spatial size of each subspace is denoted Sk;
calculating an environment weight hk of the kth subspace, wherein the calculation formula of the environment weight hk is as followsThe method comprises the steps of carrying out a first treatment on the surface of the Wherein (1)>And->Respectively preset proportional coefficients;
presetting N environmental levels, and marking the number of the environmental levels as N; setting an environment weight lower limit value hn for the nth environment level, wherein the damage coefficient range of the damage degree level of the nth level is between hn and h (n+1);
according to the environment weight hk of the kth subspace, matching the environment grade corresponding to the kth subspace;
marking a set of subspace numbers matched by the nth environmental level as Kn;
the warehouse space division data comprise a set of corresponding subspace numbers under all environment levels, warehouse environment data of each subspace and space size of each subspace.
6. The wine warehousing management system based on the environment refinement partition according to claim 5, wherein the method for estimating the quality guarantee duration of each wine type under different environment levels is as follows:
calculating average warehouse environment data of each environment level; the average warehouse environment data comprise an average temperature average value, an average humidity average value, an average illumination intensity average value and an average airflow speed average value, and are respectively marked as dkn, ekn, fkn and gkn;
taking the average warehouse environment data of the nth area as the input of the jth machine learning model to obtain the prediction of the quality guarantee period of the jth wine type in the nth area, which is output by the jth machine learning model.
7. The wine warehousing management system based on the environment refinement partition according to claim 6, wherein the mean warehousing environment data of each environment level is calculated by:
for the nth environmental class:
8. The system for wine warehousing management based on refined partitions of the environment according to claim 7, wherein the allocation of the warehousing locations for all wine types of wine is:
marking Mjn the predicted quality guarantee period of the jth alcoholic beverage type in the nth region;
calculating the total space size On of the nth environmental level; wherein, the calculation formula of the total space size On is that;
The number of the jth wine type brand wine is marked as rj, the number of the jth brand wine is marked as Trj, the occupied space of each bottle of the jth brand wine is marked as Urj, and the price of each bottle of the jth brand wine is marked as Vrj;
setting a distribution variable xrjn for rj brands of wine; the distribution variable xrjn refers to the quantity of rj brands distributed to the nth environmental grade;
designing an optimization objective function Y;
Designing a constraint target set Z, wherein the constraint target set Z comprises:
wherein, the->The quantity of rj brands of wine to be dispensed is not greater than the quantity thereof;/>for limiting the space allocated to each environmental level to be no greater than the total space size of that environmental level; />Is a positive limit; />Refers to any->Similarly->Refers to any->,/>Refers to any->Optionally->;
Taking a minimized optimization objective function Y as an optimization objective of the linear programming problem, taking a constraint objective set Z as a constraint objective set of the linear programming problem, and solving the integer programming problem by using a linear programming solving tool to obtain a solution set; from each allocation variable in the solution setThe number of rj brands assigned to the nth environmental class is set to the value of xrij.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310643791.9A CN116402444B (en) | 2023-06-02 | 2023-06-02 | Wine warehouse management system based on environment refined partition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310643791.9A CN116402444B (en) | 2023-06-02 | 2023-06-02 | Wine warehouse management system based on environment refined partition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116402444A true CN116402444A (en) | 2023-07-07 |
CN116402444B CN116402444B (en) | 2023-08-11 |
Family
ID=87014533
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310643791.9A Active CN116402444B (en) | 2023-06-02 | 2023-06-02 | Wine warehouse management system based on environment refined partition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116402444B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106067102A (en) * | 2016-05-24 | 2016-11-02 | 北京京东尚科信息技术有限公司 | The optimization method of layout for storekeeping and optimization device |
CN108022071A (en) * | 2017-12-05 | 2018-05-11 | 深圳春沐源控股有限公司 | Storage management method and Warehouse Management System |
CN109886478A (en) * | 2019-01-29 | 2019-06-14 | 东南大学 | A kind of slotting optimization method of finished wine automatic stereowarehouse |
US20190236525A1 (en) * | 2018-01-29 | 2019-08-01 | Maplebear, Inc. (Dba Instacart) | Machine-learned model for optmizing selection sequence for items in a warehouse |
CN112330255A (en) * | 2020-11-20 | 2021-02-05 | 重庆电子工程职业学院 | Warehouse management system |
CN113879750A (en) * | 2021-09-26 | 2022-01-04 | 云南追溯科技有限公司 | Intelligent Pu' er tea storage system and construction method |
CN114357740A (en) * | 2021-12-22 | 2022-04-15 | 中国人民解放军陆军装甲兵学院 | Material storage layout model construction method |
CN116050154A (en) * | 2023-02-07 | 2023-05-02 | 黄河科技学院 | Intelligent warehouse management method and system in Internet of things environment |
-
2023
- 2023-06-02 CN CN202310643791.9A patent/CN116402444B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106067102A (en) * | 2016-05-24 | 2016-11-02 | 北京京东尚科信息技术有限公司 | The optimization method of layout for storekeeping and optimization device |
CN108022071A (en) * | 2017-12-05 | 2018-05-11 | 深圳春沐源控股有限公司 | Storage management method and Warehouse Management System |
US20190236525A1 (en) * | 2018-01-29 | 2019-08-01 | Maplebear, Inc. (Dba Instacart) | Machine-learned model for optmizing selection sequence for items in a warehouse |
CN109886478A (en) * | 2019-01-29 | 2019-06-14 | 东南大学 | A kind of slotting optimization method of finished wine automatic stereowarehouse |
CN112330255A (en) * | 2020-11-20 | 2021-02-05 | 重庆电子工程职业学院 | Warehouse management system |
CN113879750A (en) * | 2021-09-26 | 2022-01-04 | 云南追溯科技有限公司 | Intelligent Pu' er tea storage system and construction method |
CN114357740A (en) * | 2021-12-22 | 2022-04-15 | 中国人民解放军陆军装甲兵学院 | Material storage layout model construction method |
CN116050154A (en) * | 2023-02-07 | 2023-05-02 | 黄河科技学院 | Intelligent warehouse management method and system in Internet of things environment |
Also Published As
Publication number | Publication date |
---|---|
CN116402444B (en) | 2023-08-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116500955B (en) | Zero-carbon type storage building internal environment control system and method | |
CN116402444B (en) | Wine warehouse management system based on environment refined partition | |
WO2021140941A1 (en) | Harvest prediction device and harvest prediction method | |
CN109583566A (en) | Ammonia concentration prediction technique in a kind of cold ground pig house based on empirical mode decomposition and Elman neural network | |
CN106570592A (en) | Artificial-neural-network-based intelligent numerical value forecasting correction system | |
CN112465109A (en) | Green house controlling means based on cloud limit is in coordination | |
CN113723757B (en) | Decision generation model training method, decision generation method and device | |
Schemminger et al. | Ambient air cereal grain drying–Simulation of the thermodynamic and microbial behavior | |
CN117314024B (en) | Wisdom agricultural insect pest cloud platform | |
Swaney et al. | Using crop models for management: Impact of weather characteristics on irrigation decisions in soybeans | |
Labidi et al. | Control of relative humidity inside an agricultural greenhouse | |
CN106875067B (en) | The method of greenhouse carbon dioxide concentration prediction model when building winter fine day | |
CA3143484A1 (en) | Information processing device and method | |
CN116307384A (en) | Intelligent agriculture soil culture on-line monitoring system and method based on Internet of things | |
Finandhita et al. | Development of Smart Environment Systems Model for The Optimization of Agriculture Products | |
Temeyer et al. | Using an artificial neural network to predict parameters for frost deposition on Iowa bridgeways | |
CN112449956A (en) | Micro-nano ozone green prevention and control device | |
Houter et al. | Simulation of CO2 consumption in greenhouses | |
Li et al. | Response of the water footprint of maize production to high temperatures in the Huang‐Huai‐Hai region of China | |
CN116993273B (en) | Grain depot operation and maintenance management system based on data analysis | |
van den Bemd | Robust deep reinforcement learning for greenhouse control and crop yield optimization | |
Kittas et al. | Characterization and analysis of the effects of greenhouse climate control equipment on greenhouse microclimate and crop response | |
de Camargo | Determination of the water balance components and drought sensitivity indices for a sorghum crop | |
Wagle et al. | Prediction of tomato plant disease with meteorological condition and artificial intelligence | |
Miranda et al. | An adaptive architecture for portability of greenhouse models |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |