CN116703468B - Agricultural product marketing method, system and storage medium based on big data - Google Patents
Agricultural product marketing method, system and storage medium based on big data Download PDFInfo
- Publication number
- CN116703468B CN116703468B CN202310953855.5A CN202310953855A CN116703468B CN 116703468 B CN116703468 B CN 116703468B CN 202310953855 A CN202310953855 A CN 202310953855A CN 116703468 B CN116703468 B CN 116703468B
- Authority
- CN
- China
- Prior art keywords
- target
- agricultural products
- data
- farmland
- target agricultural
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000012797 qualification Methods 0.000 claims abstract description 64
- 238000012217 deletion Methods 0.000 claims description 15
- 230000037430 deletion Effects 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 15
- 239000002689 soil Substances 0.000 claims description 15
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 230000002950 deficient Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 3
- 235000013399 edible fruits Nutrition 0.000 description 25
- 238000003306 harvesting Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 239000010751 BS 2869 Class A2 Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012258 culturing Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005058 diapause Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000002329 infrared spectrum Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method, a system and a storage medium for marketing agricultural products based on big data, which belong to the technical field of data processing and comprise the following steps of S1: dividing the target agricultural products into a plurality of grades, and predicting the quantity of demands of each area for the target agricultural products with different grades in the future; step S2: predicting the future output quantity of each target farmland; step S3: calculating the total output quantity of the target agricultural products at different grades based on the first table and the second table, and the total demand quantity of the target agricultural products at different grades in each region, if the total output quantity of the target agricultural products at all grades is smaller than the total demand quantity, generating an adjustment strategy, and generating a third table based on the adjustment strategy; step S4: generating a regional supply plan based on the first table and the third table; step S5: and calculating a second qualification rate of each region, and generating warning information based on the second qualification rate. The invention can dynamically adjust the sales strategy of the agricultural products based on the actual yield and demand of the agricultural products.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to an agricultural product marketing method, system and storage medium based on big data.
Background
The traditional agricultural product supply chain is faced with the problems of information lag, inflexibility in sales, low efficiency, large capital and manpower waste in supply chain circulation and the like, and in order to solve the problems, an agricultural product sales platform is established to solve the problems currently on the basis of cloud computing, big data and other technologies, specifically, the agricultural product sales platform collects historical data and analyzes the historical data to establish user figures of consumer groups in all areas, so that a dealer can know the specification preference, variety preference, price preference and the like of agricultural products in all areas conveniently, and further the dealer is assisted in carrying out accurate marketing of the agricultural products.
More specifically, the prior art proposes the following technical scheme to construct an agricultural product sales platform, for example, a Chinese patent application CN113627990A discloses a big data analysis system and analysis method for accurate sales of agricultural products, the method comprises a user terminal, a management terminal, a yield information acquisition module, a user information acquisition module, a sales data analysis module, a product pushing module, a warehouse entry registration module, a warehouse exit registration module, an inventory early warning module, a dynamic price adjustment module, an after-sales management module and an agricultural product sales platform, and the method can dynamically adjust the selling price by analyzing the purchasing habit of a user and the time of storing the agricultural products, thereby effectively improving the selling efficiency of the agricultural products and effectively ensuring that the agricultural products can be sold in time in a shelf life; for example, chinese patent application CN110163722a discloses a big data analysis system and analysis method for accurate sales of agricultural products, the method collects and stores data information in internet through big data base platform module, then extracts characteristic data information through data acquisition module and forms characteristic dataset, finally analyzes and processes the data information in the preprocessed dataset through data processing module, and finally outputs analysis result. The method is based on a big data platform, realizes the storage and analysis of data information, and builds a complete customer portrait, thereby finally achieving the purpose of accurate sales.
According to the scheme, the user portrait is constructed through the historical data, and then the future demands of the user are predicted based on the user portrait, so that the aims of accurate planting and sales are achieved; however, due to the specificity of the agricultural products, the predicted harvest result and the actual harvest result may have larger float during planting, which may occur when the yield and the demand of the agricultural products are different, so how to dynamically adjust the sales objective according to the actual yield of the agricultural products is a technical problem to be solved in the art.
Disclosure of Invention
In order to solve the problems, the invention provides a method, a system and a storage medium for marketing agricultural products based on big data, so as to dynamically adjust the marketing target according to the actual yield of the agricultural products.
In order to achieve the above object, the present invention provides a method for marketing agricultural products based on big data, comprising:
Step S1: setting standard parameters, classifying the quality of target agricultural products into grades A1-An based on the standard parameters, acquiring historical sales data of the target agricultural products, and predicting the quantity of demands of different grades of the target agricultural products in each future based on the historical sales data;
Step S2: selecting a plurality of target farmlands, acquiring the grade of the target agricultural products planned to be produced by each target farmland in advance, and acquiring information data of each target farmland, wherein the information data comprises soil data, environment data and growth image data, and predicting the future production quantity of each target farmland based on the information data;
Step S3: establishing a first table and a second table, sequentially filling the target agricultural product grades and the future output quantities of the target agricultural products produced by each target farmland into the first table, filling the required quantities of the target agricultural products with different grades in each region into the second table, calculating the total quantity of the target agricultural products with different grades in the first table, and the total quantity of the target agricultural products with different grades in the second table, if the total quantity of the target agricultural products with all grades is smaller than the total quantity of the required quantities, generating an adjustment strategy, calculating the loss value of the adjustment strategy, and if the loss value is smaller than a preset first threshold, adjusting the second table based on the adjustment strategy to generate a third table;
step S4: generating a supply plan for each region based on the first table and the third table, the supply plan including the target agricultural product quantity provided by the target agricultural field;
Step S5: after the target farmlands are harvested, calculating a first qualification rate of each target farmland, calculating a second qualification rate of each region based on the first qualification rate, setting a second threshold, and generating warning information if the second qualification rate is smaller than the second threshold.
Further, in the step S2, predicting the quantity of the target agricultural product produced by the target farmland in the future includes the steps of:
Step S21: establishing a first prediction model, a second prediction model and a third prediction model, wherein the first prediction model, the second prediction model and the third prediction model predict the future yield of the target agricultural product based on a first data set, a second data set and a third data set respectively, the first data set and the second data set contain time series data of the same type, but the acquisition frequency of each time series data is different, the third data set expands the data type on the basis of the first data set, and the time series data of the same type of the third data set and the time series data of the same type of the first data set are acquired with the same frequency;
Step S22: testing the first prediction model, the second prediction model and the third prediction model respectively to obtain a first tolerance, a second tolerance and a third tolerance which do not affect the prediction accuracy when data are lost;
Step S23: and acquiring the information data of the target agricultural product, calculating the missing degree of the information data, and compensating the information data if the corresponding prediction model cannot be matched based on the information data and the missing degree matching corresponding prediction model.
Further, compensating the information data based on the steps of;
Acquiring the earliest date of data deletion in the information data, judging whether the date is data deletion or not on the next day of the date, and if so, continuously judging whether the date is data deletion or not on the next day of the date, repeating the step, and directly positioning to the date on which the data is not deleted;
Acquiring the information data of a plurality of historical year data missing dates, and calculating the deviation value of the jth date in each historical year on the basis of a first formula The first formula is:
，
Wherein, Screening historical year date corresponding to the maximum deviation value for the information data of the jth date in the z year, and deleting the historical year date;
and calculating the average value of the information data on the same date as the missing date in the historical year after deletion, and setting the average value as a supplementary value of the missing date.
Further, in the step S3, calculating the loss value of the adjustment policy includes the steps of:
step S31: calculating the total amount of the demand of each region for all the levels of the target agricultural products, screening the region with the minimum total amount of the demand, defining the region as a low-value region, deleting the low-value region from the second table, recalculating the total amount of the demand of each level of the target agricultural products in the second table, repeating the step if the total amount of the output of the target agricultural products in all the levels is still smaller than the total amount of the demand, continuing deleting other regions in the second table until the total amount of the output of the target agricultural products in all the levels is greater than or equal to the total amount of the demand, and obtaining the third table;
step S32: adjusting the loss value of a policy based on a second formula: , Wherein/>After the second table is adjusted, the total output of the target agricultural products of each level is greater than the sum of the total demand, and the total output of the target agricultural products of each level is greater than the sum of the total demandAnd/>Before and after the second table is adjusted, the total output of the target agricultural products in each level is smaller than the sum of the total demands.
Further, in the step S4, generating the supply scheme for each region based on the first table and the third table includes the steps of:
step S41: calculating the demand rate of the mth region on the target agricultural product of the grade Ai in the second table based on a third formula The third formula is: /(I)Wherein/>Representing the demand of the mth region for the target agricultural product of the grade Ai,/>The total output of the target agricultural products is classified as Ai;
step S42: calculating the quantity of agricultural products needed to be provided by the M th piece of target farmland in the target farmland of the yield grade Ai based on a fourth formula The fourth formula is: /(I)Wherein/>And repeatedly calculating the number of the target agricultural products needed to be provided by other target farmlands based on the step for the number of the target agricultural products produced by the Mth target farmlands, and combining the number of the target agricultural products to generate the supply scheme of the Mth region.
Further, the step S5 calculates the first qualification rate and the second qualification rate based on the following steps:
step S51: calculating the first qualification rate of the M-th block of the grade Ai based on a fifth formula The fifth formula is: /(I)Wherein/>For the number of the target agricultural products which have been detected and which meet the current level corresponding to the standard parameter,/>Is the number of the target agricultural products that have been detected;
Step S52: when the number of the target agricultural products that have been detected by the respective target agricultural fields is equal to the number of the target agricultural products that need to be provided in the supply plan for the mth region, calculating the second percent of pass of the supply grade Ai of the target agricultural products to the mth region based on a sixth formula: 。
Further, in the step S52, after calculating the second qualification rate and generating the warning message, the method further includes the following steps:
If the second qualification rate of the mth region is lower than the second threshold value, positioning the target farmland with the lowest first qualification rate in the target farmland supplied to the region, acquiring the number of the target agricultural products provided by the target farmland, defining the number as a shortage, and calculating a screening value through a seventh formula The seventh formula is: /(I)Wherein/>For the second threshold,/>For the target farmland quantity supplied to the mth region,/>The sum of the first qualification rates of the rest of the target farmlands except the target farmlands with the lowest first qualification rate;
And obtaining the target farmland with the first qualification rate larger than the screening value from the target farmland supplied to the mth region, defining a standby farmland, selecting the standby farmland with the residual quantity of the target agricultural products larger than or equal to the deficient quantity from the standby farmland after the region is selected to be supplied, and using the farmland to supply the target agricultural products to the mth region.
The invention also provides a big data-based agricultural product marketing system, which is used for realizing the big data-based agricultural product marketing method, and mainly comprises the following steps:
the demand prediction module is internally provided with standard parameters, divides the quality of the target agricultural product into grades A1-An based on the standard parameters, acquires historical sales data of the target agricultural product, and predicts the demand quantity of the target agricultural product in different grades in the future based on the historical sales data;
A yield prediction module, which selects a plurality of target farmlands from the yield prediction module, obtains the grade of each target farm land for planning to produce the target agricultural products, and collects information data of each target farm land, wherein the information data comprises soil data, environment data and growth image data, and predicts the future yield quantity of each target farm land based on the information data;
The scheme generation module is used for establishing a first table and a second table, sequentially filling the target agricultural product grade and the future yield quantity of each target agricultural product produced by the farmland into the first table, filling the required quantity of the target agricultural products with different grades in each region into the second table, calculating the total quantity of the target agricultural products with different grades in the first table, and the total quantity of the target agricultural products with different grades in the second table, if the total quantity of the target agricultural products with all grades is smaller than the total quantity of the required products, generating an adjustment strategy, calculating the loss value of the adjustment strategy, and if the loss value is smaller than a preset first threshold, adjusting the second table based on the adjustment strategy to generate a third table, and generating a supply scheme of each region based on the first table and the third table, wherein the supply scheme comprises the target agricultural products and the target quantity provided by the target agricultural products;
The early warning generation module calculates the first qualification rate of each target farmland after the target farmland is harvested, calculates the second qualification rate of each region based on the first qualification rate, sets a second threshold value, and generates warning information if the second qualification rate is smaller than the second threshold value.
The invention also provides a computer storage medium which stores program instructions, wherein the equipment where the computer storage medium is located is controlled to execute the agricultural product marketing method based on big data when the program instructions run.
Compared with the prior art, the invention has the following beneficial effects:
firstly, dividing agricultural products into a plurality of grades by setting standard parameters, and then predicting future demand of each region based on historical sales data; then, soil data, environment data and image data in farmlands are collected through sensors, so that the agricultural product output of each farmland is predicted; after the output and the demand of the agricultural products are obtained, a first table and a second table are established, the output and the demand of the agricultural products with the same grade are compared based on the first table and the second table, so that future supply and demand conditions are predicted, if the supply and demand of all the agricultural products are smaller than the demand, a corresponding adjustment strategy is generated, a loss value of the adjustment strategy is calculated, if the loss value is overlarge, the adjustment of the sales target based on the adjustment strategy is indicated to cause larger loss, the sales target is not adjusted, and if the loss value is smaller, the adjustment of the sales target based on the adjustment strategy is indicated to reduce the loss, and therefore the sales target can be adjusted. Therefore, the invention generates the corresponding adjustment strategy by calculating the supply-demand relationship between the agricultural products and the market, so as to realize the dynamic adjustment of the sales targets and reduce the loss of unbalanced supply-demand relationship as much as possible.
The first qualification rate of each farmland is calculated, and then the second qualification rate is calculated based on the first qualification rate; therefore, the agricultural qualification rate supplied to each region can be calculated, so that the supply quality of agricultural products is ensured, and the influence of the too low supply quality on the sales of the products is avoided.
Drawings
FIG. 1 is a flow chart of the steps of a method for marketing agricultural products based on big data according to the present invention;
FIG. 2 is a schematic diagram of a first table of the present invention;
FIG. 3 is a schematic diagram of a second table of the present invention;
Fig. 4 is a schematic structural diagram of an agricultural product marketing system based on big data according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It will be understood that the terms "first," "second," and the like, as used herein, may be used to describe various elements, but these elements are not limited by these terms unless otherwise specified. These terms are only used to distinguish one element from another element. For example, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script, without departing from the scope of this disclosure.
As shown in FIG. 1, a method for marketing agricultural products based on big data includes.
Step S1: setting standard parameters, classifying the quality of the target agricultural products into grades A1-An based on the standard parameters, acquiring historical sales data of the target agricultural products, and predicting the quantity of demands of different grades of target agricultural products in each area in the future based on the historical sales data.
Specifically, taking fruit F as an example, the standard parameters include the external dimensions, sugar content, skin color, etc., for example, the present embodiment classifies the fruit F into a class A1, a class A2 and a class A3 based on the standard parameters, and then obtains historical sales data of the fruit F, where the historical sales data includes sales data of the fruit F of the class A1, the class A2 and the class A3 in the region 1, the region 2 and the region 3, where sales are weights of the fruit F, for example, sales are 500kg, and numbers described later are also weights. And then predicting the demand of different grades of fruits in each area in the future based on the historical sales data, wherein the prediction method can be determined by relatively simple and average value of sales of the past years, and can also be used for establishing relatively complex machine learning models, such as BP neural network models or LSTM neural network models, which are well known to those skilled in the art and are not repeated herein.
Step S2: and selecting a plurality of target farmlands, acquiring the grade of target agricultural products planned to be produced by each target farmland in advance, and acquiring information data of each target farmland, wherein the information data comprise soil data, environment data and growth image data, and predicting the future production quantity of each target farmland based on the information data.
Generally, the planting and culturing modes of the farmland are determined before planting, so that the fruit grade to be produced by the farmland is determined, therefore, after a target farmland is selected, the grade of fruit F to be produced by each target farmland is obtained, then soil information, environment data and image data of each target farmland are collected through sensors arranged in the farmland, wherein the soil information comprises the content of various elements in the soil, the environment data comprises information such as temperature, humidity and illumination data, and the growth image data comprises the appearance image information of the fruit F in the process from planting to fruiting. Similarly, when the output data of the target farmland is required to be predicted, the prediction can be also performed based on the model method described above. In particular, predictions herein refer to short-term predictions, typically made when agricultural products are to be harvested, so that the yield of the farm field is known in advance, and a future sales plan is made.
Step S3: establishing a first table and a second table, sequentially filling the grade of the target agricultural products produced by each target farmland and the future yield into the first table, filling the required quantity of the target agricultural products with different grades in each region into the second table, calculating the total quantity of the target agricultural products with different grades in the first table and the required quantity of the target agricultural products with different grades in the second table, generating an adjustment strategy if the total quantity of the target agricultural products with all grades is smaller than the required total quantity, calculating the loss value of the adjustment strategy, and adjusting the second table based on the adjustment strategy if the loss value is smaller than a preset first threshold value to generate a third table.
As shown in fig. 2, for the fruit F, the first table is filled with the grades of the fruit F produced by each target farmland and the corresponding predicted yields, and arranged in descending order of the predicted yields, for example, in fig. 2, the first column of the table is filled with the numbers of each target farmland, the second column is filled with the grades of the fruit F produced by the target farmland, and the third column is filled with the corresponding yields; in the second table of fig. 3, the first column is filled with the numbers of each region, and the second and third columns are filled with the required number of different grades of fruit F for each region.
After the two tables are filled, calculating the total output and the total demand of each grade of fruit F in the first table and the second table, for example, the total expected output of the grade a fruit F is 300+200=500 kg, as shown in fig. 3, the total expected demand of the grade a fruit F is 200+200+150=550 kg, which means that the target total output of the grade A1 agricultural product is smaller than the demand, and similarly, calculating the other grades of fruit based on the principle, and finally, the results show that the output of all grades of fruit is lower than the demand, and at this time, an adjustment strategy needs to be generated; specifically, the adjustment policy is to delete the product supply to a certain area, for example, delete the product supply to the area 3 in this embodiment, calculate the loss value of implementing the adjustment policy after the adjustment policy is generated, and delete the product supply to the area in the second table if the loss value is smaller than the first threshold; if the loss value is greater than or equal to a preset first threshold value, the second table is not adjusted.
Step S4: a supply plan for each region is generated based on the first table and the third table, the supply plan including a target agricultural product quantity provided by the target agricultural field.
For example, after the third table is created, a supply scheme is created for area 1, with the farmland 1, farmland 4 and farmland 6 providing the area 1 with fruit F of grade A2 in supply amounts of 560kg, 466.7kg and 373.3kg, respectively, in a manner to be described later; if the second table is not adjusted, sales in each region are manually assigned.
Step S5: after harvesting the target farmlands, calculating the first qualification rate of each target farmland, calculating the second qualification rate of each region based on the first qualification rate, setting a second threshold value, and generating warning information if the second qualification rate is smaller than the second threshold value.
Specifically, after the agricultural products are harvested, the standard parameters of the agricultural products are measured to calculate the qualification rate of the farmland, wherein the overall dimension, the sugar content, the skin color and the like can be obtained through image analysis, and the sugar content can be subjected to nondestructive measurement through a near infrared spectrum technology; therefore, the agricultural qualification rate supplied to each region can be calculated, so that the supply quality of agricultural products is ensured, and the influence of the too low supply quality on the sales volume and the acquisition rate of the products is avoided.
Firstly, dividing agricultural products into a plurality of grades by setting standard parameters, and then predicting future demand of each region based on historical sales data; then, soil data, environment data and image data in farmlands are collected through sensors, so that the agricultural product output of each farmland is predicted; after the output and the demand of the agricultural products are obtained, a first table and a second table are established, the output and the demand of the agricultural products with the same grade are compared based on the first table and the second table, so that future supply and demand conditions are predicted, if the supply and demand of all the agricultural products are smaller than the demand, a corresponding adjustment strategy is generated, a loss value of the adjustment strategy is calculated, if the loss value is overlarge, the adjustment of the sales target based on the adjustment strategy is indicated to cause larger loss, the sales target is not adjusted, and if the loss value is smaller, the adjustment of the sales target based on the adjustment strategy is indicated to reduce the loss, and therefore the sales target can be adjusted. Therefore, the invention generates the corresponding adjustment strategy by calculating the supply-demand relationship between the agricultural products and the market, so as to realize the dynamic adjustment of the sales targets and reduce the loss of unbalanced supply-demand relationship as much as possible.
The first qualification rate of each farmland is calculated, and then the second qualification rate is calculated based on the first qualification rate; therefore, the agricultural qualification rate supplied to each region can be calculated, so that the supply quality of agricultural products is ensured, and the influence of the too low supply quality on the sales of the products is avoided.
It is particularly noted that the present invention dynamically adjusts the marketing strategy of agricultural products based on the actual yield and demand of the agricultural products, thereby reducing the instances of diapause of the agricultural products.
In the actual prediction of the yield of agricultural products, only one model is often set in the system to predict, however, due to various factors in reality, the loss of the actually collected environmental data can influence the prediction accuracy of the model, and even the model cannot predict, so that the invention proposes the following steps to predict the yield of the agricultural products in the future.
Step S21: and establishing a first prediction model, a second prediction model and a third prediction model, wherein the first prediction model, the second prediction model and the third prediction model predict the future target agricultural product yield based on a first data set, a second data set and a third data set respectively, the first data set and the second data set contain time series data of the same type, but the acquisition frequencies of the time series data are different, the data type of the third data set is expanded on the basis of the first data set, and the acquisition frequency of the time series data of the same type of the third data set and the time series data of the first data set are the same.
The first prediction model, the second prediction model and the third prediction model are all established based on a machine learning technology, in the first data set of the embodiment, soil, air temperature, humidity and growth images are included, the collection interval of the first data set is one day, the second data set also includes soil, air temperature, humidity and growth images, the collection interval of the second data set is 4 hours, and the third data set includes soil, air temperature, humidity, growth images and sunlight data, and the collection interval of the third data set is one day. Then, before the model is predicted in the data input of the data set, the average value is calculated to predict, for example, the acquisition interval of the first data set is 1 day, and then the data of the first data set is directly input into the prediction model; and if the acquisition interval of the second data set is 4 hours, accumulating the second data set, averaging the second data set and inputting the second data set into the prediction model.
Step S22: and respectively testing the first prediction model, the second prediction model and the third prediction model to obtain a first tolerance, a second tolerance and a third tolerance which do not affect the prediction accuracy when the data is lost.
In the actual data acquisition process, due to sensor faults and other reasons, the acquired data may be missing, for example, the first data set should include data of 1 # to 30 # within one month, but temperature data is missing between 8 # and 10 #, which may affect the prediction accuracy of the model, so that the tolerance of each model to the missing data needs to be tested in advance; in the test, the tolerance of the model to the data missing is tested by inputting the data with different missing degrees into a first prediction model, a second prediction model and a third prediction model and by the prediction results of the three models, and in the embodiment, the first tolerance and the second tolerance of the first prediction model and the second prediction model to the temperature data are respectively 15%, 5%, and the third tolerance and 11% of the third prediction model to the sunlight data.
Step S23: obtaining information data of the target agricultural product, calculating the missing degree of the information data, matching a corresponding prediction model based on the information data and the missing degree, and compensating the information data if the corresponding prediction model cannot be matched.
For example, the collected information data includes soil, air temperature, humidity, growth image and sunlight data, the collected information data is corresponding to a third prediction model, the sunlight data is excluded if the loss degree of the sunlight data is 20%, the first prediction model and the second prediction model are used for prediction, then the collection frequency of each data type in the information data is obtained, if the collection frequency is 1 day, the future farmland yield is predicted based on the first prediction model, and if the collection frequency is 4 hours, the future farmland yield is predicted based on the second prediction model; in addition, if the acquisition frequency is 4 hours, but the degree of missing of the temperature data is 10%, and the first prediction model and the second prediction model can input the same type of data, so that the average value of the temperature data can be calculated and the first prediction model can be used for predicting the future yield of the farmland; if the missing value of the temperature data is 20%, the temperature data needs to be compensated for so as to predict.
Through the steps, a plurality of prediction models are established, so that different prediction models can be matched based on different acquired data, the future yield of the model can be predicted, and the prediction accuracy is ensured.
In this embodiment, the acquired data is compensated based on the following steps.
And acquiring the earliest date of data missing in the information data, and judging whether the date is missing or not on the next day of the date, if so, continuously judging whether the date is missing or not on the next day of the date, repeating the step, and directly positioning to the date on which the data is not missing.
Taking the temperature data in the information data as an example, if the temperature data has data deletion for the first time in 3 months of 2013 and 10 days, continuously judging whether the data deletion exists in 3 months and 11 days, if the data deletion still exists, continuously acquiring the data in 3 months and 12 days, repeating the steps until the data deletion does not occur in a certain date, for example, the data deletion does not occur in 3 months and 15 days, and setting the data deletion date as 3 months and 10 days to 3 months and 15 days.
Acquiring information data of missing dates of a plurality of historical year data, and calculating deviation values of the jth date in each historical year according to a first formulaThe first formula is:
，
Wherein, And screening the historical year date corresponding to the maximum deviation value for the information data of the jth date in the z year, and deleting the historical year date.
Specifically, after determining that the data of 3 months 10 to 3 months 15 is missing, temperature data of 3 months 9 to 3 months 16 years of 2010 to 2012 is obtained, then each date deviation value of each year is calculated based on a first formula, for example, 9 temperatures of 3 months 9 to 3 months 11 of 2009, 2010 and 2011 are obtained, then an average value of the temperatures of 3 months 9 to 3 months 11 of 2009 is calculated, for example, 15.2 ℃, 15.5 ℃, 16.9 ℃, then the average value is (15.2+15.5+16.9)/3=15.8, then an average value of the temperatures of 3 months 9 to 3 months 11 of 2010 is calculated, for example, 17, repeating this step, the average value of the temperatures of 3 months 9 to 3 months 11 of 2010 is calculated, then the deviation of 3 months 10 of 2010 is calculated to (17-15.8) + (17-15.5) =2.7, and then the difference value of 3 months 11 of 2012 to 3 months 11 is calculated based on the data of 3 months 11 of 2012 is calculated.
If the deviation values of other dates are less than 2.7 in 2010 to 2012, deleting the date of 3 months in 2010 and the date of 10 months in 2012, and only selecting the temperature data of the date of 3 months in 2011 and the date of 10 months in 2012 for addition and averaging when the calculation is carried out later. Therefore, the abnormality in the historical year is removed through the step, so that the accuracy and the rationality of the compensation data are ensured.
And calculating the average value of date information data which is the same as the missing date in the historical year after deletion, and setting the average value as a supplementary value of the missing date.
Taking the example of day 3 and 10, in the above case, the temperature data of 2011 and 2012 at day 3 and 10 are averaged, and the average value is taken as the temperature data of day 2013 and day 3 and 10.
In step S3 of the present embodiment, calculating the adjustment policy loss value includes the steps of:
Step S31: calculating the total quantity of the demands of all the levels of the target agricultural products in each region, screening the region with the minimum total quantity of the demands, defining the region as a low-value region, deleting the low-value region from the second table, recalculating the total quantity of the demands of all the levels of the target agricultural products in the second table, repeating the step if the total quantity of the target agricultural products in all the levels is still smaller than the total quantity of the demands, continuously deleting other regions in the second table until the total quantity of the target agricultural products in all the levels is larger than or equal to the total quantity of the demands, and obtaining a third table.
Specifically, when the fruit F output of the grades A1, A2, A3 is smaller than the demand, firstly calculating the total demand of each region, screening the region with the smallest total demand, for example, the demand of region 1, region 2 and region 3 for three grades of fruit F is 200+800+700=1700, 200+600+600=1400, 150+200+500=850, respectively, thus setting region 3 as a low value region, and deleting region 3 from the second table; then, the relation between the output and the demand of the grade A1 is recalculated, after the area 3 is deleted, the demand of the grade A1, A2 and A3 is 400kg, 1400kg and 1300kg, the output is larger than the demand, and the requirement is met, so the second table after the area 3 is deleted is set as a third table.
Step S32: and adjusting the loss value of the strategy based on a second formula, wherein the second formula is as follows: Wherein/> After the second table is adjusted, the total output of the agricultural products of each grade is greater than the total sum of the total demand, and the total output of the agricultural products of each grade is greater than the total sum of the total demandAnd/>Before and after the second table is adjusted, the total output of the target agricultural products of each grade is smaller than the sum of the total demand.
In the foregoing calculation, it has been obtained that the yield of the grade A1 is 500kg, the yield of the grade A2 is 1500kg, the yield of the grade A3 is 1700kg, after the adjustment to obtain the third table, the total demand for the grade A1 is 400kg, the total demand for the grade A2 is 1400kg, and the total demand for the grade A3 is 1300kg, then the value of B1 is (500-400) + (1500-1400) + (1700-1300) =600 by calculation, the value of B2 is (550-500) + (1600-1500) + (1800-1500) =450 before the adjustment to obtain the second table, since the yield of all the grade agricultural products is greater than the demand after the adjustment, the value of B3 is 0, then it is substituted into the second formula, the loss value of the adjustment policy is 600/450=1.33, and if the first threshold is set to 1, it is indicated that deleting the region 3 will cause greater loss.
The core idea of the step is that the adjustment strategy is evaluated by calculating the supply-demand relationship before and after adjustment, if the adjusted loss value is more than 1, the difference value of the supply-demand relationship after adjustment is enlarged, so that the region does not need to be deleted; if the loss value is smaller than 1, it indicates that the supply-demand relationship after adjustment is reduced, for example, after deleting a certain area, the difference between the output and the demand is reduced, which indicates that the adjustment has a beneficial effect, so that the second table can be adjusted to the third table. The reason for adopting the strategy is that in the case of unbalanced supply and demand, the difference between supply and demand is reduced by adjusting the strategy, in the case of smaller difference, the sales personnel can more conveniently adjust the supply and demand relationship by other ways, and in the way of deleting a whole area, the situation that even if the demand of a certain area is lower, the situation that the supply is possibly carried out can be avoided, because the situation greatly increases the transportation cost of products.
It should be noted that, the adjustment policy is only a suggested policy generated in the system, and only assists the relevant sales person to make a judgment.
In step S4 in the present embodiment, generating a supply scheme for each region based on the first table and the target table includes the following steps.
Step S41: calculating the demand rate of the mth region on the grade Ai target agricultural products in the second table based on the third formulaThe third formula is: /(I)Wherein/>Represents the demand of the mth region for the grade Ai target agricultural product,The total output of the agricultural products is the grade Ai target.
Step S42: calculating the quantity of agricultural products needed to be provided by the M th target farmland in the target farmland of the yield grade Ai based on the fourth formulaThe fourth formula is: /(I)Wherein/>And repeatedly calculating the number of the target agricultural products needed to be provided by other target farmlands based on the step for the number of the target agricultural products produced by the Mth target farmlands, and combining the number of the target agricultural products to generate a supply scheme of the Mth region.
With continued reference to fig. 2 and 3, for example, the demand of zone 1 for level A2 is 800kg and the total output of level A2 is 1500kg, then it is calculated by substituting it into the third equation, and the demand rate of zone 1 for level A2 is 800/1500≡0.53. The amount of product to be provided per farmland is then calculated based on the demand, for example, 600 x 0.53=318 kg for farmland 1, 500 x 0.53=265 kg for farmland 4 and 212kg for farmland 6. The supply scheme of each area is sequentially generated through the mode, so that fruits can be harvested from each farmland at the same time, the larger the yield of the farmland is, the more agricultural products need to be provided, the harvesting efficiency of the farmland with high yield can be ensured, the condition that agricultural products decay due to slower harvesting is avoided, meanwhile, the low-yield farmland can be ensured to supply goods to the area, and the balance of agricultural product harvesting is ensured to be provided.
In the present embodiment, the first yield and the second yield are calculated based on the following steps.
Step S51: calculating a first qualification rate of the Mth target farmland of the grade Ai based on a fifth formulaThe fifth formula is: /(I)Wherein/>For the number of target agricultural products that have completed the detection and meet the current level corresponding standard parameters,Is the number of target agricultural products that have been detected.
Specifically, the expected yield of farmland 1 is 600kg, because it is required to provide 318kg of agricultural products to area 1, and thus the quality of the agricultural products is continuously checked when it is harvested, and the first qualification rate of the agricultural products is updated, for example, when the farmland is harvested to 318kg, 318kg is D in the formula, of which 318kg of agricultural products 302kg are judged as grade A1 and the remaining 16kg of agricultural products are judged as grade A2 or A3, and then the first qualification rate of the farmland is 302/318≡0.95.
Step S52: when the number of target agricultural products that have been detected by each target agricultural field is equal to the number of target agricultural products that need to be provided in the mth regional supply scheme, calculating a second yield of the supply of the grade Ai target agricultural products to the mth regional based on a sixth formula:。
Since the area 1 needs to receive the agricultural products supplied from the farmlands 1,4 and 6, the first pass rates thereof need to be calculated by using the above steps, and by calculating the first pass rates of the farmlands 4 and 6 to be 0.9 and 0.95, respectively, then substituting the first pass rates into the sixth formula to calculate the second pass rate of the agricultural products supplied to the area 1 to be (0.95+0.9+0.95)/3 means 0.93.
In this embodiment, after calculating the second qualification rate and generating the warning information in step S52, the following steps are further included.
If the second qualification rate of the mth region is lower than the second threshold value, locating a target farmland with the lowest first qualification rate in the target farmland supplied to the region, acquiring the number of target agricultural products provided by the target farmland, defining the number as a shortage number, and calculating a screening value through a seventh formulaThe seventh equation is: /(I)Wherein/>Is a second threshold,/>For the target farmland quantity supplied to the mth region,/>The first qualification rate is the sum of the first qualification rates of other target farmlands except the target farmlands with the lowest first qualification rate;
And obtaining a target farmland with a first qualification rate larger than a screening value from target farmland supplied to an mth region, defining the target farmland as a standby farmland, selecting the standby farmland with a target agricultural product allowance larger than or equal to the deficient quantity from the standby farmland after the region supply is completed, and using the farmland to supply target agricultural products to the mth region.
The above steps will be explained below, assuming that farmlands 7, 8, 9 and 10 for providing fruit F to the area 4 (not shown) have a first qualification rate of 0.9, 0.85, 0.65 and 0.6, respectively, and a second qualification rate of 0.75, if the second threshold is set to 0.8, the second qualification rate is smaller than the second threshold, and the amount of fruit F required to be provided by the area 10 is acquired, and if it is required to provide 400kg of fruit F to the area 4, the shortage amount is set to 400kg; then, the screening value is calculated by the seventh formula, and if the screening value x=0.8x4- (0.9+0.85+0.65) =0.8, then the farmland with the first qualification rate greater than 0.8, specifically, farmland 7 and farmland 8, is selected from farmland 7, farmland 8, and farmland 9, and if the remaining amount of farmland 8 is still greater than 400kg after the supply of agricultural products to all areas except area 4 is completed, then 400kg is supplied to area 4.
As shown in fig. 4, the present invention further provides a big data based agricultural product marketing system, which is used for implementing the above-mentioned big data based agricultural product marketing method, and the system mainly includes:
The demand prediction module is internally provided with standard parameters, divides the quality of the target agricultural products into grades A1-An based on the standard parameters, acquires historical sales data of the target agricultural products, and predicts the demand quantity of the target agricultural products with different grades in each future based on the historical sales data;
The yield prediction module is used for selecting a plurality of target farmlands, acquiring the grade of a target agricultural product planned to be produced by each target farmland, acquiring information data of each target farmland, wherein the information data comprises soil data, environment data and growth image data, and predicting the future production quantity of each target farmland based on the information data;
The scheme generation module is used for establishing a first table and a second table, sequentially filling the grade and the future yield quantity of the target agricultural products produced by each target farmland into the first table, filling the required quantity of the target agricultural products with different grades in each region into the second table, calculating the total quantity of the produced of the target agricultural products with different grades in the first table and the required quantity of the target agricultural products with different grades in the second table, generating an adjustment strategy if the total quantity of the produced of the target agricultural products with all grades is smaller than the required quantity, calculating the loss value of the adjustment strategy, and adjusting the second table based on the adjustment strategy to generate a third table if the loss value is smaller than a preset first threshold, wherein the scheme generation module generates a supply scheme of each region based on the first table and the third table, and the supply scheme comprises the target farmland and the target quantity provided by the target agricultural products;
the early warning generation module calculates the first qualification rate of each target farmland after the target farmland is harvested, calculates the second qualification rate of each region based on the first qualification rate, sets a second threshold value, and generates warning information if the second qualification rate is smaller than the second threshold value.
The invention also provides a computer storage medium which stores program instructions, wherein the equipment where the computer storage medium is located is controlled to execute the agricultural product marketing method based on big data when the program instructions run.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that implementing all or part of the above-described methods may be accomplished by way of computer programs, which may be stored on a non-transitory computer readable storage medium, and which, when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the foregoing embodiments may be arbitrarily combined, and for brevity, all of the possible combinations of the technical features of the foregoing embodiments are not described, however, they should be considered as the scope of the disclosure as long as there is no contradiction between the combinations of the technical features.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (3)
1. A method of marketing agricultural products based on big data, comprising:
Step S1: setting standard parameters, classifying the quality of target agricultural products into grades A1-An based on the standard parameters, acquiring historical sales data of the target agricultural products, and predicting the quantity of demands of different grades of the target agricultural products in each future based on the historical sales data;
Step S2: selecting a plurality of target farmlands, acquiring the grade of the target agricultural products planned to be produced by each target farmland in advance, and acquiring information data of each target farmland, wherein the information data comprises soil data, environment data and growth image data, and predicting the future production quantity of each target farmland based on the information data;
Step S3: establishing a first table and a second table, sequentially filling the target agricultural product grades and the future output quantities of the target agricultural products produced by each target farmland into the first table, filling the required quantities of the target agricultural products with different grades in each region into the second table, calculating the total quantity of the target agricultural products with different grades in the first table, and the total quantity of the target agricultural products with different grades in the second table, if the total quantity of the target agricultural products with all grades is smaller than the total quantity of the required quantities, generating an adjustment strategy, calculating the loss value of the adjustment strategy, and if the loss value is smaller than a preset first threshold, adjusting the second table based on the adjustment strategy to generate a third table;
step S4: generating a supply plan for each region based on the first table and the third table, the supply plan including the target agricultural product quantity provided by the target agricultural field;
Step S5: after the target farmlands are harvested, calculating a first qualification rate of each target farmland, calculating a second qualification rate of each region based on the first qualification rate, setting a second threshold, and generating warning information if the second qualification rate is smaller than the second threshold;
In the step S2, predicting the quantity of the target agricultural products produced by the target farmland in the future includes the steps of:
Step S21: establishing a first prediction model, a second prediction model and a third prediction model, wherein the first prediction model, the second prediction model and the third prediction model predict the future yield of the target agricultural product based on a first data set, a second data set and a third data set respectively, the first data set and the second data set contain time series data of the same type, but the acquisition frequency of each time series data is different, the third data set expands the data type on the basis of the first data set, and the time series data of the same type of the third data set and the time series data of the same type of the first data set are acquired with the same frequency;
Step S22: testing the first prediction model, the second prediction model and the third prediction model respectively to obtain a first tolerance, a second tolerance and a third tolerance which do not affect the prediction accuracy when data are lost;
Step S23: acquiring the information data of the target agricultural product, calculating the missing degree of the information data, and compensating the information data if the corresponding prediction model cannot be matched based on the information data and the missing degree;
compensating the information data based on the following steps;
Acquiring the earliest date of data deletion in the information data, judging whether the date is data deletion or not on the next day of the date, and if so, continuously judging whether the date is data deletion or not on the next day of the date, repeating the step, and directly positioning to the date on which the data is not deleted;
Acquiring the information data of a plurality of historical year data missing dates, and calculating the deviation value of the jth date in each historical year on the basis of a first formula The first formula is:
，
Wherein, Screening historical year date corresponding to the maximum deviation value for the information data of the jth date in the z year, and deleting the historical year date;
Calculating an average value of the information data on the same date as the missing date in the historical year after deletion, and setting the average value as a supplementary value of the missing date;
The step S5 calculates the first yield and the second yield based on the steps of:
step S51: calculating the first qualification rate of the M-th block of the grade Ai based on a fifth formula The fifth formula is: /(I)Wherein D is the number of the target agricultural products which have been detected and meet the standard parameters corresponding to the current level, and D is the number of the target agricultural products which have been detected;
Step S52: when the number of the target agricultural products that have been detected by the respective target agricultural fields is equal to the number of the target agricultural products that need to be provided in the supply plan for the mth region, calculating the second percent of pass of the supply grade Ai of the target agricultural products to the mth region based on a sixth formula:
In the step S3, calculating the loss value of the adjustment policy includes the steps of:
step S31: calculating the total amount of the demand of each region for all the levels of the target agricultural products, screening the region with the minimum total amount of the demand, defining the region as a low-value region, deleting the low-value region from the second table, recalculating the total amount of the demand of each level of the target agricultural products in the second table, repeating the step if the total amount of the output of the target agricultural products in all the levels is still smaller than the total amount of the demand, continuing deleting other regions in the second table until the total amount of the output of the target agricultural products in all the levels is greater than or equal to the total amount of the demand, and obtaining the third table;
Step S32: adjusting the loss value of a policy based on a second formula: wherein, B 1 is the sum of the total output amount of the target agricultural products of each level is greater than the total output amount of the demand after the adjustment of the second table, and B 2 and B 3 are the sum of the total output amount of the target agricultural products of each level is less than the total output amount of the demand before and after the adjustment of the second table;
In the step S52, after calculating the second qualification rate and generating the warning message, the method further includes the following steps:
If the second qualification rate of the mth region is lower than the second threshold value, positioning the target farmland with the lowest first qualification rate, obtaining the number of the target agricultural products provided by the target farmland, defining the number as a shortage, and calculating a screening value x by a seventh formula, wherein the seventh formula is as follows: x=ω×k- γ, where ω is the second threshold value, k is the target number of farmlands supplied to the mth region, and γ is the sum of the first yields of the remaining target farmlands except the target farmlands whose first yields are lowest;
obtaining the target farmland with the first qualification rate larger than the screening value from the target farmland supplied to the mth region, defining a standby farmland, selecting the standby farmland with the residual quantity of the target agricultural products larger than or equal to the deficient quantity from the standby farmland after the region is selected to be supplied, and using the farmland to supply the target agricultural products to the mth region;
in the step S4, generating the supply scheme for each region based on the first table and the third table includes the steps of:
step S41: calculating the demand rate of the mth region on the target agricultural product of the grade Ai in the second table based on a third formula The third formula is: /(I)Wherein/>The demand of the mth region for the target agricultural products of the grade Ai is represented, and W Ai is the total output quantity of the target agricultural products of the grade Ai;
Step S42: calculating the quantity p M of agricultural products required to be provided by the M th piece of target farmland in the target farmland of the yield grade Ai based on a fourth formula, wherein the fourth formula is as follows: And P M is the number of the target agricultural products produced by the Mth target farmland, the number of the target agricultural products needed to be provided by other target farmlands is repeatedly calculated based on the step, and the target agricultural products are combined to generate the supply scheme of the Mth region.
2. A big data based agricultural product marketing system for implementing the big data based agricultural product marketing method of claim 1, comprising:
the demand prediction module is internally provided with standard parameters, divides the quality of the target agricultural product into grades A1-An based on the standard parameters, acquires historical sales data of the target agricultural product, and predicts the demand quantity of the target agricultural product in different grades in the future based on the historical sales data;
A yield prediction module, which selects a plurality of target farmlands from the yield prediction module, obtains the grade of each target farm land for planning to produce the target agricultural products, and collects information data of each target farm land, wherein the information data comprises soil data, environment data and growth image data, and predicts the future yield quantity of each target farm land based on the information data;
the scheme generation module is used for establishing a first table and a second table, sequentially filling the target agricultural product grade and the future yield quantity of each target agricultural product produced by the farmland into the first table, filling the required quantity of the target agricultural products with different grades in each region into the second table, calculating the total quantity of the target agricultural products with different grades in the first table, and the required quantity of the target agricultural products with different grades in the second table, if the total quantity of the target agricultural products with all grades is smaller than the required quantity, generating an adjustment strategy, calculating the loss value of the adjustment strategy, if the loss value is smaller than a preset first threshold, adjusting the second table based on the adjustment strategy to generate a third table, and generating a supply scheme of each region based on the first table and the third table, wherein the supply scheme comprises the target farmland and the target agricultural product quantity provided by the target farmland;
The early warning generation module calculates the first qualification rate of each target farmland after the target farmland is harvested, calculates the second qualification rate of each region based on the first qualification rate, sets a second threshold value, and generates warning information if the second qualification rate is smaller than the second threshold value.
3. A computer storage medium storing program instructions, wherein the program instructions, when executed, control a device in which the computer storage medium is located to perform a method of marketing commodity based on big data as claimed in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310953855.5A CN116703468B (en) | 2023-08-01 | 2023-08-01 | Agricultural product marketing method, system and storage medium based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310953855.5A CN116703468B (en) | 2023-08-01 | 2023-08-01 | Agricultural product marketing method, system and storage medium based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116703468A CN116703468A (en) | 2023-09-05 |
| CN116703468B true CN116703468B (en) | 2024-05-07 |
Family
ID=87832453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310953855.5A Active CN116703468B (en) | 2023-08-01 | 2023-08-01 | Agricultural product marketing method, system and storage medium based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116703468B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732426A (en) * | 2015-03-25 | 2015-06-24 | 中国农业科学院农业信息研究所 | Agricultural product production and sale decision-making method, device and system |
| CN112329709A (en) * | 2020-11-25 | 2021-02-05 | 中国农业大学 | Intelligent agricultural product control system, method, computer equipment and storage medium |
| CN113378793A (en) * | 2021-07-09 | 2021-09-10 | 北京京东乾石科技有限公司 | Crop yield prediction method and device |
| CN113435649A (en) * | 2021-06-29 | 2021-09-24 | 布瑞克农业大数据科技集团有限公司 | Global agricultural data sorting method, system, device and medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA2987761A1 (en) * | 2017-12-06 | 2019-06-06 | South Country Equipment Ltd. | Water-driven crop yield potential forecasting |
-
2023
- 2023-08-01 CN CN202310953855.5A patent/CN116703468B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104732426A (en) * | 2015-03-25 | 2015-06-24 | 中国农业科学院农业信息研究所 | Agricultural product production and sale decision-making method, device and system |
| CN112329709A (en) * | 2020-11-25 | 2021-02-05 | 中国农业大学 | Intelligent agricultural product control system, method, computer equipment and storage medium |
| CN113435649A (en) * | 2021-06-29 | 2021-09-24 | 布瑞克农业大数据科技集团有限公司 | Global agricultural data sorting method, system, device and medium |
| CN113378793A (en) * | 2021-07-09 | 2021-09-10 | 北京京东乾石科技有限公司 | Crop yield prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116703468A (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bang et al. | Fuzzy logic based crop yield prediction using temperature and rainfall parameters predicted through ARMA, SARIMA, and ARMAX models | |
| US20210209705A1 (en) | System and Method for Managing and Operating an Agricultural-Origin-Product Manufacturing Supply Chain | |
| Divisekara et al. | Forecasting the red lentils commodity market price using SARIMA models | |
| Bocca et al. | When do I want to know and why? Different demands on sugarcane yield predictions | |
| Medar et al. | Sugarcane crop yield forecasting model using supervised machine learning | |
| Paam et al. | The impact of inventory management on economic and environmental sustainability in the apple industry | |
| US20170364816A1 (en) | Prediction of Discernible Fungus Establishment on a Crop | |
| Çakır et al. | Yield prediction of wheat in south-east region of Turkey by using artificial neural networks | |
| CN115205695B (en) | Method and system for determining planting strategy according to planting data | |
| Sheng et al. | Comparing agricultural total factor productivity between Australia, Canada, and the United States, 1961-2006 | |
| Brinkhoff et al. | Block-level macadamia yield forecasting using spatio-temporal datasets | |
| Gómez-Lagos et al. | A new method based on machine learning to forecast fruit yield using spectrometric data: analysis in a fruit supply chain context | |
| Chitsiko et al. | Review of current models and approaches used for maize crop yield forecasting in sub-Saharan Africa and their potential use in early warning systems | |
| Akbarian et al. | Plot level sugarcane yield estimation by machine learning on multispectral images: A case study of Bundaberg, Australia | |
| CN116703468B (en) | Agricultural product marketing method, system and storage medium based on big data | |
| Lin et al. | Predictive quality-aware control for scheduling of potato starch production | |
| KR102222004B1 (en) | Prediction system for traffic of fruits and predicting method using the same | |
| JP2022538597A (en) | sensor fusion | |
| CN116361562A (en) | Knowledge recommendation method and system for agricultural industry Internet | |
| US20220309595A1 (en) | System and Method for Managing and Operating an Agricultural-Origin-Product Manufacturing Supply Chain | |
| Brinkhoff et al. | The influence of nitrogen and variety on rice grain moisture content dry-down | |
| Lekakis et al. | Evaluation of a satellite drought indicator approach and its potential for agricultural drought prediction and crop loss assessment. The case of BEACON project | |
| Muir et al. | 'Sugar from Space': Using Satellite Imagery to Predict Cane Yield and Variability | |
| Clark et al. | Matching the model to the available data to predict wheat, barley, or canola yield: A review of recently published models and data | |
| Abewickrama | Analyzing and Predicting the Market Price of Fruits and Vegetables |
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 |