Smart agriculture data processing method, system, terminal and medium based on Internet of Things

Abstract

The present invention discloses a smart agricultural data processing method, system, terminal and medium based on the Internet of Things, and relates to the technical field of agricultural data processing. The key points of the technical solution are: obtaining the real-time variety set planted in the current cycle, and constructing an associated variety set with production and marketing association based on the real-time variety set; determining the picking time and real-time yield information according to real-time growth information, and determining the real-time profit coefficient in combination with the standard selling price; constructing a coordinated balance model according to the real-time variety set and the associated variety set; inputting the real-time profit coefficient and real-time yield information into the pre-constructed coordinated balance model, and obtaining a production and marketing strategy composed of the picking and sales strategy of the real-time variety set and the pre-planting strategy of the associated variety set. The present invention can ensure market stability and stable income for producers.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural data processing, and more specifically, to a method, system, terminal and medium for processing smart agricultural data based on the Internet of Things. Background Art

[0002] The existing Internet agricultural systems mainly include production and marketing sharing, yield forecasting and analysis systems. On the one hand, producers can collect plant variety growth information based on the Internet of Things technology and analyze future yields in combination with relevant growth forecasting models, which can provide certain reference data for market regulation; on the other hand, producers and sellers can sign orders through a shared trading platform, which solves the sales problem of producers to a certain extent. However, the output and sales of agricultural products are mainly affected by market supply and demand. The high returns of a product will cause some people to follow suit, resulting in a large amount of output within a certain period of time; with the influence of time, there will be a large accumulation of output. In this process, the economic benefits of producers are not controlled and there is a high risk. It can be seen that there is a lack of benign regulation in the existing agricultural field, resulting in large market fluctuations. Summary of the invention

[0003] In order to solve the deficiencies in the prior art, the purpose of the present invention is to provide a smart agricultural data processing method, system, terminal and medium based on the Internet of Things.

[0004] In the first aspect, a smart agricultural data processing method based on the Internet of Things is provided, comprising the following steps:

[0005] Obtain the real-time variety set that has been planted in the current cycle, and build a related variety set with production and marketing association based on the real-time variety set;

[0006] Obtaining real-time growth information of each variety in the real-time variety set, and determining the picking time and real-time yield information based on the real-time growth information, and determining the real-time profit coefficient based on the picking time, real-time yield information and standard selling price;

[0007] Construct a coordinated balance model based on the real-time variety set and the associated variety set;

[0008] The real-time profit coefficient and real-time yield information are input into the pre-built coordination equilibrium model to obtain the production and marketing strategy consisting of the picking and selling strategy of the real-time variety set and the pre-planting strategy of the associated variety set.

[0009] Furthermore, the construction process of the associated variety set is specifically as follows:

[0010] Determine the associated full cycle based on the latest collection cycle of the real-time varieties in the real-time variety set from the current cycle;

[0011] The varieties that can be planted to replace the real-time varieties within the entire associated cycle are taken as the associated varieties of the corresponding real-time varieties to obtain the associated variety set.

[0012] Furthermore, the process of determining the picking time and yield information is specifically as follows:

[0013] Predict and analyze product weight curves over time based on real-time growth information;

[0014] Determine the loss curve of the corresponding real-time variety in the process of growth, production and marketing that changes over time according to different picking times;

[0015] The product weight curve and the loss curve are fused to obtain the picking yield curve that represents the correlation between picking time and yield information.

[0016] Furthermore, the calculation formula of the real-time profit coefficient is specifically as follows:

[0017]

[0018] Where Y(i) represents the real-time profit coefficient of the i-th real-time variety; G0(i) represents the standard selling price of the i-th real-time variety; ΔT0(i) represents the standard planting time of the i-th real-time variety; ΔT s (i) represents the actual planting time of the i-th real-time variety; α represents the selling price impact coefficient, which is negatively correlated with the actual planting time.

[0019] Furthermore, the expression of the coordinated balance model is specifically:

[0020]

[0021] Among them, C s (i) represents the real-time production information of the i-th real-time variety; N represents the number of real-time varieties; X s (i) represents the demand and output information of the i-th real-time variety; k(i) represents the number of related varieties of the i-th real-time variety; B g (j) represents the standard yield information of the jth associated variety; C g (j) represents the estimated yield information of the j-th associated variety; Y(i) represents the real-time profit coefficient of the ith real-time variety; Y(j) represents the estimated profit coefficient of the j-th associated variety; Z0 represents the lower limit threshold of the adjustment coefficient of the real-time variety; Z3 represents the upper limit threshold of the adjustment coefficient of the real-time variety; Z1 represents the lower limit threshold of the adjustment coefficient of the associated variety; Z2 represents the upper limit threshold of the adjustment coefficient of the associated variety.

[0022] Furthermore, the lower limit threshold of the adjustment coefficient of the real-time variety and the lower limit threshold of the adjustment coefficient of the associated variety are both less than 1, and the lower limit threshold of the adjustment coefficient of the real-time variety is less than the lower limit threshold of the adjustment coefficient of the associated variety;

[0023] The upper limit threshold of the adjustment coefficient of the associated variety and the upper limit threshold of the adjustment coefficient of the real-time variety are both greater than 1, and the upper limit threshold of the adjustment coefficient of the associated variety is less than the upper limit threshold of the adjustment coefficient of the real-time variety.

[0024] Furthermore, the estimated yield information and estimated profit coefficient of the related varieties are obtained through training based on historical data.

[0025] Secondly, a smart agricultural data processing system based on the Internet of Things is provided, including:

[0026] The association building module is used to obtain the real-time variety set planted in the current cycle, and to build an associated variety set with production and marketing association based on the real-time variety set;

[0027] The profit analysis module is used to obtain the real-time growth information of each variety in the real-time variety set, and determine the picking time and real-time yield information based on the real-time growth information, and determine the real-time profit coefficient based on the picking time, real-time yield information and standard selling price;

[0028] A model building module, used for building a coordinated balance model based on a real-time variety set and a related variety set;

[0029] The strategy analysis module is used to input the real-time profit coefficient and real-time yield information into the pre-built coordination balance model to obtain the production and marketing strategy composed of the picking and sales strategy of the real-time variety set and the pre-planting strategy of the associated variety set.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. The method for processing smart agricultural data based on the Internet of Things proposed in the present invention, when there is an imbalance between supply and demand of agricultural varieties, establishes a coordinated balance model based on the real-time variety set planted in the current cycle and the associated variety set with production and marketing associations, and regulates the output of the associated varieties in the future period, so that various varieties in the entire agricultural range can develop in a balanced and coordinated manner, and the fluctuation range of the market economy is small, which ensures the stability of the market and the stability of the producer's income;

[0032] 2. When the present invention establishes a coordinated balance model based on the real-time variety set planted in the current cycle and the associated variety set with production and marketing associations, it not only takes into account the maximization of the producer's economic benefits, but also considers limiting the regulation of agricultural variety yields within a relatively stable range, avoiding excessive interference in variety yields and causing chain reactions, and making the production and marketing strategy more reasonable;

[0033] 3. The present invention takes into account the analysis process of the real-time profit coefficient, namely, the time cost and the loss affected by time, and also takes into account the impact of product output time on the selling price, so as to make the analysis of the producer's economic benefits more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In the attached picture:

[0035] Figure 1 is a flow chart in an embodiment of the present invention;

[0036] Figure 2 It is a system block diagram in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] Example 1: A smart agricultural data processing method based on the Internet of Things, such as Figure 1 As shown, the following steps are included:

[0038] S1: Obtain the real-time variety set planted in the current cycle, and build a related variety set with production and marketing association based on the real-time variety set;

[0039] S2: obtaining real-time growth information of each variety in the real-time variety set, and determining the picking time and real-time yield information based on the real-time growth information, and determining the real-time profit coefficient based on the picking time, real-time yield information and standard selling price;

[0040] S3: Construct a coordinated equilibrium model based on the real-time variety set and the associated variety set;

[0041] S4: Input the real-time profit coefficient and real-time yield information into the pre-built coordination equilibrium model to obtain a production and marketing strategy consisting of a picking and selling strategy for a real-time variety set and a pre-planting strategy for an associated variety set.

[0042] Specifically, the associated full cycle is determined based on the latest collection cycle of the real-time varieties in the real-time variety set from the current cycle; the varieties that can be planted to replace the real-time varieties within the associated full cycle are used as associated varieties of the corresponding real-time varieties to obtain an associated variety set.

[0043] Specifically, a product weight curve is predicted and analyzed based on real-time growth information to predict and analyze the changes in variety weight over time. A loss curve of the corresponding real-time variety while maintaining growth and production and marketing processes over time is determined based on different picking times. The product weight curve and the loss curve are merged to obtain a picking yield curve that represents the association between picking time and yield information.

[0044] The calculation formula of real-time profit coefficient is as follows:

[0045]

[0046] Where Y(i) represents the real-time profit coefficient of the i-th real-time variety; G0(i) represents the standard selling price of the i-th real-time variety; ΔT0(i) represents the standard planting time of the i-th real-time variety; ΔT s (i) represents the actual planting time of the i-th real-time variety; α represents the selling price impact coefficient, which is negatively correlated with the actual planting time.

[0047] The expression of the coordinated equilibrium model is as follows:

[0048]

[0049] Among them, C s (i) represents the real-time production information of the i-th real-time variety; N represents the number of real-time varieties; X s (i) represents the demand and output information of the i-th real-time variety; k(i) represents the number of related varieties of the i-th real-time variety; B g (j) represents the standard yield information of the jth associated variety; C g (j) represents the estimated yield information of the j-th associated variety; Y(i) represents the real-time profit coefficient of the ith real-time variety; Y(j) represents the estimated profit coefficient of the j-th associated variety; Z0 represents the lower limit threshold of the adjustment coefficient of the real-time variety; Z3 represents the upper limit threshold of the adjustment coefficient of the real-time variety; Z1 represents the lower limit threshold of the adjustment coefficient of the associated variety; Z2 represents the upper limit threshold of the adjustment coefficient of the associated variety.

[0050] It should be noted that the estimated yield information and estimated profit coefficients of related varieties are obtained through training based on historical data.

[0051] Embodiment 2: A smart agricultural data processing system based on the Internet of Things, the system is used to implement the method described in Embodiment 1, such as Figure 2 As shown, it includes an association building module, a benefit analysis module, a model building module and a strategy analysis module.

[0052] Among them, the association construction module is used to obtain the real-time variety set planted in the current cycle, and to construct an associated variety set with production and marketing association based on the real-time variety set; the profit analysis module is used to obtain the real-time growth information of each variety in the real-time variety set, and determine the picking time and real-time yield information based on the real-time growth information, and determine the real-time profit coefficient based on the picking time, real-time yield information and standard selling price; the model construction module is used to construct a coordinated balance model based on the real-time variety set and the associated variety set; the strategy analysis module is used to input the real-time profit coefficient and real-time yield information into the pre-constructed coordinated balance model to obtain the production and marketing strategy composed of the picking and sales strategy of the real-time variety set and the pre-planting strategy of the associated variety set.

[0053] The above specific implementation methods further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific implementation methods of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The method for processing smart agricultural data based on the Internet of Things is characterized by: The following steps are involved: Obtain the real-time variety set that has been planted in the current cycle, and build a related variety set with production and marketing association based on the real-time variety set; Obtaining real-time growth information of each variety in the real-time variety set, and determining the picking time and real-time yield information based on the real-time growth information, and determining the real-time profit coefficient based on the picking time, real-time yield information and standard selling price; Construct a coordinated balance model based on the real-time variety set and the associated variety set; Input the real-time profit coefficient and real-time yield information into the pre-built coordination balance model to obtain the production and marketing strategy consisting of the picking and selling strategy of the real-time variety set and the pre-planting strategy of the associated variety set; The calculation formula of the real-time profit coefficient is specifically: Where Y(i) represents the real-time profit coefficient of the i-th real-time variety; G0(i) represents the standard selling price of the i-th real-time variety; ΔT0(i) represents the standard planting time of the i-th real-time variety; ΔT s (i) represents the actual planting time of the i-th real-time variety; α represents the selling price impact coefficient, which is negatively correlated with the actual planting time.

2. The method for processing smart agricultural data based on the Internet of Things according to claim 1 is characterized in that: The construction process of the associated variety set is specifically as follows: Determine the associated full cycle based on the latest collection cycle of the real-time varieties in the real-time variety set from the current cycle; The varieties that can be planted to replace the real-time varieties within the entire associated cycle are taken as the associated varieties of the corresponding real-time varieties to obtain the associated variety set.

3. The method for processing smart agricultural data based on the Internet of Things according to claim 1, characterized in that: The specific process of determining the picking time and yield information is as follows: Predict and analyze product weight curves over time based on real-time growth information; Determine the loss curve of the corresponding real-time variety in the process of growth, production and marketing that changes over time according to different picking times; The product weight curve and the loss curve are fused to obtain the picking yield curve that represents the correlation between picking time and yield information.

4. The method for processing smart agricultural data based on the Internet of Things according to claim 1, characterized in that: The expression of the coordinated equilibrium model is specifically: Among them, C s (i) represents the real-time production information of the i-th real-time variety; N represents the number of real-time varieties; X s (i) represents the demand and output information of the i-th real-time variety; k(i) represents the number of related varieties of the i-th real-time variety; B g (j) represents the standard yield information of the jth associated variety; C g (j) represents the estimated yield information of the j-th associated variety; Y(i) represents the real-time profit coefficient of the ith real-time variety; Y(j) represents the estimated profit coefficient of the j-th associated variety; Z0 represents the lower limit threshold of the adjustment coefficient of the real-time variety; Z3 represents the upper limit threshold of the adjustment coefficient of the real-time variety; Z1 represents the lower limit threshold of the adjustment coefficient of the associated variety; Z2 represents the upper limit threshold of the adjustment coefficient of the associated variety.

5. The method for processing smart agricultural data based on the Internet of Things according to claim 4 is characterized in that: The lower limit threshold of the adjustment coefficient of the real-time variety and the lower limit threshold of the adjustment coefficient of the associated variety are both less than 1, and the lower limit threshold of the adjustment coefficient of the real-time variety is less than the lower limit threshold of the adjustment coefficient of the associated variety; The upper limit threshold of the adjustment coefficient of the associated variety and the upper limit threshold of the adjustment coefficient of the real-time variety are both greater than 1, and the upper limit threshold of the adjustment coefficient of the associated variety is less than the upper limit threshold of the adjustment coefficient of the real-time variety.

6. The method for processing smart agricultural data based on the Internet of Things according to claim 4 is characterized in that: The estimated yield information and estimated profit coefficient of the related varieties are obtained through training based on historical data.

7. The smart agricultural data processing system based on the Internet of Things is characterized by: include: The association building module is used to obtain the real-time variety set planted in the current cycle, and to build an associated variety set with production and marketing association based on the real-time variety set; The profit analysis module is used to obtain the real-time growth information of each variety in the real-time variety set, and determine the picking time and real-time yield information based on the real-time growth information, and determine the real-time profit coefficient based on the picking time, real-time yield information and standard selling price; A model building module, used for building a coordinated balance model based on a real-time variety set and a related variety set; The strategy analysis module is used to input the real-time profit coefficient and the real-time yield information into the pre-built coordination balance model to obtain the production and marketing strategy consisting of the picking and sales strategy of the real-time variety set and the pre-planting strategy of the associated variety set; The calculation formula of the real-time profit coefficient is specifically: Where Y(i) represents the real-time profit coefficient of the i-th real-time variety; G0(i) represents the standard selling price of the i-th real-time variety; ΔT0(i) represents the standard planting time of the i-th real-time variety; ΔT s (i) represents the actual planting time of the i-th real-time variety; α represents the selling price impact coefficient, which is negatively correlated with the actual planting time.

8. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the smart agriculture data processing method based on the Internet of Things as described in any one of claims 1-6 is implemented.

9. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the smart agriculture data processing method based on the Internet of Things as described in any one of claims 1-6.

Images