Intelligent agricultural production and sales prediction and adjustment decision system

Abstract

This invention discloses an intelligent agricultural product production and sales forecasting and adjustment decision-making system, comprising a data storage unit and a processing unit. The data storage unit stores environmental monitoring data and market demand data. The processing unit has a built-in algorithm that executes supply forecasting and demand forecasting modules, generating supply forecast curves and demand forecast curves covering specified time periods, respectively. The production and sales decision-making module compares the two curves over time, defines supply gap periods, calculates the sum of the differences between supply and demand during these periods as total demand, and allocates this total demand to the production season to generate a production and sales recommendation plan including suggested purchase quantities. In this way, by utilizing data processing and inventory adjustment mechanisms, the system solves the problem of mismatch between the agricultural product production and sales seasons, achieving a balance between production and sales.

Description

Intelligent Agricultural Product Production and Marketing Forecasting and Regulation Decision System INTELLIGENT AGRICULTURAL PRODUCTION AND SALES PREDICTION AND ADJUSTMENT DECISION SYSTEM Technical Field

[0001] This work relates to an agricultural product supply chain management technology, specifically an intelligent agricultural product production and sales forecasting and adjustment decision-making system that utilizes environmental and sales data for artificial intelligence analysis, and performs production and sales balance calculations and inventory adjustments accordingly. Prior Technology

[0002] Traditional agricultural product supply chains have long suffered from severe information asymmetry and time lags between production and sales. On the production side, farmers or suppliers often rely solely on past experience, last year's market prices, or fragmented information passed down through word of mouth to determine the types and scale of crops to plant, a traditional "production-driven" model that lacks data on actual market demand (distributors / consumers). Because of the information gap between production data (such as climate and yield) and sales data (such as demand from various distribution channels and seasonal fluctuations), the supply chain cannot make comprehensive supply and demand forecasts. This often results in overproduction during peak seasons leading to price collapses, or in situations where insufficient inventory planning leads to a lack of goods to sell during off-seasons, severely impacting the commercial value of agricultural products and the stability of the supply chain.

[0003] Existing agricultural management systems often focus on single-dimensional data collection. For example, only field environmental sensing systems monitor the growing environment, or only POS systems at the sales end compile historical transaction records. This creates data silos, lacking a comprehensive analytical platform that integrates "supply-related factors" and "market demand." Furthermore, for agricultural products with strong seasonality (such as mangoes and strawberries), conventional technologies lack effective algorithms to calculate the total demand gap during off-seasons. In other words, they cannot accurately convert the annual market demand into recommended purchasing and inventory plans for peak production periods. Therefore, purchasing and inventory adjustment decisions often rely on human experience and judgment, lacking scientific data support, making it difficult to achieve accurate production-sales balance. Summary of the Invention

[0004] In view of this, the main purpose of this invention is to provide an intelligent agricultural product production and sales forecasting and adjustment decision-making system. By integrating satellite monitoring, meteorological data and sales channel data, it uses algorithmic models to predict future supply and demand curves and introduces an inventory balancing calculation program to solve the problem of mismatch between the production season and the sales season of agricultural products.

[0005] To achieve the above objectives, this invention provides an intelligent agricultural product production and sales forecasting and adjustment decision-making system, comprising a data storage unit and a processing unit. The data storage unit stores a production-side database and a sales-side database. The production-side database stores environmental monitoring data; the sales-side database stores market demand data. The processing unit is electrically connected to the data storage unit. The processing unit has a built-in algorithm model configured to execute a supply forecasting module, a demand forecasting module, and a production and sales decision-making module. The supply forecasting module accesses the production-side database, analyzes the environmental monitoring data, and generates a supply forecast curve covering a specified time period through calculation. The demand forecasting module accesses the sales-side database, analyzes market demand data, and generates a demand forecast curve covering a specified time period through calculation. The production and sales decision-making module compares the demand forecast curve and the supply forecast curve over time and outputs a production and sales recommendation plan.

[0006] The data source attributes of environmental monitoring data in the production area database include satellite monitoring data, ground sensing data, field measurement data, production history information, publicly available government information, agricultural contract information, or weather forecast data.

[0007] Among them, the parameters of the environmental monitoring data in the production area database include crop type, planting area, crop growth, crop physiological index characteristics, environmental disasters or soil moisture content.

[0008] The database at the production site further includes historical data. The parameters of this historical data include historical yields, historical meteorological data, and historical peak production periods.

[0009] The supply forecasting module inputs environmental monitoring data and historical data into the algorithm model to generate an estimated crop production period range for the next 3 to 12 months, and generates estimated yields for multiple intervals within that range. Based on the estimated crop production period range and estimated yields, the supply forecasting module outputs a supply forecast curve.

[0010] The data source attributes of the market demand data in the sales database include historical sales data, business order data, publicly available government information, third-party map information platforms, or market research reports.

[0011] Among them, the market demand data parameters in the sales database include customer geographic location, customer business type, demanded agricultural products, demanded agricultural product quantity, or market analysis.

[0012] The demand forecasting module inputs market demand data into an algorithm model to generate an estimated sales period of 3 to 12 months, and an estimated total sales volume for one of several segments within that estimated sales period. Based on the estimated sales period and the estimated total sales volume, the demand forecasting module then generates a demand forecast curve.

[0013] The production and sales decision-making module executes an inventory balancing calculation procedure, which includes defining the supply gap period and the production season period. The supply gap period refers to the time segment where the supply forecast curve is lower than the demand forecast curve, and the production season period refers to the time segment where the supply forecast curve is higher than the demand forecast curve. The production and sales decision-making module calculates the sum of the differences between the demand forecast curve and the supply forecast curve within the supply gap period, defining this sum as total demand. The production and sales decision-making module allocates the total demand to the production season period to generate the recommended purchase quantity in the production and sales recommendation plan.

[0014] The data storage unit further stores an inventory database, which in turn stores existing inventory data. The production and sales decision-making module allocates total demand and existing inventory data to different production seasons to generate recommended purchase quantities in the production and sales recommendation plan.

[0015] In summary, by utilizing the data stored in the data storage unit and the built-in algorithm models, modules, and computational programs of the processing unit, this invention predicts future supply and demand curves and provides production and sales recommendations to address the information asymmetry problem between traditional agricultural production and sales. In particular, by accurately calculating the total market demand gap during off-seasons and translating it into purchasing decisions during peak production periods, it not only realizes a "demand-driven" business model but also effectively reduces inventory risk and waste, achieving an optimal balance between production and sales in the agricultural product supply chain. Simple Explanation of the Diagram

[0016]

[0017] Figure 1 is a schematic diagram of an intelligent agricultural product production and sales forecasting and regulation decision-making system in one specific embodiment of this invention.

[0018] Figure 2 is a schematic diagram of the supply gap period and production season period in one specific embodiment of this work.

[0019] Figure 3 is a schematic diagram of an intelligent agricultural product production and sales forecasting and regulation decision-making system in another specific embodiment of this invention. Implementation

[0020] Preferred embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be thorough and complete, and will fully convey the scope of the present disclosure to those skilled in the art.

[0021] Please refer to Figure 1. Figure 1 is a schematic diagram of the intelligent agricultural product production and sales forecasting and adjustment decision-making system in a specific embodiment of this invention. The intelligent agricultural product production and sales forecasting and adjustment decision-making system S of this invention includes a data storage unit 1 and a processing unit 2. The data storage unit 1 stores a production-end database 18 and a sales-end database 14. The production-end database 18 stores environmental monitoring data; the sales-end database 14 stores market demand data. The processing unit 2 is electrically connected to the data storage unit 1. The processing unit 2 has a built-in algorithm model, which is configured to execute a supply forecasting module 28, a demand forecasting module 24, and a production and sales decision-making module 26. The supply forecasting module 28 accesses the production-end database 18, analyzes the environmental monitoring data, and generates a supply forecast curve covering a specified time period through calculation. The demand forecasting module 24 accesses the sales-end database 14, analyzes the market demand data, and generates a demand forecast curve covering a specified time period through calculation. The production and sales decision-making module 26 compares the demand forecast curve and the supply forecast curve in a time series and outputs a production and sales recommendation plan 30.

[0022] Data storage unit 1 can be a physical server's hard drive, disk array, or cloud storage space. The production-side database 18 and sales-side database 14 can be an integrated cloud database system responsible for storing sales data from ERP and POS systems, as well as environmental data from satellites and the Internet of Things. Processing unit 2 can be a central processing unit, microprocessor, graphics processing unit, or a cloud server with artificial intelligence computing capabilities. Forecasting module 28, demand forecasting module 24, and production and sales decision-making module 26 are software code, applications, or algorithmic logic stored in memory and executed by processing unit 2.

[0023] The production and sales recommendation plan 30 is the final product output by the system, which can be presented to users through the display interface. The plan includes the recommended purchase quantity and the recommended inventory schedule, which is used by decision-makers to negotiate contracts with production areas or arrange processing processes based on the plan, so as to fill the supply gap during the off-season.

[0024] Production and Sales Recommendation Plan 30 can be used for procurement decisions and contract negotiations, inventory and processing scheduling, and marketing and fundraising presentations. Procurement personnel can use Production and Sales Recommendation Plan 30 to discuss contract details with production areas and the future supply volume; factory personnel can use Production and Sales Recommendation Plan 30 to arrange the future processing of agricultural products after they enter the factory; sales personnel can use Production and Sales Recommendation Plan 30 to present future production and inventory levels to restaurants and distributors to demonstrate a stable and secure supply throughout the year.

[0025] The purpose of the Production and Marketing Recommendation Plan 30 is to transform agricultural products with biodiversity and non-standardized characteristics into standardized semi-finished products (such as frozen juice and fruit chunks) with uniform specifications and easy storage and transportation through planned processing schedules. This mechanism is similar to the pre-deployment of logistics centers, ensuring that the order demand of the catering channel can still be met with standardized product specifications during the off-season.

[0026] Among them, the data source attributes of the environmental monitoring data in the production area database 18 include satellite monitoring data, ground sensing data, field measurement data, production history information, government-published information, agricultural contract information, or weather forecast data.

[0027] Satellite monitoring data is acquired through satellite remote sensing technology. The image sources for this data include multispectral, hyperspectral, synthetic aperture radar (SAR), LiDAR, and thermal infrared images. Through backend algorithm analysis of these images, physiological indices of crops that are difficult to discern with the naked eye can be obtained.

[0028] For example, by utilizing visible and near-infrared light bands to visualize the entire planted area, chlorophyll content and vegetation indices (such as NDVI and EVI) can be calculated to determine crop growth density and health status, thus obtaining information on crop growth and health. Spectral characteristics can be analyzed to determine crop flowering and color-changing periods, allowing for accurate estimation of yield. Thermal infrared or microwave radar can be used to analyze soil moisture content, surface temperature, and crop water stress indicators (such as NDWI). Furthermore, by leveraging the cloud penetration characteristics of radar waves, environmental disasters such as crop lodging area, flooding extent, and pest and disease conditions can be analyzed to revise estimated yields.

[0029] Ground sensing data refers to microclimate data transmitted back by IoT monitoring devices installed in the field, including soil temperature and humidity, conductivity, or sunshine.

[0030] Field measurement data refers to observational data recorded by personnel during actual field inspections (such as the actual number of fruits borne and the incidence of pests and diseases). This data can be used to compare and correct with satellite analysis results to improve model accuracy.

[0031] Production history information refers to the field operation process recorded by farmers or producers, including crop type, fertilization records, pesticide records, or harvest batch records.

[0032] Government-disclosed information refers to macroeconomic data released by government agricultural authorities, such as crop types in various regions, wholesale market transaction volume and prices, and statistics on crop planting area.

[0033] Agricultural contract information refers to the contents of the contract signed between farmers and buyers, including the type of crop to be delivered, the scheduled delivery date, and the guaranteed purchase quantity.

[0034] Meteorological forecast data refers to forecast data from meteorological units, including short-term (within 10 days) weather forecasts and medium- to long-term (10 to 180 days) climate trend forecasts, such as the impact of El Niño / El Niño phenomenon on the birth season.

[0035] Therefore, the parameters of the environmental monitoring data in the production area database 18 include crop type, planting area, crop growth, crop physiological index characteristics, environmental disasters, or soil moisture content.

[0036] The production area database 18 further includes historical data. The parameters of this historical data include historical yield, historical meteorological data, and historical peak production periods. Historical yield refers to the total annual output in tons or yield per unit area of ​​a specific crop over the past few years. This data is used to establish a baseline for the production capacity of the production area. Historical meteorological data refers to key meteorological factors affecting the growth of the crop over the past few years, including cumulative rainfall, cumulative sunshine hours, accumulated temperature, and historical disaster records (such as typhoons and cold waves). Historical peak production periods refer to the time periods over the past few years during which the crop's yield reached its peak.

[0037] Please refer to Figures 1 and 2. Figure 2 is a schematic diagram of the supply gap period and production season period in one specific embodiment of this invention. The supply forecasting module 28 inputs environmental monitoring data and historical data into the algorithm model to generate the estimated crop production period range for the next 3 to 12 months, and generates the estimated yield for multiple intervals within the estimated crop production period range. The supply forecasting module 28 then outputs the supply forecasting curve C8 based on the estimated crop production period range and the estimated yield.

[0038] Specifically, the algorithm model can employ a combination of time series analysis and multivariate regression models. This model uses historical yield data as a basis and incorporates environmental monitoring data as a dynamic weighting factor. For example, the module analyzes meteorological forecast data and satellite spectral data. Using crop phenology models, it calculates the cumulative temperature of the crop and predicts the yield period.

[0039] Furthermore, the total yield for the production period can be estimated using the following formula: Estimated total yield = Planting area × Historical yield per unit area × Physiological index correction coefficient. The physiological index correction coefficient is affected by external factors such as soil moisture content and pests and diseases.

[0040] Finally, the calculated total output is allocated to multiple intervals within the production period according to normal distribution or historical output patterns, and a supply forecast curve C8 is plotted. The Y-axis of the supply forecast curve C8 represents the estimated output, and the X-axis represents time, showing a trend of output gradually increasing from low to high, reaching a production peak, and then decreasing.

[0041] When the supply forecasting module 28 receives real-time environmental monitoring data for the current year, it can compare it with historical data. For example, if the climate pattern for the current year is similar to a historical El Niño year, the system will adjust the supply forecast curve for the next 3 to 12 months based on the production records of that historical year, thereby correcting the errors in satellite estimation and improving the accuracy of the forecast.

[0042] The supply forecasting module 28 can use the aforementioned historical data as a training dataset for AI learning. Historical meteorological data serves as input features, while historical yields and historical peak production periods are used as target labels to train the algorithm to learn a model of the correlation between climate and output.

[0043] Among them, the data source attributes of the market demand data in the sales database 14 include historical sales data, business order data, publicly available government information, third-party map information platforms, or market research reports.

[0044] Historical sales data and business order data refer to records from the company's internal ERP or POS system, including actual shipments for each past month, customer order frequency, and undelivered pre-orders.

[0045] Third-party map information platforms refer to geographic information services such as Google Maps that connect via APIs. The system can then analyze the geographic distribution density of customers, the attributes of their business districts, and the competitive landscape of restaurants in that area.

[0046] Market research reports and publicly available government information include food and beverage industry trend reports, national tourism data, or statistical data on the correlation between temperature and beverage sales.

[0047] Among them, the market demand data parameters in the sales database 14 include customer geographic location, customer business type, demanded agricultural products, demanded agricultural product quantity, or market analysis.

[0048] The customer business type is a system that categorizes customers by label, such as bubble tea chains, brunch shops, all-you-can-eat restaurants, or high-end dessert shops. Different business types have different requirements for the quality and seasonality of fruit ingredients. For example, bubble tea shops may sell mango smoothies all year round.

[0049] The demand for agricultural products refers to the fact that this system not only records the sales volume of end products, but also, based on the bill of materials, reverse-calculates the demand for raw materials from the end products.

[0050] Customer geography and market analysis are used to analyze taste preferences in specific counties, cities, or regions during specific seasons. For example, demand for lemon-based drinks is higher in the south than in the north during the summer.

[0051] Specifically, the demand forecasting module 24 inputs market demand data into the algorithm model to generate an estimated sales period range of 3 to 12 months for the next period, and generates an estimated total sales volume for one of several segments within that estimated sales period range. Based on the estimated sales period range and the estimated total sales volume, the demand forecasting module 24 then generates a demand forecast curve C4.

[0052] Algorithm models, such as time series analysis (ARIMA or LSTM), analyze pre-orders, historical sales data, and seasonality indices to predict the estimated sales volume of beverages to end consumers across various channels over the next 3 to 12 months. The demand forecasting module 24 then converts the estimated sales volume into the estimated total sales volume of a specific agricultural product based on the recipe proportions of each customer's business format. The final output demand forecast curve C4 has an X-axis representing the time axis (covering both off-season and production season) and a Y-axis representing the total demand for the agricultural product. The demand forecast curve C4 typically exhibits stable demand throughout the year.

[0053] In the demand forecasting module 24, the algorithm assigns high weight to customers with regular subscriptions or long-term contracts as the base demand. Furthermore, the system calculates safety stock levels based on each customer's historical consumption rate and automatically generates proactive replenishment instructions in the production and sales recommendation plan 30 when customer inventory falls below the threshold.

[0054] The production and sales decision-making module 26 executes an inventory balancing calculation procedure, which includes defining the supply gap period and the production season period. The supply gap period refers to the time segment where the value of the supply forecast curve C8 is lower than the value of the demand forecast curve C4, and the production season period refers to the time segment where the value of the supply forecast curve C8 is higher than the value of the demand forecast curve C4. The production and sales decision-making module 26 calculates the sum of the differences between the demand forecast curve C4 and the supply forecast curve C8 within the supply gap period, and defines the sum of the differences as the total demand. The production and sales decision-making module 26 allocates the total demand to the production season period to generate the suggested purchase quantity in the production and sales suggestion plan 30.

[0055] A supply gap period indicates market demand but a lack of fresh fruit production in the producing areas; the peak production season represents abundant production capacity in the producing areas, making it the optimal time for strategic procurement. For identified supply gap periods, the production and sales decision-making module 26 performs a cumulative summation calculation, essentially the integration concept from calculus. The module calculates the positive difference between "demand and supply" at each point in time (e.g., each month) within that period. All differences are summed to calculate the total difference for that gap period, defined as "total demand." This value represents the total inventory that must be prepared in advance to meet all future non-peak season orders. The production and sales decision-making module 26 then allocates the calculated total demand backwards to the peak season, using the following formula to estimate the recommended procurement quantity: Recommended Procurement Quantity = Current Monthly Demand + (Total Demand ÷ Number of Months in the Peak Season)

[0056] In this way, the system's output plan will instruct purchasing personnel to make over-purchases during peak production periods and simultaneously trigger the factory's frozen processing schedule to convert excess fresh fruit into frozen inventory for use during subsequent shortage periods.

[0057] Furthermore, production history information and satellite monitoring data stored in the production site database 18 can be integrated and encoded into a traceability tag by the processing unit 2 and attached to the final product. This function is not only used for quality control, but also serves as an information bridge connecting environmental data at the production end (such as carbon-reduced planting and environmentally friendly farming methods) with the sales end, thereby enhancing the added value of the product.

[0058] Please refer to Figure 3. Figure 3 is a schematic diagram of an intelligent agricultural product production and sales forecasting and adjustment decision system in another specific embodiment of this invention. The data storage unit 1 further stores an inventory database 19, which in turn stores existing inventory data. The production and sales decision module 26 allocates the total demand and existing inventory data to different production season periods to generate the recommended purchase quantity in the production and sales recommendation plan 30.

[0059] The inventory database 19 does not record a single value, but rather manages agricultural products by category according to different types. Existing inventory data includes information such as fresh fruit inventory, frozen inventory, and storage location information. Fresh fruit inventory refers to inventory stored at room temperature or refrigerated, which needs to be sold, processed, or frozen within a short period. Frozen inventory refers to semi-finished product inventory that has undergone peeling, dicing, quick-freezing (IQF), or processing into fruit puree. This type of inventory has a long shelf life (e.g., 1-2 years) and is the main tool for this system to adjust for "supply gap periods." Storage location information records the storage location and expiration date of each batch of inventory.

[0060] The allocation calculation performed by the production and sales decision-making module 26, in this embodiment, adopts net demand calculation, and the calculation formula is as follows: Suggested purchase quantity = Total demand - Effective existing inventory + Safety stock level

[0061] The production and sales decision module 26 first adds up the total demand during the supply gap period and subtracts the current available inventory in the warehouse. If the value after subtraction is positive, it means that the current reservoir level is insufficient, and the system allocates the difference to the upcoming production season, requiring the purchasing department to purchase this difference in addition during the peak production period.

[0062] The intelligent agricultural product production and sales forecasting and adjustment decision-making system S generates a production and sales recommendation plan 30 containing two levels of instructions: a purchasing instruction instructing purchasing personnel on the purchase volume during the production season, which is usually much higher than the actual sales volume of the month; and a processing scheduling instruction that automatically plans the processing plant's capacity based on the recommended purchase volume. For example, the recommendation plan shows that "from June 1st to June 15th, three frozen diced production lines need to be started to convert 80% of the daily fresh fruit into frozen inventory" to ensure that sufficient volume is accumulated in the inventory database to cope with the supply gap in the following nine months.

[0063] The data storage unit 1 and algorithm model of this system can be further constructed into an agricultural data service platform (Data-as-a-Service). Through the application interface, the predicted production and demand trends are provided to third parties (such as financial institutions for farmer loan assessments and logistics operators for capacity planning), serving not only for internal production and sales regulation but also as the digital infrastructure of the agricultural supply chain.

[0064] In summary, by utilizing the data stored in the data storage unit and the built-in algorithm models, modules, and computational programs of the processing unit, this invention predicts future supply and demand curves and provides production and sales recommendations to address the information asymmetry problem between traditional agricultural production and sales. In particular, by accurately calculating the total market demand gap during off-seasons and translating it into purchasing decisions during peak production periods, it not only realizes a "demand-driven" business model but also effectively reduces inventory risk and waste, achieving an optimal balance between production and sales in the agricultural product supply chain.

[0065] It should be noted that the relational terms used in this document are used only to distinguish an entity or operation from another entity or operation, without requiring or implying any actual relationship or order between these entities or operations. Furthermore, the words “including,” “contains,” and other similar forms are intended to be semantically equivalent and are open-ended; one or more items following any of these words do not imply an exhaustive list of such items or that the list is limited to only one or more items listed.

[0066] As used herein, unless otherwise expressly stated, the term "or" covers all possible combinations unless impractical. For example, if a component is stated to contain either A or B, then unless otherwise expressly stated or impractical, the component may contain A, or B, or A and B. As a second example, if a component is stated to contain A, B, or C, then unless otherwise expressly stated or impractical, the component may contain A, or B, or C, or A and B, or A and C, or B and C, or A and B and C.

[0067] In the foregoing description, numerous specific details have been described with reference to embodiments, which may vary depending on the implementation. Certain modifications and alterations may be made to the described embodiments. Other embodiments will be apparent to those skilled in the art in light of the description and practice of this invention disclosed herein. The description and examples are intended to be considered exemplary only, and the true scope and spirit of this invention are indicated by the following claims.

[0068] Exemplary embodiments have been disclosed in the accompanying drawings and description. However, many variations and modifications can be made to these embodiments. Therefore, although specific terminology has been used, it is used in a general and descriptive sense only and not for limiting purposes.

[0069] 1: Data storage unit

[0070] 14: Sales Database

[0071] 18: Origin Database

[0072] 19: Inventory Database

[0073] 2: Processing Unit

[0074] 24: Demand Forecasting Module

[0075] 26: Production and Sales Decision Module

[0076] 28: Supply Forecasting Module

[0077] 30: Production and Sales Recommendation Plan

[0078] S: Intelligent Agricultural Product Production and Marketing Forecasting and Adjustment Decision System

[0079] C4: Demand Forecast Curve

[0080] C8: Supply Forecast Curve

Claims

1. A smart agricultural product production and sales forecasting and adjustment decision-making system, comprising: a data storage unit storing a production-end database and a sales-end database, wherein: The production-side database stores environmental monitoring data; the sales-side database stores market demand data; and a processing unit electrically connected to the data storage unit, the processing unit having a built-in algorithm model and configured to execute: a supply forecasting module, which accesses the production-side database, analyzes the environmental monitoring data, and generates a supply forecast curve covering a specified time period through calculation; a demand forecasting module, which accesses the sales-side database, analyzes the market demand data, and generates a demand forecast curve covering a specified time period through calculation; and a production and sales decision-making module, which performs a time-series comparison of the demand forecast curve and the supply forecast curve, and outputs a production and sales recommendation plan.

2. The intelligent agricultural product production and marketing forecasting and regulation decision-making system as described in claim 1, wherein the data source attributes of the environmental monitoring data in the production area database include one or a combination of satellite monitoring data, ground sensing data, field measurement data, production history information, publicly available government information, agricultural contract information, or meteorological forecast data.

3. The intelligent agricultural product production and marketing forecasting and regulation decision-making system as described in claim 1, wherein the parameter indicators of the environmental monitoring data in the production area database include one or a combination of crop type, planting area, crop growth, crop physiological index characteristics, environmental disasters or soil moisture content.

4. The intelligent agricultural product production and marketing forecasting and regulation decision-making system as described in claim 1, wherein the production area database further includes historical data, the parameter indicators of which include one or a combination of historical yield, historical meteorological data or historical peak production period.

5. The intelligent agricultural product production and sales forecasting and adjustment decision system as described in claim 4, wherein the supply forecasting module inputs the environmental monitoring data and the historical data into the algorithm model to generate an estimated crop production period range of 3 to 18 months in the future, and generates an estimated yield of one of multiple intervals within the estimated crop production period range, and generates the supply forecasting curve based on the estimated crop production period range and the estimated yield.

6. The intelligent agricultural product production and sales forecasting and adjustment decision-making system as described in claim 1, wherein the data source attributes of the market demand data in the sales database include one or a combination of historical sales data, business order data, publicly available government information, third-party map information platforms, or market research reports.

7. The intelligent agricultural product production and sales forecasting and adjustment decision system as described in claim 1, wherein the parameter indicators of the market demand data in the sales database include one or a combination of customer geographical location, customer business type, demanded agricultural product items, demanded agricultural product quantities, or market analysis.

8. The intelligent agricultural product production and sales forecasting and adjustment decision system as described in claim 1, wherein the demand forecasting module inputs the market demand data into the algorithm model to generate an estimated sales period range of 3 to 18 months in the future, and generates an estimated total sales volume of one of multiple intervals within the estimated sales period range, and generates the demand forecasting curve based on the estimated sales period range and the estimated total sales volume.

9. The intelligent agricultural product production and sales forecasting and adjustment decision system as described in claim 1, wherein the production and sales decision module executes an inventory balancing calculation procedure, the inventory balancing calculation procedure comprising: defining a supply gap period and a production season period, the supply gap period referring to the time segment in which the value of the supply forecast curve is lower than the value of the demand forecast curve, and the production season period referring to the time segment in which the value of the supply forecast curve is higher than the value of the demand forecast curve; calculating the sum of the differences between the demand forecast curve and the supply forecast curve during the supply gap period, defining the sum of the differences as a total demand; and allocating the total demand to the production season period to generate a suggested purchase quantity in the production and sales suggestion plan.

10. The intelligent agricultural product production and sales forecasting and adjustment decision system as described in claim 9, wherein the data storage unit further stores an inventory database, and the inventory database further stores existing inventory data; the production and sales decision module allocates the total demand and the existing inventory data to the production season period to generate the recommended purchase quantity in the production and sales recommendation plan.

Images