An Information Integration Method for Agricultural Product Supply Chains Based on Big Data Analysis

Abstract

The present invention relates to the technical field of information integration in the agricultural product supply chain. The present invention relates to a method for integrating information in the agricultural product supply chain based on big data analysis. It includes the following steps: S1. Establish a supply chain port, and collect a list of agricultural product regions and a list of sales regions; S2. Extract production-related data of the agricultural product regions, sort the production-related data according to the collection time node, and at the same time set the true weight for the production-related data according to the collection method, and establish a corresponding regional simulation model for each agricultural product region; By establishing a supply chain port, collecting a list of agricultural product regions and a list of sales regions, the present invention integrates and manages the information of agricultural product suppliers and sales managers, realizes the digitization of the information of supply chain members, facilitates different members to access and manage information, and improves the information transparency and management efficiency of the supply chain.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural product supply chain information integration, and specifically, to a method for integrating agricultural product supply chain information based on big data analysis. Background Art

[0002] Currently, the information transmission among supply chain members such as agricultural product suppliers and sales managers mostly relies on manual communication and paper document records. It is difficult to share and integrate information in real time among various links. The data collection methods in the production link are relatively single, and cannot comprehensively and accurately reflect the actual production status of agricultural products. The market demand prediction in the sales link is mostly based on experience, lacking the effective utilization of emerging information sources such as network big data.

[0003] In such a scenario, the scattered information leads to difficulties in coordinating various links of the supply chain, making it difficult to achieve precise production and sales planning, and unable to effectively guarantee the stable supply of agricultural products. The incomplete and inaccurate production data collection makes the production decision lack a reliable basis, easily causing waste of production resources or insufficient supply. The market demand prediction based on experience is difficult to cope with the complex and changeable market environment, affecting the sales effect and economic benefits. Therefore, a method for integrating agricultural product supply chain information based on big data analysis is proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for integrating agricultural product supply chain information based on big data analysis to solve the problems raised in the above background art.

[0005] To achieve the above purpose, a method for integrating agricultural product supply chain information based on big data analysis is provided, including the following steps:

[0006] S1. Establish a supply chain port, and collect the list of agricultural product regions and the list of sales regions;

[0007] S2. Extract the production-related data of the agricultural product regions, sort the production-related data according to the collection time nodes, and set the real weights for the production-related data according to the collection methods, and establish a corresponding regional simulation model for each agricultural product region;

[0008] S3. Set a difference threshold, and at the same time, perform real analysis on the production-related data after outputting the simulation results in combination with the regional simulation model and the difference threshold, and then input the production-related data that passes the real analysis into the regional simulation model for agricultural production data prediction calibration;

[0009] S4. Extract the sales data and network market demand data of the sales regions, and perform predicted demand change analysis by combining the sales data with the network market demand data;

[0010] S5. Combine the logistics transportation simulation of agricultural product supply for each agricultural product area with the sales area, evaluate and compare the simulation results with the predicted demand of the sales area, and mutually display the sales areas and agricultural product areas that meet the demand at the supply chain port according to the comparison results.

[0011] As a further improvement of this technical solution, in S1, a supply chain port is established and opened for use by agricultural product suppliers and sales managers. At the same time, when agricultural product suppliers and sales managers register for accounts, they need to fill in the area information they are responsible for.

[0012] As a further improvement of this technical solution, the steps of S1 are as follows:

[0013] S1.1. Collect agricultural product data from each agricultural product supplier. The agricultural product data includes agricultural product types and product grades. Then, generate agricultural product areas based on the agricultural product data feedback by the agricultural product suppliers combined with the area information, and summarize to generate a list of agricultural product areas.

[0014] S1.2. Generate corresponding sales areas based on the area information filled in by each sales manager, and summarize to generate a list of sales areas.

[0015] As a further improvement of this technical solution, the steps of S2 are as follows:

[0016] S2.1. Extract the production-related data of the agricultural product areas, sort it according to the collection time nodes of the production-related data, and set real weights for the production-related data according to the collection methods.

[0017] S2.2. Combine the production-related data repeatedly to generate multiple area simulation models corresponding to different combinations. Then, calculate the multiple area simulation models combined with the production-related data and the corresponding real weights, and select the area simulation model with the highest weight to represent the corresponding agricultural product area.

[0018] As a further improvement of this technical solution, when generating area simulation models in S2.2, if the production-related data of the agricultural product area is insufficient to support the establishment of the area simulation model, no simulation will be established. Send data collection information to the agricultural product supplier corresponding to the agricultural product area according to the missing data, and conduct establishment analysis based on the feedback information. If it still does not meet the establishment requirements, this agricultural product area will not be recommended at the supply chain port and will be independently operated by the agricultural product supplier.

[0019] As a further improvement of this technical solution, the steps of S3 are as follows:

[0020] S3.1. Set a dynamic difference threshold according to the latest simulation results of the area model combined with the time difference.

[0021] S3.2. Calculate the time difference between the production-related data collected after the latest simulation results and the latest simulation results, then extract the corresponding dynamic difference threshold for the time difference, and then conduct a difference rate analysis by combining the production-related data with the latest simulation results. At the same time, conduct a real analysis by combining the difference rate with the dynamic difference threshold. When the difference rate is less than or equal to the dynamic difference threshold, it is determined as real production-related data; otherwise, when the difference rate is greater than the dynamic difference threshold, it is determined as false production-related data;

[0022] S3.3. Input the production-related data determined as real in S3.2 into the regional simulation model for agricultural production data prediction calibration, so as to regenerate the simulation results.

[0023] As a further improvement of this technical solution, the S3.3 further includes the following steps:

[0024] S3.3.1. Send the latest simulation results to the agricultural product suppliers in the agricultural product regions through the supply chain port, and at the same time send accurate feedback to the agricultural product suppliers at the time point corresponding to the latest simulation results;

[0025] S3.3.2. Monitor the feedback results of S3.3.1. When the agricultural product suppliers give accurate feedback, continue to monitor; otherwise, when the agricultural product suppliers give inaccurate feedback, collect the growth data of the agricultural product regions from the agricultural product suppliers, and send the growth data to the supply chain port for manual review, and replace the latest simulation results according to the review results.

[0026] As a further improvement of this technical solution, the steps of S4 are as follows:

[0027] S4.1. Extract the sales data of the sales regions, and at the same time collect market demand data in the network;

[0028] S4.2. Conduct a predicted demand change analysis by combining the sales data with the network market demand data to obtain the predicted demand corresponding to the sales regions, and then send the predicted demand to the sales managers for modification feedback, and determine the predicted demand according to the feedback results.

[0029] As a further improvement of this technical solution, the steps of S5 are as follows:

[0030] S5.1. Conduct a logistics transportation simulation of the agricultural product processes by combining each agricultural product region with the sales regions, and then evaluate and compare the simulation results with the predicted demand of the sales regions. When the simulation results meet the predicted demand, retain them; otherwise, when the simulation results do not meet the predicted demand, do not retain them;

[0031] S5.2. Extract the corresponding sales regions and agricultural product regions based on the simulation results retained in S5.1 and display them mutually at the supply chain ports.

[0032] Advantages of the present invention compared with the prior art:

[0033] 1. In this method for integrating agricultural product supply chain information based on big data analysis, by establishing supply chain ports, collecting lists of agricultural product regions and sales regions, and integrating and managing the information of agricultural product suppliers and sales managers, the digitization of supply chain member information is achieved, facilitating different members to access and manage information, and improving the information transparency and management efficiency of the supply chain.

[0034] 2. In this method for integrating agricultural product supply chain information based on big data analysis, by extracting production-related data of agricultural product regions, sorting according to the collection time nodes and setting real weights, establishing a regional simulation model, supplementing and analyzing data when the data is insufficient, the accuracy and reliability of the model are ensured. By selecting the model with the highest weight to represent the agricultural product region, the production situation of the agricultural product region can be more accurately reflected, providing strong support for agricultural production. At the same time, the logistics transportation simulation of the agricultural product region and the sales region is carried out, and the evaluation and comparison are combined with the predicted demand to display the sales regions and agricultural product regions that meet the demand. By simulating the transportation process and considering various factors, the transportation efficiency and demand satisfaction are evaluated, which helps to optimize the logistics transportation path and resource allocation, improve the overall efficiency of the supply chain, reduce costs, and improve customer satisfaction.

[0035] 3. In this method for integrating agricultural product supply chain information based on big data analysis, by setting a difference threshold, the real analysis of the production-related data after the output of the simulation results is carried out to determine the authenticity of the data, and the real data is input into the regional simulation model for prediction calibration, making the simulation results closer to the actual production situation. By sending the simulation results and feedback to the suppliers, and monitoring and calibrating according to the feedback, the accuracy of the agricultural production simulation results is ensured, providing a reliable basis for production decisions. Description of the Drawings

[0036] Figure 1 is the overall flow chart of the present invention;

[0037] Figure 2 is the flow chart of summarizing and generating the sales region list of the present invention;

[0038] Figure 3 is the flow chart of selecting the regional simulation model with the highest weight to represent the corresponding agricultural product region of the present invention;

[0039] Figure 4 is the flow chart of setting the dynamic difference threshold of the present invention;

[0040] Figure 5 This is the flowchart for the present invention to determine the predicted demand based on the feedback results;

[0041] Figure 6 This is the flowchart for the present invention to extract the corresponding sales regions and agricultural product regions and display them to each other at the supply chain port. Detailed implementation manners

[0042] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] Please refer to Figure 1 - Figure 6 as shown, the purpose of this embodiment is to provide an agricultural product supply chain information integration method based on big data analysis, including the following steps:

[0044] S1. Establish a supply chain port and collect the list of agricultural product regions and the list of sales regions;

[0045] S1 is to establish a supply chain port and open it for use by agricultural product suppliers and sales managers in the supply chain port. At the same time, when agricultural product suppliers and sales managers register for accounts, they need to fill in the regional information they are responsible for. The specific steps are as follows:

[0046] Establish a supply chain port: The supply chain port is a digital platform for supply chain management that allows different supply chain members (such as agricultural product suppliers and sales managers) to access and manage information. It has functions including allowing suppliers and sales managers to create accounts, granting different permissions according to the user type (supplier or sales manager), and users filling in the regional information they are responsible for when registering (such as agricultural product suppliers filling in the regions they supply, and sales managers filling in the sales regions they are responsible for);

[0047] Registration of agricultural product suppliers: Agricultural product suppliers need to fill in the regional information they are responsible for during the registration process. The regional information can include the types of agricultural products, the supplied regions, and the product grades;

[0048] Registration of sales managers: Sales managers need to fill in the sales regions they are responsible for when registering. The sales region information includes sales channels and sales regions.

[0049] The steps of S1 are as follows:

[0050] S1.1. Collect agricultural product data from each agricultural product supplier. The agricultural product data includes the type and grade of agricultural products. Then, based on the agricultural product data feedback by the agricultural product supplier and combined with regional information, generate agricultural product regions and summarize them to generate a list of agricultural product regions.

[0051] Each agricultural product supplier needs to register on the supply chain port and fill in the information of the agricultural products it supplies. At the same time, the type, grade, and supply area information of the agricultural products provided by the supplier will be stored in the database and form data records. Then, the generation of agricultural product regions is based on the regional information and types of agricultural products provided by the supplier. According to the region where the supplier is located and the agricultural products it supplies, the system will automatically generate the regional information of each agricultural product, and then summarize all the agricultural product regional information to generate a complete list of agricultural product regions.

[0052] S1.2. Generate corresponding sales regions according to the regional information filled in by each sales manager and summarize them to generate a list of sales regions.

[0053] When registering, the sales manager needs to fill in the sales region information it is responsible for. The sales region information filled in by the sales manager will be stored in the database and form corresponding records. At the same time, the generation of sales regions is based on the regional information provided by the sales manager. The regional information filled in by the sales manager is closely related to the sales channels it is responsible for. The system will generate corresponding sales regions based on this information, and finally summarize all the sales region information to generate a complete list of sales regions.

[0054] S2. Extract the production-related data of agricultural product regions, sort the production-related data according to the collection time node, and at the same time set the real weights for the production-related data according to the collection method, and establish a corresponding regional simulation model for each agricultural product region.

[0055] The steps of S2 are as follows:

[0056] S2.1. Extract the production-related data of agricultural product regions and sort them according to the collection time node of the production-related data. At the same time, set the real weights for the production-related data according to the collection method. For example, satellite remote sensing can be set to 0.9, Internet of Things device collection to 0.8, manual reporting to 0.6, and local agricultural bureau to 0.7.

[0057] The production-related data includes environmental data such as the type of agricultural products, grade of agricultural products, production area, yield, planting cycle, soil type, and water source conditions, climate data (temperature, precipitation, humidity), data collection time node, and data collection method.

[0058] The data sources include manual reporting, Internet of Things device collection, satellite remote sensing, and synchronization with the local agricultural bureau system.

[0059] S2.2. Repeatedly combine the production-related data to generate regional simulation models corresponding to multiple different combinations. Then, calculate by combining the multiple regional simulation models with the production-related data and the corresponding true weights, and select the regional simulation model with the highest weight to represent the corresponding agricultural product region. The specific formula is as follows:

[0060] ;

[0061] where, v i is the key index value of the i-th data (such as yield, planting area, etc., which can be weighted and combined), w i is the true weight of the i-th data, n is the total number of data, M is the regional simulation model, and Score(M) is the score of the regional simulation model;

[0062] Then, select the model with the highest score as the representative simulation model of the current agricultural product region.

[0063] When generating the regional simulation model in S2.2, if the production-related data of the agricultural product region is insufficient to support the establishment of the regional simulation model, then the simulation establishment is not carried out. Send data collection information to the agricultural product supplier corresponding to the agricultural product region according to the missing data, and conduct establishment analysis based on the feedback information. If it still does not meet the establishment requirements, then this agricultural product region is not recommended at the supply chain port and is independently operated by the agricultural product supplier. The steps are as follows:

[0064] Check the integrity of the production data: Before establishing the regional simulation model, it is first necessary to confirm whether the production data of the agricultural product region is complete, that is, whether it meets the most basic data requirements of the model. The inspection indicators include whether the key production data is missing (such as planting area, yield, soil type, climate, etc.), whether the collected data meets the expected standards, and there are no abnormal fluctuations;

[0065] If the data is insufficient, request data supplementation from the supplier. The specific content of the requested data includes the missing data types (yield, climate, soil type, etc.), suggestions for data collection methods (remote sensing, sensor reporting, manual reporting, etc.), and the time node for requesting data (to ensure timeliness). The supplier feeds back the supplementary data within the specified time;

[0066] Analyze and establish based on the supplementary data fed back by the supplier: The supplier returns the required supplementary data within the specified time. Check the integrity of the data again. If the supplementary data is still insufficient, proceed to the next step (i.e., reject the establishment of the simulation model). On the contrary, if the data meets the requirements, then continue to construct the regional simulation model, conduct scoring and selection.

[0067] S3. Set a difference threshold, and at the same time, combine the production-related data after outputting the simulation results with the regional simulation model and the difference threshold for real analysis, and then input the production-related data passed through the real analysis into the regional simulation model for agricultural production data prediction calibration;

[0068] The steps of S3 are as follows:

[0069] S3.1. Set a dynamic difference threshold according to the latest simulation results of the regional model in combination with the time difference;

[0070] S3.2. Calculate the time difference between the production-related data collected after the latest simulation results and the latest simulation results, then extract the corresponding dynamic difference threshold for the time difference, and then conduct a difference rate analysis by combining the production-related data with the latest simulation results. At the same time, conduct a real analysis by combining the difference rate with the dynamic difference threshold. When the difference rate is less than or equal to the dynamic difference threshold, it is determined as real production-related data. On the contrary, when the difference rate is greater than the dynamic difference threshold, it is determined as false production-related data. The specific steps are as follows:

[0071] Obtain the latest regional simulation results: Obtain the latest results of the regional simulation model, which usually include predicted values of various production-related data, such as yield, planting area, etc.;

[0072] Collect new production-related data: Collect the latest production-related data at the current time point. These data may come from on-site collection, sensors, supplier feedback, etc. Compare the time stamps of the latest simulation results and the collection time of the new data, and calculate the time difference between the two;

[0073] Set the dynamic difference threshold: The dynamic difference threshold calculated according to the time difference. The setting of the dynamic difference threshold can be determined by a preset rule, which is usually related to the time difference: as the time difference increases, the threshold will change. The formula is as follows:

[0074] ;

[0075] where E(t) is the dynamic difference threshold, t is the time difference, e is the initial threshold, and α is the attenuation factor;

[0076] Conduct a difference rate analysis: Calculate the difference rate between the new production data and the latest simulation results. The difference rate can be calculated by the ratio or difference between the two. If the difference rate is less than or equal to the dynamic difference threshold, the data is considered real. On the contrary, if the difference rate is greater than the dynamic difference threshold, the data is considered false data;

[0077] Feedback and adjustment: According to the judgment result, it is automatically fed back to the supply chain port. If the data is judged to be false, the supplier can be required to re-verify or adjust the data. If the data is judged to be true, it can be incorporated into the adjustment of the new regional model to further improve the prediction.

[0078] S3.3. Input the production-related data determined to be true in S3.2 into the regional simulation model for agricultural production data prediction calibration, so as to regenerate the simulation result.

[0079] The calibrated regional simulation model will generate new agricultural production prediction data. The model will correct the prediction result according to the real input data to make it closer to the actual production situation. The calibrated agricultural production data can be used for further decision support, production planning, supply chain adjustment, etc.

[0080] S3.3 also includes the following steps:

[0081] S3.3.1. Send the latest simulation result to the agricultural product suppliers in the agricultural product region through the supply chain port, and at the same time send an accurate feedback to the agricultural product suppliers at the time point corresponding to the latest simulation result;

[0082] S3.3.2. Monitor the feedback result of S3.3.1. When the feedback from the agricultural product supplier is accurate, continue to monitor. On the contrary, when the feedback from the agricultural product supplier is inaccurate, collect the growth data of the agricultural product region from the agricultural product supplier, and feed the growth data back to the supply chain port for manual review, and replace the latest simulation result according to the review result;

[0083] Realize sending the latest simulation result to the supplier, continuously monitoring and calibrating the model according to the feedback of the supplier. When the feedback is inaccurate, the system will collect new growth data and conduct manual review, and finally replace the simulation data according to the review result, which can ensure that the simulation result of agricultural production always remains accurate and provides strong support for production decision-making.

[0084] S4. Extract the sales data and network market demand data in the sales region, and combine the sales data with the network market demand data to analyze the predicted demand changes;

[0085] The steps of S4 are as follows:

[0086] S4.1. Extract the sales data in the sales region, and at the same time collect the market demand data in the network;

[0087] S4.2. Combine the sales data with the network market demand data to analyze the predicted demand changes, obtain the predicted demand corresponding to the sales region, and then send the predicted demand to the sales manager for modification feedback, and determine the predicted demand according to the feedback result. The specific steps are as follows:

[0088] Extract sales data for the sales area: Extract historical sales data for the sales area from the database or sales management system. This data usually includes time, sales volume, sales amount, product category, etc.;

[0089] Collect market demand data: Collect market demand data through the Internet. This data includes user behavior, social media trends, search engine query volume, consumer reviews, etc.;

[0090] Conduct predictive analysis by combining sales data and market demand data: Use machine learning algorithms to combine sales data and market demand data to generate a prediction of future demand. The specific formula is as follows:

[0091] ;

[0092] where D x is the predicted demand, S x is the historical sales data, A x is the market demand data, and β and ε are weight coefficients indicating the importance of sales data and market demand data;

[0093] Send the predicted demand to the sales manager for modification feedback: Send the generated predicted demand to the sales manager. The sales manager reviews and adjusts it. The feedback from the sales manager may be based on factors such as market strategy, production capacity, inventory, etc.;

[0094] Determine the final predicted demand based on the feedback results: Adjust the predictive demand model according to the feedback from the sales management side and finally determine the sales demand to be executed.

[0095] S5. Simulate the logistics transportation of agricultural product supply by combining each agricultural product area with the sales area, evaluate and compare the simulation results with the predicted demand of the sales area, and display the sales areas and agricultural product areas that meet the demand to each other at the supply chain port.

[0096] The steps of S5 are as follows:

[0097] S5.1. Simulate the logistics transportation of agricultural product processes by combining each agricultural product area with the sales area, and then evaluate and compare the simulation results with the predicted demand of the sales area. If the simulation results meet the predicted demand, they are retained; otherwise, if the simulation results do not meet the predicted demand, they are not retained;

[0098] S5.2. Extract the corresponding sales areas and agricultural product areas based on the simulation results retained in S5.1 and display them to each other at the supply chain port. The specific steps are as follows:

[0099] Conduct logistics transportation simulation by combining the agricultural product regions and the sales regions: According to the technological processes and characteristics of each agricultural product, simulate the transportation process from the production areas (agricultural product regions) to the sales regions. The factors to be considered include transportation modes, time, cost, weather, transportation restrictions, etc. The logistics paths and times may vary for each sales region's demand and the corresponding agricultural product regions. The simulation results will help evaluate the transportation efficiency of each region;

[0100] Combine the predicted demands of the sales regions: Compare the predicted demands of the sales regions with the transportation simulation results. The simulation results can be a transportation plan, including the transportation times, product arrival quantities, etc. for different sales regions. Compare these with the demands of the sales regions to evaluate whether the demands can be met;

[0101] Evaluate whether the simulation results meet the predicted demands: Set a threshold. When the satisfaction degree of the transportation simulation results is not lower than the threshold, retain the simulation results; when the results are lower than the threshold, do not retain them. The evaluation criteria can be factors such as transportation time, product integrity, transportation cost, demand coverage rate, etc.;

[0102] Extract and display the results at the supply chain ports: Extract the corresponding sales region and agricultural product region data from the retained simulation results and display them at the supply chain ports (such as supply chain management systems, visualization panels, etc.), providing an interactive display of data such as the logistics transportation process, demand satisfaction, cost, time, etc., so that managers can make more targeted decisions.

[0103] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. The above embodiments and the descriptions in the specification are only preferred examples of the present invention and are not used to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An information integration method for agricultural product supply chains based on big data analysis, characterized in that: It includes the following steps: S1. Establish a supply chain port, and collect the list of agricultural product regions and the list of sales regions; S2. Extract the production-related data of the agricultural product regions, sort the production-related data according to the collection time node, and set the real weight for the production-related data according to the collection method, and establish a corresponding regional simulation model for each agricultural product region; S3. Set the difference threshold, and at the same time conduct real analysis on the production-related data after the output simulation results in combination with the regional simulation model and the difference threshold, and then input the production-related data that passes the real analysis into the regional simulation model for agricultural production data prediction calibration; S4. Extract the sales data and online market demand data of the sales regions, and conduct predictive demand change analysis by combining the sales data with the online market demand data; S5. Conduct logistics transportation simulation of agricultural product supply by combining each agricultural product region with the sales region, evaluate and compare the simulation results with the predicted demand of the sales region, and display the sales regions and agricultural product regions that meet the demand to each other at the supply chain port according to the comparison results; The steps of S3 are as follows: S3.

1. Set a dynamic difference threshold according to the latest simulation result of the regional model in combination with the time difference; S3.

2. Calculate the time difference between the production-related data collected after the latest simulation result and the latest simulation result, then extract the corresponding dynamic difference threshold from the time difference, and then conduct difference rate analysis on the production-related data collected after the latest simulation result in combination with the latest simulation result. At the same time, conduct real analysis by combining the difference rate with the dynamic difference threshold. When the difference rate is less than or equal to the dynamic difference threshold, it is determined as real production-related data. On the contrary, when the difference rate is greater than the dynamic difference threshold, it is determined as false production-related data; S3.

3. Input the production-related data determined as real in S3.2 into the regional simulation model for agricultural production data prediction calibration, so as to regenerate the simulation result; The S3.3 also includes the following steps: S3.3.

1. Send the latest simulation result to the agricultural product suppliers in the agricultural product regions through the supply chain port, and send accurate feedback to the agricultural product suppliers at the time point corresponding to the latest simulation result; S3.3.

2. Monitor the feedback result of S3.3.

1. When the agricultural product supplier's feedback is accurate, continue to monitor. On the contrary, when the agricultural product supplier's feedback is inaccurate, collect the growth data of the agricultural product region from the agricultural product supplier, and feedback the growth data to the supply chain port for manual review, and replace the latest simulation result according to the review result; 2. The method for integrating agricultural product supply chain information based on big data analysis according to claim 1, wherein: S1 is implemented by establishing a supply chain port and opening it for use by agricultural product suppliers and sales managers in the supply chain port. At the same time, when the agricultural product suppliers and sales managers register for accounts, they need to fill in the regional information they are responsible for; 3. A method for integrating agricultural product supply chain information based on big data analysis according to claim 1, characterized in that: The steps of S1 are as follows: S1.

1. Collect agricultural product data from each agricultural product supplier. The agricultural product data includes the type of agricultural product and the product grade. Then, generate agricultural product regions according to the agricultural product data feedback by the agricultural product suppliers in combination with the regional information, and summarize them to generate a list of agricultural product regions; S1.

2. Generate corresponding sales regions based on the regional information filled in by each sales manager, and summarize them to generate a list of sales regions.

4. A method for integrating agricultural product supply chain information based on big data analysis according to claim 1, characterized in that: The steps of S2 are as follows: S2.

1. Extract the production-related data of the agricultural product regions, sort them according to the collection time nodes of the production-related data, and set the real weights for the production-related data according to the collection methods. S2.

2. Repeatedly combine the production-related data to generate multiple regional simulation models corresponding to different combinations, and then calculate by combining the multiple regional simulation models with the production-related data and the corresponding real weights, and select the regional simulation model with the highest weight to represent the corresponding agricultural product region.

5. A method for integrating agricultural product supply chain information based on big data analysis according to claim 4, characterized in that: When generating the regional simulation model in S2.2, if the production-related data of the agricultural product region is insufficient to support the establishment of the regional simulation model, no simulation establishment will be carried out. Send data collection information to the agricultural product supplier corresponding to the agricultural product region according to the missing data, and conduct establishment analysis based on the feedback information. If it still does not meet the establishment requirements, then this agricultural product region will not be recommended at the supply chain port and will be independently operated by the agricultural product supplier.

6. The information integration method of the agricultural product supply chain based on big data analysis according to claim 1, characterized in that: The steps of S4 are as follows: S4.

1. Extract the sales data of the sales regions and collect market demand data on the network at the same time. S4.

2. Conduct predictive demand change analysis by combining the sales data with the network market demand data to obtain the predictive demand corresponding to the sales region, and then send the predictive demand to the sales manager for modification feedback, and determine the predictive demand according to the feedback results.

7. A method for integrating agricultural product supply chain information based on big data analysis according to claim 1, characterized in that: The steps of S5 are as follows: S5.

1. Conduct logistics transportation simulation of the agricultural product process by combining each agricultural product region with the sales region, and then evaluate and compare the simulation results with the predictive demand of the sales region. When the simulation results meet the predictive demand, they will be retained; otherwise, when the simulation results do not meet the predictive demand, they will not be retained. S5.

2. Extract the corresponding sales regions and agricultural product regions based on the simulation results retained in S5.1 and display them to each other at the supply chain port.

Images