Agricultural product and explosive product identification method and system based on county and rural e-commerce big data

Abstract

The invention discloses an agricultural product and explosive product identification method and system based on county and rural e-commerce big data, and belongs to the technical field of e-commerce and big data analysis. Data is collected from multiple channels including all rural e-commerce platforms, government agricultural departments and third-party data service institutions in the county; preprocessing the data; constructing an explosive identification model, and training a linear regression model by using historical time sequence data; explosive identification: inputting new agricultural product data into the trained explosive identification model; the model performs prediction and classification according to the characteristic variables of the input data, and judges whether the agricultural product has the potential of becoming a blasting product or not; carrying out deep analysis on the identified explosives; making a marketing strategy; and monitoring and adjusting in real time. The agricultural product sales data can be deeply mined and analyzed, and scientific and accurate product selection suggestions are provided for agricultural product suppliers and e-commerce platforms.

Description

Technical Field

[0001] The present invention relates to the field of e-commerce and big data analysis technology, and in particular to a method and system for identifying hot-selling agricultural products based on county rural e-commerce big data. Background Art

[0002] With the rapid development of rural e-commerce, the sales of agricultural products in the county are gradually moving online and on a large scale. However, faced with a large number of agricultural product types and complex market demands, how to accurately select products has become a major problem for agricultural product suppliers and e-commerce platforms. Traditional product selection methods mostly rely on experience judgment or limited market research, which makes it difficult to fully grasp market trends and changes in consumer demand. Therefore, how to use big data analysis technology to optimize product selection strategies and achieve intelligent and personalized agricultural product selection has become a difficult problem that needs to be overcome in the current development of rural e-commerce. Summary of the invention

[0003] The technical task of the present invention is to address the above shortcomings and provide a method and system for identifying hot-selling agricultural products based on county rural e-commerce big data, which can deeply mine and analyze agricultural product sales data and provide scientific and accurate product selection suggestions for agricultural product suppliers and e-commerce platforms.

[0004] The technical solution adopted by the present invention to solve its technical problem is:

[0005] A method for identifying hot-selling agricultural products based on county rural e-commerce big data, the implementation of which includes the following steps:

[0006] 1) Data collection: Collect data from multiple channels including various rural e-commerce platforms in the county, government agricultural departments, and third-party data service agencies, including agricultural product transaction data, user behavior data, price information, inventory status, etc.;

[0007] 2) Data preprocessing: cleaning, deduplication, and formatting the collected raw data to ensure data quality;

[0008] 3) Build a hot-selling product identification model, perform time series preprocessing on sample data, extract key information such as characteristics; use historical time series data to train a linear regression model;

[0009] 4) Hot-selling product identification: input new agricultural product data into the trained hot-selling product identification model; the model predicts and classifies the characteristic variables of the input data to determine whether the agricultural product has the potential to become a hot-selling product;

[0010] 5) Feature analysis: conduct in-depth analysis of the identified hot products to provide a strong basis for the formulation of marketing strategies;

[0011] 6) Marketing strategy formulation;

[0012] 7) Real-time monitoring and adjustment.

[0013] This method integrates the massive data resources of rural e-commerce platforms within the county, applies advanced data analysis algorithms to deeply mine and analyze agricultural product sales data, and provides scientific and accurate product selection suggestions for agricultural product suppliers and e-commerce platforms.

[0014] Furthermore, for the data collection, the types of data collected include agricultural product sales volume, page views, add-to-cart rate, conversion rate, user reviews, repurchase rate, seasonal sales trends, etc.

[0015] Furthermore, for the data preprocessing, data desensitization technology is applied to protect user privacy and security; the data is standardized for subsequent analysis.

[0016] Furthermore, for the construction of the popular product identification model, the linear regression model is as follows:

[0017] y_t = β_0 + β_1x_t +... + β_nx_{t - n} + ε

[0018] where y_t is the predicted value, x_t is the input feature (such as historical quarterly value), β is the coefficient, and ε is the error term.

[0019] Furthermore, for the feature analysis,

[0020] Conduct in-depth analysis on the identified popular products, including analyzing features such as their price, quality, taste, packaging, etc., to understand the needs and preferences of the target user group;

[0021] Combined with user portrait and purchase behavior analysis, provide a strong basis for the formulation of marketing strategies.

[0022] Furthermore, for the formulation of marketing strategies:

[0023] Based on the feature analysis results of popular products and the needs of the target user group, formulate targeted marketing strategies;

[0024] Marketing strategies may include price adjustment, promotional activities, advertising investment, social media promotion, etc., aiming to increase the popularity and sales volume of popular products.

[0025] Furthermore, for the real-time monitoring and adjustment, it includes:

[0026] Conduct real-time monitoring of the sales situation of popular products;

[0027] According to market changes and consumer feedback, timely adjust marketing strategies and supply chain management;

[0028] Through continuous optimization and improvement, ensure the continuous market competitiveness of popular products.

[0029] The present invention also claims to protect an agricultural product bestseller identification system based on county-level rural e-commerce big data, which includes a model construction module, a bestseller analysis module, and a market insight module:

[0030] The model construction module includes: data collection, data preprocessing, and bestseller identification model construction;

[0031] The bestseller analysis module includes: bestseller identification and feature analysis;

[0032] The market insight module includes marketing strategy formulation and real-time monitoring and adjustment;

[0033] This system realizes the identification of agricultural product bestsellers based on county-level rural e-commerce big data through the above method.

[0034] By deeply mining multi-dimensional data such as market trends, consumer behavior, and product performance, it provides accurate and efficient agricultural product selection suggestions for e-commerce platforms and merchants, so as to enhance market competitiveness and sales efficiency.

[0035] The present invention also claims to protect an agricultural product bestseller identification device based on county-level rural e-commerce big data, which includes at least one memory and at least one processor;

[0036] The at least one memory is used to store machine-readable programs;

[0037] The at least one processor is used to call the machine-readable program to implement the above method.

[0038] The present invention also claims to protect a computer-readable medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the processor implements the above method.

[0039] Compared with the prior art, an agricultural product bestseller identification method and system based on county-level rural e-commerce big data of the present invention has the following beneficial effects:

[0040] 1. Precise identification: Through big data analysis and machine learning algorithms, it can accurately identify agricultural product bestsellers with market potential.

[0041] 2. Comprehensive analysis: Considering multiple dimensions and characteristic variables comprehensively, it conducts a comprehensive analysis of bestsellers, providing a strong basis for the formulation of marketing strategies.

[0042] 3. Real-time monitoring: Real-time monitoring of the sales situation of bestsellers can timely detect market changes and changes in consumer demands, providing timely feedback for the adjustment of marketing strategies.

[0043] 4. Optimization Management: Through the implementation of the present invention, accurate analysis and effective management of popular agricultural products can be achieved, improving the competitiveness of rural e-commerce in counties and promoting the sales of agricultural products. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 FIG. is a diagram showing the model construction process in the method for identifying popular agricultural products based on big data of rural e-commerce in counties according to an embodiment of the present invention;

[0045] Figure 2 FIG. is a diagram showing the analysis process of popular products in the method for identifying popular agricultural products based on big data of rural e-commerce in counties according to an embodiment of the present invention;

[0046] Figure 3 FIG. is a diagram showing the market insight process in the method for identifying popular agricultural products based on big data of rural e-commerce in counties according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The present invention will be further described below with reference to specific embodiments.

[0048] An embodiment of the present invention provides a method for identifying popular agricultural products (agricultural product selection) based on big data of rural e-commerce in counties, and the implementation of this method includes the following steps:

[0049] 1. Data Collection:

[0050] Collect data such as agricultural product transaction data, user behavior data, price information, inventory status, etc. from various channels such as rural e-commerce platforms, government agricultural departments, and third-party data service institutions within the county.

[0051] The data types include but are not limited to agricultural product sales volume, page views, add-to-cart rate, conversion rate, user reviews, repurchase rate, seasonal sales trends, etc.

[0052] 2. Data Preprocessing:

[0053] Clean, deduplicate, and format the collected original data to ensure data quality.

[0054] Apply data desensitization technology to protect user privacy and security.

[0055] Standardize the data for subsequent analysis.

[0056] 3. Construction of Popular Product Identification Model:

[0057] Perform time series preprocessing on the sample data to extract key information such as characteristic information.

[0058] Train a linear regression model using historical time series data:

[0059] y_t = β_0 + β_1x_t +... + β_nx_{t - n} + ε

[0060] Among them, y_t is the predicted value, x_t is the input feature (such as historical quarterly value), β is the coefficient, and ε is the error term.

[0061] 4. Best-selling product identification:

[0062] Input the new agricultural product data into the trained best-selling product identification model.

[0063] The model makes predictions and classifications based on the characteristic variables of the input data to determine whether the agricultural product has the potential to become a best-selling product.

[0064] 5. Feature analysis:

[0065] Conduct in-depth analysis on the identified best-selling products.

[0066] Analyze the characteristics in aspects such as price, quality, taste, packaging, etc., and understand the needs and preferences of the target user group.

[0067] Combined with user portrait and purchase behavior analysis, it provides a strong basis for formulating marketing strategies.

[0068] 6. Marketing strategy formulation:

[0069] Based on the results of the feature analysis of best-selling products and the needs of the target user group, formulate targeted marketing strategies.

[0070] The marketing strategies can include price adjustment, promotional activities, advertising investment, social media promotion, etc., aiming to improve the popularity and sales volume of best-selling products.

[0071] 7. Real-time monitoring and adjustment:

[0072] Conduct real-time monitoring on the sales situation of best-selling products.

[0073] According to market changes and consumer feedback, timely adjust marketing strategies and supply chain management.

[0074] Through continuous optimization and improvement, ensure the continuous market competitiveness of best-selling products.

[0075] This method for identifying best-selling agricultural products based on county-level rural e-commerce big data can accurately select agricultural product best-sellers with market potential through the application of big data analysis and machine learning algorithms, and provide decision-making support for agricultural product suppliers and e-commerce platforms. The implementation of this method is of great significance for enhancing the competitiveness of county-level rural e-commerce and promoting the sales of agricultural products.

[0076] An embodiment of the present invention also provides an agricultural product hit product identification system based on county-level rural e-commerce big data. This system realizes the identification of agricultural product hit products based on county-level rural e-commerce big data through the agricultural product hit product identification method described in the above embodiment.

[0077] The system includes a model construction module, a hit product analysis module, and a market insight module.

[0078] The model construction module includes: data collection, data preprocessing, and hit product identification model construction.

[0079] Data collection:

[0080] Collect data such as agricultural product transaction data, user behavior data, price information, inventory status, etc. from multiple channels such as rural e-commerce platforms, government agricultural departments, and third-party data service agencies within the county;

[0081] The data types include but are not limited to agricultural product sales volume, page views, add-to-cart rate, conversion rate, user reviews, repurchase rate, seasonal sales trends, etc.

[0082] Data preprocessing:

[0083] Clean, deduplicate, and format the collected raw data to ensure data quality;

[0084] Apply data desensitization technology to protect user privacy and security;

[0085] Standardize the data for subsequent analysis.

[0086] Hit product identification model construction:

[0087] Perform time series preprocessing on the sample data to extract key information such as characteristic information;

[0088] Use historical time series data to train a linear regression model:

[0089] y_t = β_0 + β_1x_t +... + β_nx_{t - n} + ε

[0090] Where y_t is the predicted value, x_t is the input feature (such as historical quarterly value), β is the coefficient, and ε is the error term.

[0091] The hit product analysis module includes: hit product identification and feature analysis.

[0092] Hit product identification:

[0093] Input new agricultural product data into the trained hit product identification model.

[0094] The model makes predictions and classifications based on the characteristic variables of the input data to determine whether the agricultural product has the potential to become a hit product.

[0095] Feature analysis:

[0096] Conduct in-depth analysis on the identified hit products;

[0097] Analyze their characteristics in terms of price, quality, taste, packaging, etc., and understand the needs and preferences of the target user group;

[0098] Combined with user profiling and purchase behavior analysis, provide strong evidence for the formulation of marketing strategies.

[0099] The market insight module described above includes the formulation of marketing strategies and real-time monitoring and adjustment.

[0100] Formulation of marketing strategies:

[0101] Based on the results of the feature analysis of the hit products and the needs of the target user group, formulate targeted marketing strategies;

[0102] The marketing strategies may include price adjustment, promotional activities, advertising placement, social media promotion, etc., aiming to increase the popularity and sales volume of the hit products.

[0103] Real-time monitoring and adjustment:

[0104] Conduct real-time monitoring on the sales situation of the hit products;

[0105] According to market changes and consumer feedback, timely adjust marketing strategies and supply chain management;

[0106] Through continuous optimization and improvement, ensure the continuous market competitiveness of the hit products.

[0107] This system provides accurate and efficient agricultural product selection suggestions for e-commerce platforms and merchants by deeply mining multi-dimensional data such as market trends, consumer behavior, and product performance, so as to enhance market competitiveness and sales efficiency.

[0108] An embodiment of the present invention also provides an agricultural product hit product identification device based on county-level rural e-commerce big data, including at least one memory and at least one processor;

[0109] The at least one memory is used to store machine-readable programs;

[0110] The at least one processor is used to call the machine-readable program to implement the agricultural product hit product identification method described in the above embodiment.

[0111] An embodiment of the present invention further provides a computer-readable medium, on which computer instructions are stored. When the computer instructions are executed by a processor, the processor is caused to execute the method for identifying popular agricultural products based on county-level rural e-commerce big data described in the above embodiments. Specifically, a system or device equipped with a storage medium can be provided, on which software program codes for implementing the functions of any one of the above embodiments are stored, and the computer (or CPU or MPU) of the system or device is caused to read and execute the program codes stored in the storage medium.

[0112] In this case, the program code read from the storage medium itself can implement the functions of any one of the above embodiments. Therefore, the program code and the storage medium storing the program code constitute a part of the present invention.

[0113] Embodiments of the storage medium for providing program codes include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Optionally, the program code can be downloaded from a server computer via a communication network.

[0114] Furthermore, it should be clear that not only can the functions of any one of the above embodiments be realized by executing the program code read by the computer, but also by causing an operating system operating on the computer based on the instructions of the program code to complete part or all of the actual operations.

[0115] In addition, it can be understood that the program code read from the storage medium is written into the memory provided in the expansion board inserted into the computer or into the memory provided in the expansion unit connected to the computer, and then based on the instructions of the program code, the CPU etc. installed on the expansion board or the expansion unit are caused to execute part and all of the actual operations, thereby realizing the functions of any one of the above embodiments.

[0116] The present invention has been described in detail above through the drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above-mentioned multiple embodiments, those skilled in the art can know that more embodiments of the present invention can be obtained by combining the code review means in the above different embodiments, and these embodiments are also within the protection scope of the present invention.

Claims

1. A method for identifying hot agricultural products based on county rural e-commerce big data, characterized in that: The implementation of this method includes the following steps: 1) Data collection: Collect data from multiple channels including various rural e-commerce platforms in the county, government agricultural departments, and third-party data service agencies, including agricultural product transaction data, user behavior data, price information, and inventory status; 2) Data preprocessing: cleaning, deduplication, and formatting the collected raw data to ensure data quality; 3) Build a hot-selling product identification model, perform time series preprocessing on sample data, and extract characteristic key information; use historical time series data to train a linear regression model; 4) Hot-selling product identification: input new agricultural product data into the trained hot-selling product identification model; the model predicts and classifies the characteristic variables of the input data to determine whether the agricultural product has the potential to become a hot-selling product; 5) Feature analysis: conduct in-depth analysis of the identified hot products to provide a strong basis for the formulation of marketing strategies; 6) Marketing strategy formulation; 7) Real-time monitoring and adjustment.

2. According to claim 1, a method for identifying hot agricultural products based on county rural e-commerce big data is characterized in that: The data collected includes agricultural product sales, page views, add-to-cart rate, conversion rate, user reviews, repurchase rate, and seasonal sales trends.

3. The method for identifying hot agricultural products based on county rural e-commerce big data according to claim 1 is characterized in that: The data preprocessing applies data desensitization technology to protect user privacy and security; the data is standardized for subsequent analysis.

4. According to claim 1, a method for identifying hot agricultural products based on county rural e-commerce big data is characterized in that: The hot-selling product identification model is constructed, and the linear regression model is as follows: y_t=β_0+β_1x_t+...+β_nx_{tn}+ε Where y_t is the predicted value, x_t is the input feature, β is the coefficient, and ε is the error term.

5. The method for identifying hot agricultural products based on county rural e-commerce big data according to claim 1 is characterized in that: The feature analysis, Conduct in-depth analysis of the identified hot-selling products, including analyzing their price, quality, taste, and packaging characteristics to understand the needs and preferences of the target user groups; Combine user portraits and purchasing behavior analysis to provide a basis for the formulation of marketing strategies.

6. The method for identifying hot agricultural products based on county rural e-commerce big data according to claim 1 is characterized in that: The marketing strategy is formulated by: Develop targeted marketing strategies based on the characteristics analysis results of hot products and the needs of target user groups; Marketing strategies may include price adjustments, promotions, advertising, and social media outreach.

7. The method for identifying hot agricultural products based on county rural e-commerce big data according to claim 1 is characterized in that: The real-time monitoring and adjustment include: Real-time monitoring of the sales of hot products; Timely adjust marketing strategies and supply chain management according to market changes and consumer feedback; Ensure the continued market competitiveness of hot products through continuous optimization and improvement.

8. A system for identifying hot agricultural products based on county-level rural e-commerce big data, characterized in that: Including model building module, hot product analysis module and market insight module: The model building module includes: data collection, data preprocessing and hot product identification model building; The hot-product analysis module includes: hot-product identification and feature analysis; The market insight module includes marketing strategy formulation and real-time monitoring and adjustment; The system realizes the identification of hot-selling agricultural products based on county rural e-commerce big data through any method described in claims 1 to 7.

9. A device for identifying hot agricultural products based on county rural e-commerce big data, characterized in that: comprising at least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is used to call the machine-readable program to implement the method described in any one of claims 1 to 7.

10. A computer-readable medium, characterized in that The computer readable medium stores computer instructions, which, when executed by a processor, enable the processor to implement the method according to any one of claims 1 to 7.

Images