Research on E-commerce Mode of Rural Common Wealth Realisation Path under the Internet Environment
Published Online: Feb 03, 2025
Received: Sep 20, 2024
Accepted: Dec 26, 2024
DOI: https://doi.org/10.2478/amns-2025-0038
Keywords
© 2025 Yuming Cen et al., published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.
Common prosperity is an important element of China’s socialist core values and one of the major goals of national development. Common prosperity requires not only an increase in the average income level of rural residents but also an increase in the fairness of income distribution. Realizing common prosperity is a comprehensive goal that requires the joint efforts of the government and all sectors of society. Rural e-commerce is an important way to realize common prosperity in rural areas [1–4].
As the gap between urban and rural economic development gradually widens, the development of rural e-commerce has become one of the important means to promote rural economic growth. Rural e-commerce has promoted the process of farmers’ enrichment through different business models. First of all, the sales mode of agricultural products based on the e-commerce platform, combining the traditional offline market with the Internet, realizes the convenience of round-the-clock sales [5–8]. Farmers can sell their agricultural products on the shelves through the e-commerce platform and directly connect with urban consumers, breaking the limitations of traditional sales channels and improving sales efficiency and sales. Secondly, rural e-commerce also adopts the order agriculture model through cooperation with agricultural cooperatives, family farms and other organizations, matching agricultural products with orders to achieve targeted production and sales, improving the quality of supply of agricultural products and market adaptability [9–12]. In addition, rural e-commerce also uses the integration mode of rural characteristic resources, combines agricultural products with tourism, culture and other resources, and promotes and sells them through the rural e-commerce platform, increasing the added value of agricultural products and expanding the market influence of agricultural products, thus realizing the common prosperity of rural areas [13–16].
Literature [17] combined quantitative research methods such as multiple regression analysis and moderated effects modeling with qualitative research methods such as interviews and questionnaires to launch a sample survey of hundreds of Taobao villages in Zhejiang Province, and the analysis results mentioned that rural e-commerce meets the residents’ material, spiritual, and ecological needs, and promotes entrepreneurship, financial literacy, and occupational identity in the countryside, which has a reference value. Literature [18] outlined the reasons and advantages of precise poverty alleviation by e-commerce based on e-commerce and proposed feasible measures to realize precise poverty alleviation relying on rural e-commerce in Guangdong Province, taking into account the current situation of the development of rural e-commerce in Guangdong Province and its constraints. Literature [19] discusses the impact of rural e-commerce on the urban-rural income gap from the perspective of Taobao village coverage and by using two-way fixed effects, nonlinear and other models, emphasizing that there is a gap between the rural and urban ability to use e-commerce, which in fact widens the urban-rural income gap. Literature [20] discusses both positive and negative factors in the process of rural e-commerce development, in addition to proposing an e-commerce model applicable to China’s rural areas through a case study analysis of the results of rural e-commerce development, aiming to promote the development of rural e-commerce. Literature [21] explored the relationship between rural e-commerce and county economic development in China, using the comprehensive rural e-commerce demonstration policy as a quasi-natural experiment. The results of the study pointed out that the policy had a positive impact on the county-level economy, while the good development of rural e-commerce helped to stimulate the development of the county-level economy. Literature [22] aims to examine the impact that e-commerce has on the urban-rural income gap and analyzes provincial panel data from 2007-2023 by using linear and panel threshold models. The results show that in the linear model, e-commerce is conducive to narrowing the urban-rural income gap, while in the panel threshold model, only areas with relatively high levels of e-commerce have a certain effect, and the results of the narrowing of the urban-rural gap are very significant in the areas with high levels of education. Literature [23] took the projection tracing method to measure the common prosperity level of thousands of counties in China during the period from 2010 to 2023 and applied the multi-period, multi-space DID model to elucidate the impact of e-commerce development on the common prosperity of counties. It is shown that the level of common prosperity in Chinese countries has significantly increased, and rural e-commerce policies have played an important role in this process, but there are obvious regional differences. Literature [24] illustrates that the deep integration of e-commerce and rural areas is an important strategy for realizing common prosperity in rural China. The relationship between rural e-commerce and common wealth is described, and the reasons restricting the development of rural e-commerce are analyzed in light of the development status of rural e-commerce in Pus, Guang’an City, and suggestions for solutions are put forward.
The article firstly proposes to build an “Internet +” special agricultural products e-commerce platform and realize system access, database read/write operation, full-text search, single sign-on, distributed cache and other service functions. Then, with the help of the cluster analysis algorithm and association rule algorithm in the data mining method, we design the recommendation algorithm for agricultural products and propose the prediction method for agricultural products to increase the sales of e-commerce channels. Finally, in view of the problems existing in the production and operation of fruit farmers in Guangxi, the “Internet +” special agricultural products e-commerce platform proposed in this paper is put into the operation of specific agricultural products to analyze the effectiveness of its transaction scale and growth rate.
The agricultural products e-commerce platform’s system architecture is split into four layers: the access layer, front-end, web layer, business layer, and database. Users can browse the information of agricultural products by logging into the platform through public numbers and small programs on the mobile device side, or enter the platform by entering the URL through the browser. The system adopts MySQL as the database management system, which has the advantages of being lightweight, high-performance, open source, and very easy to deploy. Figure 1 illustrates the overall architecture of the agricultural products e-commerce platform.
Overall architecture diagram of the e-commerce platform
The initial intention of the “Internet +” special agricultural products e-commerce platform is to lift the rural poor out of poverty, so in terms of the functions and architecture of the e-commerce platform, it is mainly set up for the sale of agricultural products, agricultural products display, and rural characteristics of the function of tourism. The architecture is also built accordingly [25].
The e-commerce platform’s main function is to display rural agricultural products. Its display can be through mobile devices as well as PC clients. By displaying rural agricultural products during the season, planting bases, and planting processes, it can enhance the quality of local agricultural products and rural style, and gradually differentiate agricultural products. Sales and processing of agricultural products on the e-commerce platform. Based on the operating capacity of the e-commerce industrial park, we will look for cooperative processing enterprises to deep-process the local agricultural products, make exquisite promotional pictures and video packages, and then promote and sell them on the network to obtain a larger profit margin. E-commerce platform for agricultural products exhibition and tourism promotion. The e-commerce platform needs to establish two sales channels: one is to sell fresh agricultural products directly on the platform. The second is to refer to the shooting method of “Li Ziqi” to make the countryside into a niche paradise countryside tourism place. The establishment of an agricultural planting experience garden, traditional processing experience area, and special agricultural products cooking Nongjiale so that tourists can not only physically examination of local agricultural products planting, processing and cooking, but at the same time, through the flow of tourists to increase the sales and popularity of agricultural products.
The functions of the e-commerce platform are divided into two main modules: the front-end functional module and the back-end functional module. The following is the main description of the shopping cart, search login authentication, order system and other functions [26].
Shopping cart function Agricultural products belong to a kind of FMCG, and the consumer’s buying impulse mainly influences their purchase. Therefore, on the website, users add the intention to buy agricultural products to the shopping cart, the need to instantly display the amount of shopping settlement, and timely reminder of the payment. In the case of agricultural products with low inventory, the establishment of tips for reducing low inventory. If the website user has not logged in to the state added to the shopping cart, the system needs to prompt the registration and login, such as “WeChat one-click login”. By simplifying the registration process, visitors are retained and orders are converted. After the user successfully submits the settlement application, the settlement page automatically pops up to add the shipping address column and set up online payment and cash-on-delivery options. It also lists the list of agricultural products to be purchased for the user to check the type, quantity, and amount before payment. After settling successfully, users can access the history of orders by clicking on the My Orders column. Search function of this website During the visit to the e-commerce platform, users can quickly find products of the same category through the agricultural products categorized column on the left side of the webpage and can also search by entering keywords through the search bar, which provides users with an accurate product search function. In the search system, not only should agricultural product types be searchable, but inventory and stocking cycle information should also be displayed simultaneously to facilitate the user’s shopping decision. This requires the search server, the search function of this site, and a connection to the database inventory to facilitate the efficient updating of information on agricultural products and inventory information. Login authentication function Considering that users may browse and log in with different clients, it is necessary to consider the function of user login authentication. The traditional user registration and login need to write the user information to the database and then record the user’s user name and login password through the system, and every time you log in, you need to send an SMS verification code to log in, which is no longer adaptable to the user’s fast login requirements. Therefore, the design not only retains the original user name and password login, but also adds more convenient one-key login functions, such as WeChat authorization one-key login and Alipay authorization one-key login. In the user’s first use of WeChat or Alipay login, you need to ask the user whether to authorize, such as agreeing to call the user’s WeChat and Alipay information to log in without having to fill in the registration information. Order Settlement Function In order to make it more convenient for the user to view the shopping price of agricultural products in the shopping cart, including a single item, select some of them, and the price of all selected agricultural products is automatically settled. Need to meet the user to choose one of the shopping carts of agricultural products in a single or more, or select the shopping cart more than one or more of the whole selection of agricultural products in a single or more. The system can automatically calculate the total price immediately. In order to facilitate customers to pay quickly and improve the shopping experience, the order settlement function page also needs to be available so the user can self-select WeChat payment or Alipay payment. After selection, it can be supported by one key to achieve quick settlement. Order system functions Better improve the “Internet +” characteristics of agricultural products e-commerce platform access and shopping experience, but also need to set the order system in the platform order query, product collection, store attention, new reminders and coupons to receive and redeem the function. The ordering system mainly includes a historical order list, order details, logistics status, order deletion, one-click customer service, and after-sales evaluation.
Cluster analysis is one of the most commonly used algorithms in the big data mining industry. The division principle states that objects in the same category have high similarity, while objects in different categories have high dissimilarity. Cluster analysis can narrow down the problem by algorithmically dividing the objects into
Cluster analysis algorithms have been studied for over half a century, and different clustering algorithms have been proposed, developed, and evolved to enhance the cluster analysis system. The most widely used cluster analysis methods are K-Neans, fuzzy clustering, BIRCH, density clustering, grid-based typical algorithms such as STING algorithm, and so on. Data attributes in cluster analysis can be continuous, discrete, or mixed. Most cluster analysis algorithms use continuous variables to calculate the distance between samples. The commonly used methods for calculating the distance between samples are Euclidean distance, Manhattan distance, and Chebyshev distance.
If
Manhattan distance:
Chebyshev Distance:
Traditional K-means clustering, hierarchical clustering, and density clustering are not suitable for clustering data with mixed attributes. The drawbacks of K-means clustering include its significant impact on noise and outliers, the challenge of selecting merging or splitting points in hierarchical clustering, and the need to determine the parameters in density clustering. The parameters have a very significant effect on the results.
The following introduces an improved cluster analysis method based on BIRCH hierarchical clustering and two-step clustering. The two-step clustering algorithm completes the cluster analysis through two stages: pre-clustering and clustering. The characteristics of two-step clustering are as follows:
It can be applied to the clustering of mixed-attribute data, i.e., it deals with the clustering of discrete and continuous variables at the same time. Determines the number of clusters automatically. Efficiently handles massive datasets.
The association rule recommendation process is shown in Figure 2. The recommendation of association rules is based on the user’s historical transaction dataset, and the association rule algorithm is used to generate a frequent item set, and the association rules are generated according to the frequent item set, which ultimately produces a recommendation relationship. Different association rule algorithms are used in the recommendation process, and the effects of recommendations are different. This paper focuses on the case of unequal importance of items in the transaction data set and proposes to use weighted association rules for recommendation, aiming to improve the possibility of the important items appearing in the association rules.
Flowchart of association rule recommendation
Offline recommendation design
The offline recommendation operation of this system involves integrating all the user’s historical data. The produced recommendation results are periodically counted and stored through Azkaban to ensure that they remain stable for a specific time and period, and are updated according to the algorithm scheduling frequency. [27] The flow of the algorithm is depicted in Fig. 3.
In the design of the offline recommendation module, the main process is to load the data in MongoDB into the trained model, perform statistics and saving, and set the period of updating in order to update the display of the recommendation results. Finally, the calculation results obtained are written back to MongoDB.
Hot recommendation design
The popular recommendation service of this system is based on the rating data of all users, calculates the product with the highest average score, and then sorts them to achieve the popular recommendation. Figure 4 displays the well-known recommendation flowchart.
In the popular recommendation statistics module, the main process is to load the data from MongoDB, followed by the corresponding computational processing through SparkSQL in order to get the sorted list, including the agricultural products with the Top 10 average scores. After the computation is completed, the sorted results are rewritten back to the MongoDB database.
The real-time recommendation design flow is shown in Figure 5.
In the real-time recommendation module, the main process is that Flume collects the user’s behavioural log data from the integrated business service and transfers it to the message buffer queue Kafka for filtering and processing to get the user rating data, and then fuses this rating data with the rating data stored in Redis, and the fused data is loaded into the real-time recommendation algorithmic model and used to calculate the latest The fused data will be loaded into the real-time recommendation algorithm model, which is used to calculate the latest user recommendation results. The calculated recommendation results will be merged with the existing recommendation results in the MongoDB database to complete the update.
Similar products recommendation design
The recommendation of similar agricultural products in this system is different from the above recommendation methods because it is extremely difficult to transform agricultural product labels into rating data. Therefore, content feature vectors of agricultural products are constructed by extracting the label information of agricultural products, and other agricultural products that are similar to a specific agricultural product can be identified by calculating the similarity matrix. This process can be seamlessly integrated into real-time recommendation to achieve content-based similarity recommendation of agricultural products by quickly calculating similar agricultural products using user rating information of the current agricultural product.
Offline recommendation flow chart
Flowchart of popular recommendations
Real-time recommendation flow chart
The content of this section focuses on a brief arithmetic example analysis of the algorithm proposed above to explain the whole process idea mathematically. It is assumed here that there exists some transaction data distribution of agricultural products, and there is such a set of commodities in the database, whose expression is defined as
The minimum support min Sup=0.3 and the minimum confidence min Conf=0.6 are preset, and after the mining process of the Apriori algorithm, the rules in the rule result set are found to have a certain degree of matching with the previous behavioural records of the target user TC. Table 1 displays the transaction database example.
Sample transaction database
| Transaction serial number | Purchase record |
|---|---|
| T1 | ( |
| T2 | ( |
| T3 | ( |
| T4 | ( |
| T5 | ( |
| T6 | ( |
| T7 | ( |
| T8 | ( |
| T9 | ( |
The set of valuable recommendation rules is shown in Table 2.
There is a collection of value recommendation rules
| Rule Number | Support | Confidence | There Is A Value Recommendation Rule |
|---|---|---|---|
| R1 | 0.32 | 0.72 | |
| R2 | 0.32 | 0.72 | |
| R3 | 0.32 | 0.72 | |
| R4 | 0.55 | 0.68 | |
| R5 | 0.32 | 0.72 | |
| R6 | 0.32 | 0.72 | |
| R7 | 0.55 | 0.68 | |
| R8 | 0.32 | 0.72 |
According to the definition of the association rule algorithm, the eight rules in the table have met the minimum support and minimum confidence of the two basic thresholds, so they can be recommended to the target user, according to the corresponding rules in the table after the rules can be seen, the three commodities represented by
The set of rule combinations with scoring information is shown in Table 3. The eight rules in the table can all form recommendations for the target user TC, and the results of the rules in the table are aggregated and classified, in which the score information possessed by each rule is computed, resulting in a combined set of rules with the corresponding score information
A set of rules with scoring information
| Rule classification | The rule of the band | support | confidence |
|---|---|---|---|
| 1 | ( |
0.32 | 0.72 |
| ( |
0.32 | 0.72 | |
| 2 | ( |
0.32 | 0.72 |
| ( |
0.55 | 0.68 | |
| ( |
0.32 | 0.72 | |
| 3 | ( |
0.32 | 0.72 |
| ( |
0.55 | 0.68 | |
| ( |
0.32 | 0.72 |
The calculation of item similarity and rating similarity is shown in Table 4. After the aggregation and classification of the 8 rules can be obtained after the three major rule combination sets, each rule set is the same rule after the piece, which is the recommended rule to distinguish between the results of the rule. Each rule category has the corresponding support for the user of the rule for data support, the use of group decision-making ideas for each combination of the rule members of the full use of information, so that in the premise of not omitting the important rules of the rule under the premise of valuable information effectively dealt with. In this way, the valuable information in the rule set can be processed effectively without omitting important rule information. The table continues to use the three rule combination sets above as its classification basis to determine the similarity between items and scores, which is necessary for calculating the final predicted score values.
The similarity degree of the project and the calculation of the similarity of the score
| Rule classification | There is a value rule for the score | Project similarity | Scoring similarity |
|---|---|---|---|
| 1 | 0.66 | 0.22 | |
| 1.02 | 0.51 | ||
| 2 | 0.66 | 0.22 | |
| 0.66 | 0.18 | ||
| 1.02 | 0.42 | ||
| 3 | 0.66 | 0.54 | |
| 0.66 | 0.22 | ||
| 1.02 | 0.59 |
Finally, the final prediction score value information is carried out, and the prediction score value of the recommendation result is shown in Table 5. From the table, the predicted score values of rule classifications 1, 2, and 3 are 2.65, 2.21, and 3.82 respectively. The experiment demonstrates that the algorithm in this paper achieves the recommendation result by selecting only one suitable item for the target user, which ultimately results in their satisfaction.
The predicted score of the recommended results
| Rule classification | Valuable rules information | Prediction score |
|---|---|---|
| 1 | 2.65 | |
| 2 | 2.21 | |
| 3 | 3.82 | |
In order to make the research sample more representative, and the information obtained more comprehensive, this research scientific selection of points. Through online data access and asking local leaders and cadres to understand the actual situation, the study randomly selected two main planting areas of Shatangju in Guangxi, Wuming and Qinzhou, and selected 2-3 villages around Nanning, Wuming and Qinzhou, respectively, and distributed questionnaires. More than 150 questionnaires were distributed, of which more than 140 were valid. More than 140 questionnaires were distributed, more than 30 fruit co-operatives and cold storages were visited, and several co-operative managers were interviewed. Table 6 displays the survey area and sample distribution.
Investigation area and sample distribution
| Township | Sample Village | Effective Sample Number (Household) | Sample Scale(100%) | Cooperatives |
|---|---|---|---|---|
| Wu Ming | Village A | 25 | 18.52% | 10 |
| Village B | 35 | 25.93% | 5 | |
| Village C | 20 | 14.82% | 15 | |
| Qin Zhou | Village D | 30 | 22.22% | 8 |
| Village E | 25 | 18.52% | 12 | |
| Tot | -- | 140 | 100% | 50 |
The production and business situation of fruit farmers is shown in Table 7. The survey shows that farmers in the fruit planting scale are mainly concentrated in about 3 acres per family, most of the fruit farmers are experienced in planting, and most of the families have more than 8 years of experience in fruit planting. In recent years, fruit farmers generally believe that fruit prices fluctuate greatly, accounting for 89.66 per cent, 96.3 per cent of farmers believe that there are difficulties in fruit sales, and the phenomenon of slow-moving fruit often occurs.
The production and operation of the farmers
| Statistical characteristics | categories | Sample size | Proportion(%) |
|---|---|---|---|
| Area of planting | 3 mu and below | 80 | 57.14% |
| 4-10mu | 55 | 39.29% | |
| Ten mu and above | 5 | 3.57% | |
| Price volatility | general | 15 | 10.35% |
| larger | 120 | 82.76% | |
| large | 10 | 6.9% | |
| Sales difficulty | No difficulty | 5 | 3.7% |
| Occasionally difficulty | 65 | 48.15% | |
| Often difficulty | 65 | 48.15% | |
| Stable fruit sales channel | yes | 45 | 32.14% |
| no | 95 | 67.86% |
As an important part of farmers’ daily production and life, the prosperity of agriculture is related to the economic income of farmers and also affects the goal of achieving common prosperity in rural areas. Therefore, this section discusses the effect of the “Internet+” e-commerce platform designed in this paper on the sales of agricultural products from the dimensions of the education scale and growth rate of special agricultural products in Guangxi and the sales situation.
Transaction scale and growth rate The scale and growth rate of rural e-commerce transactions in Guangxi are shown in Table 8. From the table, it can be seen that the scale of rural e-commerce transactions in Guangxi is increasing. According to relevant data, in 2023, the scale of rural e-commerce transactions in Guangxi exceeded 8.46 billion yuan, a year-on-year increase of 4.62 %. The figure shows that rural e-commerce has become an important support and engine for the development of the rural economy in Guangxi. In addition to the transaction scale, the transaction growth rate is also an important indicator to measure the development of rural e-commerce. It can be seen from the data in the table that in recent years, the growth rate of rural e-commerce transactions in Guangxi has remained high. This data is significantly higher than the national average, indicating that the rural e-commerce market in Guangxi has great potential for development and vitality. Product structure and special agricultural products The structure of rural e-commerce products in Guangxi is shown in Table 9. The table shows the development trend of rural e-commerce in different product categories in Guangxi, with a clear depiction of the product structure and sales changes in rural e-commerce in Guangxi. From 2019 to 2023, the sales of agricultural products, livestock products, forest products, and other categories showed a steady growth trend. Among them, the category of agricultural products is the largest category of sales. In 2023, the sales of agricultural products in Guangxi were 43.387 billion yuan, an increase of 20.94 % year-on-year, reflecting the dominant position of agricultural products in the rural e-commerce market in Guangxi and the continuous growth of consumer demand. This trend not only shows that the market demand for these products is stable but also reflects the progress made by the Guangxi rural e-commerce platform in improving product diversity and meeting the diversified needs of consumers. In addition, although the “other” category has relatively small sales, its continued growth indicates increasing market acceptance of new categories and innovative products.
The scale and growth rate of rural e-commerce in Guangxi
| Year | The scale of the transaction (billion) | Rateyear-to-year growth |
|---|---|---|
| 2016 | 5.22 | 5% |
| 2017 | 8.62 | 10% |
| 2018 | 10.62 | 15% |
| 2019 | 1.28 | 2.76% |
| 2020 | 2.31 | 3.19% |
| 2021 | 4.22 | 4.04% |
| 2022 | 6.59 | 5.14% |
| 2023 | 8.46 | 4.62% |
Guangxi rural e-commerce product structure
| Product category | 2019 annual sales (billion yuan) | 2020 annual sales (billion yuan) | 2021 annual sales (billion yuan) | 2022 annual sales (billion yuan) | 2023 annual sales (billion yuan) |
|---|---|---|---|---|---|
| Agricultural product | (20.76) | (22.22) | (33.73) | (42.69) | (43.38) |
From the perspective of sales channels, with the continuous expansion of Guangxi’s agricultural products’ online access channels, the industrial cluster effect has become prominent. After years of efforts, the development system of agricultural products e-commerce in Guangxi is becoming more and more perfect. First, the demonstration cluster has gradually become a benchmark. Under the demonstration and guidance of the national e-commerce demonstration bases in Nanning High-tech Zone, Guilin E-commerce Valley and Beihai High-tech Zone, the cluster effect of characteristic agricultural products in the three cities is obvious, such as Nanning citrus Guilin Siraitia grosvenorii, taro, horseshoe, Beihai dried squid, dried cuttlefish, dried fish, etc., which are the main local agricultural products and are in the forefront of national agricultural product sales. Second, the emergence of new business entities, a number of farmers’ cooperative organizations, leading agricultural enterprises, the formation of modern agricultural parks, the establishment of influential self-built e-commerce platforms and websites in Guangxi (such as “Yicai Basket”), Guangxi Sugar Network has become a leading enterprise in the domestic sugar industry. Thirdly, the platform effect is noticeable. A large number of farmers, family farms, and agricultural enterprises open online stores through third-party e-commerce platforms such as Taobao and Jingdong. From the perspective of regional brands, the influence of regional agricultural products has gradually expanded. With the help of an e-commerce platform, a batch of agricultural products with regional characteristics, such as Hangzhou jasmine tea, Liuzhou snail powder, Beiliu passion fruit, Baise mango, Fuchuan navel orange, Rong’an kumquat, Pubei guava, Dongxing red girl sweet potato, Lipu taro, Luzhai orange, Lingshan litchi and other brands have increased their popularity and brand value. In 2023, 14 regional brands in Guangxi were selected for the top 100 list of Chinese brand value regional brands (based on geographical indications). The total value of agricultural brands reached 950.07 billion yuan, and the brand value of Hengxian jasmine tea and Baise mango exceeded 10 billion yuan.
These increased data not only intuitively illustrate the popularity of these characteristic agricultural products in the market, but also reflect that rural e-commerce has achieved remarkable success in promoting local characteristic products in Guangxi.
Using the “Internet +” characteristic agricultural product e-commerce platform designed in this paper to invest in specific agricultural product sales operations, it was found that the scale of rural e-commerce transactions in Guangxi showed an increasing trend, and e-commerce transactions increased by 4.62 % year-on-year in 2023. In the analysis of the sales of characteristic agricultural products, it was found that the sales performance of Guangxi characteristic agricultural products shows a significant growth trend. From 2019 to 2023, the increase in agricultural product sales led to economic growth among villagers, which promoted the common prosperity of rural areas to a certain extent.
This paper completes the research content and innovation by designing the architecture and function system of the “Internet +” characteristic agricultural e-commerce platform. Through the trial operation of a city’s characteristic agricultural products, it is proved that the platform has the ability of online operation, which provides a simple and effective method for the development of Guangxi’s e-commerce industry and also provides a reference for other rural areas.