Agricultural product transaction management method and system of e-commerce platform
Through personalized recommendations and transportation path optimization of agricultural product e-commerce platforms, the problems of inaccurate recommendations and low transportation efficiency of traditional platforms have been solved, and the user experience and service quality have been improved.
Patent Information
- Application Number
- CN202410782669.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-18
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional agricultural product e-commerce platforms have problems such as inaccurate recommendations, low matching, and low inventory management and transportation efficiency, resulting in low user experience and satisfaction.
By evaluating and extracting agricultural product category information, regression analysis is performed in combination with user demand records, and personalized recommendation pages are generated; using decision trees to analyze the storage status and transportation route weather conditions of the product placed by users, and optimize transportation paths and methods; obtain feedback Fuzzy reasoning is used to evaluate the transaction process of data, and optimize the transaction management of e-commerce platforms.
It improves user experience and inventory turnover efficiency, reduces transportation costs and inventory backlog risks, and improves service quality and user satisfaction.
Smart Images

Figure CN118941351A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of transaction management, and in particular to an agricultural product transaction management method and system for an e-commerce platform. Background Art
[0002] With the popularization of Internet technology and the rise of agricultural products e-commerce, consumers have higher and higher requirements for shopping experience and product quality. Therefore, studying how to improve the transaction efficiency and user satisfaction of agricultural products e-commerce platforms through data analysis and personalized recommendations has become a current research hotspot.
[0003] Traditional agricultural product listings often rely on experience and intuition and lack systematic data analysis, resulting in unpopular products taking up inventory space and popular products being out of stock. At the same time, the e-commerce platform's recommendation system does not have a deep enough understanding of user needs, and the recommended content does not match the user's actual needs, affecting user experience and purchase conversion rates. Traditional logistics and transportation planning ignores the impact of weather and warehouse storage conditions on transportation routes and is unable to flexibly select appropriate transportation routes. There is a lack of systematic evaluation and optimization of the transaction process on the e-commerce platform, resulting in problems such as low transaction efficiency and low user satisfaction.
[0004] Therefore, in response to the above problems, there is an urgent need for an agricultural product transaction management method and system for an e-commerce platform. Summary of the invention
[0005] In view of the shortcomings of the prior art, the present invention provides an agricultural product transaction management method and system for an e-commerce platform, which solves the problems of inaccurate recommendations, low matching degree, low inventory management and transportation efficiency, and uneven service quality on traditional agricultural product trading platforms.
[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for managing agricultural product transactions on an e-commerce platform, comprising the following steps: collecting agricultural product category information submitted by suppliers, and determining the agricultural products on the current e-commerce platform by evaluating the agricultural product category information; based on a regression analysis of the user's e-commerce platform record and the demand record of the agricultural products on the shelves in the current quarter, a personalized search recommendation page is generated for the user, and the search recommendation page is updated with the user's order record; statistics on the storage status information of the agricultural products ordered by the user, and a decision tree analysis is performed in combination with the weather conditions in the transportation route to plan and manage the transportation route and mode of the agricultural products ordered by the user; obtaining the user's search recommendation page feedback data and order completion data, and evaluating the agricultural product transaction process of the e-commerce platform by performing fuzzy reasoning on the user's search recommendation page feedback data and order completion data.
[0007] Furthermore, by evaluating the agricultural product category information, the specific analysis of the agricultural products listed on the current e-commerce platform is determined as follows: based on the product selection needs of the e-commerce platform, the agricultural product category information submitted by the supplier is preprocessed and feature extracted to obtain product selection evaluation data for each category of agricultural products, the product selection evaluation data specifically includes the single product profit of each category of agricultural products, the historical sales volume of each category of agricultural products, the pesticide residue detection content of each category of agricultural products, and the supply cycle of each category of agricultural products; weights are assigned to single product profit, historical sales volume, pesticide residue detection content and supply cycle through the priority diagram method, and then weighted synthesis is performed through the logic that single product profit and historical sales volume are proportional to the product selection and listing score, and pesticide residue detection content and supply cycle are inversely proportional to the product selection and listing score to obtain the product selection and listing score of each category of agricultural products; the product selection and listing score of each category of agricultural products is compared with the e-commerce platform product selection and listing benchmark score obtained based on the product selection needs of the e-commerce platform, and the agricultural products whose product selection and listing score exceeds the e-commerce platform product selection and listing benchmark score are marked as the agricultural products listed on the current e-commerce platform.
[0008] Furthermore, the specific analysis steps of assigning weights to single product profitability, historical sales volume, pesticide residue detection content and supply cycle by using the priority diagram method are as follows: based on the product selection needs of the e-commerce platform, the agricultural product selection evaluation data indicators of the current e-commerce platform are obtained, and the agricultural product selection evaluation data indicators of the current e-commerce platform specifically include single product profitability indicators, sales volume indicators, pesticide residue detection content indicators, and supply cycle indicators; through the single product profitability of each category of agricultural products, the historical sales volume of each category of agricultural products, the pesticide residue detection content of each category of agricultural products, the pesticide residue detection content of each category of agricultural products The supply cycle of agricultural products is compared with the single product profit index, sales quantity index, pesticide residue detection content index, and supply cycle index to obtain the profit matching degree, sales matching degree, pesticide residue detection matching degree, and supply cycle matching degree; the profit matching degree, sales matching degree, pesticide residue detection matching degree, and supply cycle matching degree are compared, and then a priority diagram is drawn according to the profit matching degree, sales matching degree, pesticide residue detection matching degree, and supply cycle matching degree to obtain the weight values of single product profit, historical sales quantity, pesticide residue detection content and supply cycle.
[0009] Furthermore, based on the regression analysis of the user's e-commerce platform records and the demand records of the agricultural products on the shelves in the current quarter, the specific analysis steps for personalized generation of the user's search recommendation page are: obtaining the total number of agricultural products displayed on the search recommendation page; extracting the user's e-commerce platform records to obtain the total number of historical search orders for the agricultural products on the shelves; extracting the demand records for the agricultural products on the shelves in the current quarter to obtain the total sales of the agricultural products on the shelves in the current quarter; using linear regression analysis to analyze the total number of historical search orders for agricultural products on the shelves in each category and the total sales of agricultural products on the shelves in each category in the current quarter, to obtain a recommendation score regression model, and to obtain the recommendation score of agricultural products on the shelves in each category; based on the total number of agricultural products displayed on the search recommendation page, select the agricultural products on the shelves category that is equivalent to the total number of agricultural products displayed on the search recommendation page according to the size of the recommendation score and generate it to the search recommendation page, thereby obtaining the user's search recommendation page.
[0010] Furthermore, the storage status information of the agricultural products ordered by users specifically includes the expiring date of the agricultural products ordered by users and the storage quantity of the agricultural products ordered by users in each warehouse where the agricultural products ordered by users are stored; the weather conditions in the transportation route specifically include the amount of rainfall on the way from each warehouse where the agricultural products ordered by users are stored to the place where the users place the order; the expiring date of the agricultural products ordered by users, the storage quantity of the agricultural products ordered by users and the amount of rainfall on the way are used as the input variables of the model, and the transportation path score is used as the output variable of the model to construct a decision tree model.
[0011] Furthermore, the transportation route and mode of agricultural products ordered by users are selected based on the transportation route score output by the decision tree model. When real-time monitoring shows that the weather conditions on the transportation route change, that is, the amount of rainfall on the road increases, the input variables of the decision tree are updated, and the transportation route and mode are selected using the updated transportation path score.
[0012] Furthermore, the specific analysis through fuzzy reasoning on the user's search recommendation page feedback data and order completion data is as follows: obtaining the agricultural product transaction process evaluation of each monitoring period of the e-commerce platform; the user's search recommendation page feedback data specifically includes the search recommendation page conversion rate in each monitoring period, and the order completion data specifically includes the average order completion time in each monitoring period; the search recommendation page conversion rate in each monitoring period and the average order completion time in each monitoring period are divided into different fuzzy sets, and fuzzy rules are established, and the fuzzy rules are specifically as follows: the search recommendation page conversion rate is proportional to the transaction evaluation value, and the average order completion time is inversely proportional to the transaction evaluation value; according to the established fuzzy rules, fuzzy reasoning is performed on the fuzzy sets corresponding to the search recommendation page conversion rate in each monitoring period and the average order completion time in each monitoring period to obtain a fuzzy set of transaction evaluation values, and then the fuzzy set of transaction evaluation values is defuzzified to obtain the transaction evaluation value, and the transaction evaluation value is used to quantify the quality of the agricultural product transaction process of the e-commerce platform.
[0013] An agricultural product transaction management system for an e-commerce platform, which applies the above-mentioned agricultural product transaction management method for an e-commerce platform, includes: an agricultural product selection module, which is used to collect agricultural product category information submitted by suppliers, and determine the agricultural products on the shelves of the current e-commerce platform by evaluating the agricultural product category information; a search recommendation page update module, which is used to generate a personalized search recommendation page for the user based on regression analysis of the user's e-commerce platform record and the demand record of the agricultural products on the shelves in the current quarter, and the search recommendation page is updated with the user's order record; a transportation route planning module, which is used to count the storage status information of the agricultural products ordered by the user, and perform decision tree analysis in combination with the weather conditions in the transportation route, so as to plan and manage the transportation route and transportation method of the agricultural products ordered by the user; a feedback evaluation module, which is used to obtain the user's search recommendation page feedback data and order completion data, and evaluate the agricultural product transaction process of the e-commerce platform by performing fuzzy reasoning on the user's search recommendation page feedback data and order completion data.
[0014] The present invention has the following beneficial effects:
[0015] (1) The agricultural product transaction management method and system of an e-commerce platform can generate a personalized search recommendation page for users by performing regression analysis on the user's e-commerce platform record and the demand record of the agricultural products on the shelves in the current quarter, so as to better meet the needs of users and improve the user experience; statistics are collected on the storage status information of the agricultural products ordered by users, and decision tree analysis is performed in combination with the weather conditions in the transportation route, which is helpful to optimize the inventory management and transportation planning of agricultural products, reduce inventory backlogs and transportation risks, and improve inventory turnover efficiency; by performing decision tree analysis on the weather conditions in the transportation route, the transportation path and mode of the agricultural products ordered by users can be more effectively planned and managed, the transportation efficiency can be improved, the transportation cost can be reduced, and it is also beneficial to ensure the quality and freshness of agricultural products during transportation; the feedback data of the user's search recommendation page and the order completion data are obtained, and the agricultural product transaction process of the e-commerce platform is evaluated through fuzzy reasoning, which is helpful to find problems and room for improvement, timely adjust and improve the service process, and improve service quality and user satisfaction.
[0016] (2) The agricultural product transaction management method and system of the e-commerce platform adopts data processing technology, specifically involving the use of priority graph method to determine weights, linear regression algorithm, decision tree algorithm and fuzzy reasoning, which can realize personalized recommendation, optimized inventory management, intelligent transportation planning, user feedback analysis and effective decision support, thereby improving management efficiency, service quality and user experience, and providing strong support for the development and operation of the e-commerce platform. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] Figure 1 This is a flow chart of an agricultural product transaction management method for an e-commerce platform of the present invention.
[0018] Figure 2 This is a structural diagram of an agricultural product transaction management system of an e-commerce platform of the present invention. DETAILED DESCRIPTION
[0019] The embodiment of the present application solves the problems of inaccurate recommendations, low matching, low inventory management and transportation efficiency, and uneven service quality on traditional agricultural product trading platforms through an agricultural product trading management method and system for an e-commerce platform.
[0020] The overall idea of the problem in the embodiment of this application is as follows:
[0021] Collect agricultural product category information submitted by suppliers, and determine the agricultural products suitable for listing on the current e-commerce platform by evaluating the agricultural product category information to ensure the quality and richness of the products; conduct regression analysis based on the user's e-commerce platform records and the demand records of agricultural products listed in the current quarter, and provide agricultural product recommendations that match user preferences and needs; collect statistics on the storage status information of agricultural products ordered by users, understand the inventory situation, conduct decision tree analysis based on the weather conditions along the transportation route, plan and manage the transportation routes and methods of agricultural products ordered by users, and ensure that the products can be delivered in a timely and safe manner; obtain users' search recommendation page feedback data and order completion data, evaluate the agricultural product transaction process of the e-commerce platform, and identify possible problems and room for improvement.
[0022] See also Figure 1 The embodiment of the present invention provides a technical solution: a method for managing agricultural product transactions on an e-commerce platform, comprising the following steps: collecting agricultural product category information submitted by suppliers, and determining the agricultural products on the shelves of the current e-commerce platform by evaluating the agricultural product category information; based on the regression analysis of the user's e-commerce platform record and the demand record of the agricultural products on the shelves in the current quarter, a personalized search recommendation page is generated for the user, and the search recommendation page is updated with the user's order record; statistics on the storage status information of the agricultural products ordered by the user, and a decision tree analysis is performed in combination with the weather conditions in the transportation route to plan and manage the transportation path and transportation method of the agricultural products ordered by the user; obtaining the user's search recommendation page feedback data and order completion data, and evaluating the agricultural product transaction process of the e-commerce platform by performing fuzzy reasoning on the user's search recommendation page feedback data and order completion data.
[0023] Specifically, by evaluating the agricultural product category information, the specific analysis of the agricultural products listed on the current e-commerce platform is determined as follows: based on the product selection needs of the e-commerce platform, the agricultural product category information submitted by the supplier is preprocessed and feature extracted to obtain the product selection evaluation data of each category of agricultural products. The product selection evaluation data specifically includes the single product profit of each category of agricultural products, the historical sales volume of each category of agricultural products, the pesticide residue detection content of each category of agricultural products, and the supply cycle of each category of agricultural products; weights are assigned to single product profit, historical sales volume, pesticide residue detection content and supply cycle through the priority diagram method. , and then through the logic that single product profit and historical sales volume are proportional to the product selection and listing score, and pesticide residue detection content and supply cycle are inversely proportional to the product selection and listing score, a weighted comprehensive method is performed to obtain the product selection and listing score of each category of agricultural products. The product selection and listing score of each category of agricultural products is used to numerically display the degree of benefit of listing each category of agricultural products; the product selection and listing score of each category of agricultural products is compared with the product selection and listing benchmark score of the e-commerce platform obtained based on the product selection needs of the e-commerce platform, and the agricultural products whose product selection and listing score exceeds the product selection and listing benchmark score of the e-commerce platform are marked as the agricultural products on the current e-commerce platform.
[0024] In this implementation plan, the product selection needs of the e-commerce platform specifically include current market demand analysis, supply chain management needs, agricultural product quality management needs, and seasonal demand analysis. The specific way to obtain product selection needs of the e-commerce platform is: through market research, including surveys on consumer demand and analysis of competitors, to understand potential demand and trends in the market, and to analyze historical sales data and order data to understand which agricultural product categories and sales are good, and which are popular, thereby guiding product selection decisions, or collecting consumer feedback and suggestions, including evaluations, comments, complaints, etc., to understand consumers' satisfaction and demand for existing agricultural products, as well as new categories or products they would like to see.
[0025] Single product profit refers to the profit that each agricultural product can bring in the sales process. It is the net profit after taking into account the sales cost and other expenses. It is calculated through sales data and cost data, including the sales price and cost of each product, and then the net profit is calculated; historical sales volume refers to the total sales volume of a certain category of agricultural products in the past period of time, reflecting the popularity and sales of this category of products in the market, and is obtained through data records of e-commerce platforms or sales systems; pesticide residue detection content refers to the detection content of residual pesticides in agricultural products, which is an important indicator for measuring product safety and quality. The lower the residual pesticide content, the higher the product quality and the smaller the health risk to users. It is obtained through test reports or certificates provided by agricultural product producers or suppliers, or through product testing by third-party organizations; supply cycle refers to the time period from the supplier providing agricultural products to the time when the products can be sold or delivered to customers normally, including the time from picking to putting on the shelves, from ordering to delivery, etc. It is obtained through cooperation and communication with suppliers to understand the picking time, supply chain process and delivery time of agricultural products, so as to determine the supply cycle.
[0026] Specifically, the specific analysis steps for assigning weights to single product profitability, historical sales volume, pesticide residue detection content and supply cycle by using the priority diagram method are as follows: based on the product selection needs of the e-commerce platform, the current e-commerce platform's agricultural product selection evaluation data indicators are obtained, and the current e-commerce platform's agricultural product selection evaluation data indicators specifically include single product profitability indicators, sales volume indicators, pesticide residue detection content indicators, and supply cycle indicators; the single product profitability of each category of agricultural products, the historical sales volume of each category of agricultural products, the pesticide residue detection content of each category of agricultural products, and the supply cycle of each category of agricultural products are compared with the single product profitability indicator, sales volume indicator, pesticide residue detection content indicator, and supply cycle indicator to obtain the profit matching degree: Sales Matching: Pesticide residue detection matching degree: Supply cycle matching: Where j represents the number of each category of agricultural products, j = 1, 2, 3, ..., j ′ , j ′ Indicates the total number of agricultural product categories, PYL j represents the profitability matching degree of the jth agricultural product, PXS j PNY represents the sales matching degree of the jth agricultural product. j PGH represents the matching degree of pesticide residue detection of the jth agricultural product. j represents the matching degree of the supply cycle of the jth agricultural product, α 1j represents the profit of the j-th agricultural product, α 2j represents the historical sales volume of the jth agricultural product, α 3j represents the pesticide residue detection content of the jth agricultural product, α 4j represents the supply cycle of the jth agricultural product, β 1j represents the single product profit index of the jth agricultural product, β 2j represents the sales quantity index of the jth agricultural product, β 3j represents the pesticide residue detection content index of the jth agricultural product, β 4j It represents the supply cycle indicator of the jth type of agricultural product; compares the profit matching, sales matching, pesticide residue detection matching, and supply cycle matching, and then draws a priority diagram according to the profit matching, sales matching, pesticide residue detection matching, and supply cycle matching to obtain the weight values of single product profit, historical sales quantity, pesticide residue detection content, and supply cycle.
[0027] In this implementation plan, the single product profit index is specifically the minimum single product profit requirement for agricultural products on the current e-commerce platform, the sales quantity index is specifically the minimum agricultural product sales situation accepted by the current e-commerce platform, the pesticide residue detection content index is specifically the maximum acceptable agricultural product pesticide residue detection content on the current e-commerce platform, and the supply cycle index is specifically the maximum acceptable agricultural product supply cycle on the current e-commerce platform.
[0028] Profit matching specifically refers to the degree of match between the profit that a certain agricultural product provided by the supplier can bring in the sales process and the overall profit target of the e-commerce platform; sales matching specifically refers to the degree of match between the historical sales of a certain agricultural product provided by the supplier in the market and the sales target of the e-commerce platform; pesticide residue detection matching specifically refers to the degree of match between the pesticide residue detection standards of a certain agricultural product provided by the supplier and the e-commerce platform or relevant regulations; supply cycle matching specifically refers to the degree of match between the supply cycle of a certain agricultural product provided by the supplier and the supply chain management goals of the e-commerce platform; in addition to calculating and obtaining profit matching, sales matching, pesticide residue detection matching, and supply cycle matching through the above formulas, you can also use the reports of market research institutions and industry research analysis to obtain data and trend analysis on profitability, sales trends, pesticide residue detection standards, supply cycles, etc., and obtain relevant matching information from them.
[0029] According to the size of profit matching, sales matching, pesticide residue detection matching, and supply cycle matching, a priority chart is drawn to obtain the weight values of single product profit, historical sales volume, pesticide residue detection content, and supply cycle as shown in Table 1 below:
[0030]
[0031] Table 1
[0032] It should be noted that in Table 1, the matching degree H, matching degree I, matching degree J, and matching degree K correspond one by one to the profit matching degree, sales matching degree, pesticide residue detection matching degree, and supply cycle matching degree in this embodiment. After sorting the profit matching degree, sales matching degree, pesticide residue detection matching degree, and supply cycle matching degree according to the size of the values, they correspond to the matching degree H, matching degree I, matching degree J, and matching degree K in order from large to small, respectively. The weight values in Table 1 are assigned one by one to the weight values of single product profit, historical sales quantity, pesticide residue detection content, and supply cycle.
[0033] In Table 1, the number 0 indicates relatively unimportant, the number 1 indicates relatively more important, and the number 0.5 indicates equally important. For example: the value of matching degree H is 70%, the value of matching degree I is 68%, the value of matching degree J is 65%, and the value of matching degree K is 60%. Then the importance of matching degree H relative to matching degree I, matching degree J, and matching degree K is high; matching degree I is not as important as matching degree H, but is important relative to matching degree J and matching degree K; matching degree J is not as important as matching degree H and matching degree I, but is important relative to matching degree K; matching degree K is not as important as matching degree H, matching degree I, and matching degree J. For example, since the value of matching degree H is greater than the value of matching degree I, the importance value of matching degree H relative to matching degree I is recorded as 1.
[0034] The TTL indicator specifically represents the score of the relative importance of each matching degree. For example, the TTL indicator of the relative importance of matching degree H is specifically obtained as: TTL=0.5+1+1+1=3.5. The weight corresponding to the relative importance of matching degree H is specifically obtained as the ratio of the TTL indicator of the relative importance of matching degree H to the sum of the TTL indicators of the relative importance of matching degree H, the relative importance of matching degree I, the relative importance of matching degree J, and the relative importance of matching degree K.
[0035] Specifically, based on the regression analysis of the user's e-commerce platform records and the demand records of agricultural products on the shelves in the current quarter, the specific analysis steps for personalized generation of the user's search recommendation page are: obtain the total number of agricultural products displayed on the search recommendation page; extract the user's e-commerce platform records to obtain the total number of historical search orders for agricultural products on the shelves; extract the demand records for agricultural products on the shelves in the current quarter to obtain the total sales of agricultural products on the shelves in the current quarter; use linear regression to analyze the total number of historical search orders for agricultural products on the shelves in each category and the total sales of agricultural products on the shelves in each category in the current quarter to obtain a recommendation score regression model and obtain the recommendation score of agricultural products on the shelves in each category; based on the total number of agricultural products displayed on the search recommendation page, select the agricultural products on the shelves category that is equivalent to the total number of agricultural products displayed on the search recommendation page according to the size of the recommendation score and generate it to the search recommendation page, thereby obtaining the user's search recommendation page.
[0036] In this implementation scheme, the recommendation score of each category of agricultural products on the shelves indicates the priority of agricultural products recommended for display on the search recommendation page in a specific category of agricultural products on the shelves. In addition to collecting user feedback and demand information through market research, understanding the market's preferences and demands for different agricultural products, and thus determining the recommendation score, it can also be obtained through linear regression analysis in this implementation scheme. The formula of the specific recommendation score regression model is: i =δ0+δ1*μ 1i +δ2*μ 2i +∈, where i represents the number of agricultural products on the shelf, i=1,2,3,...,i ′ ,i ′ Indicates the total number of agricultural product categories on the shelves, Α i represents the recommendation score of the i-th category of agricultural products on the shelves, μ 1i represents the total number of historical search orders for the i-th category of agricultural products on the shelves, μ 2i represents the total sales volume of the i-th category of agricultural products on the shelves in the current quarter, δ0, δ1, δ2 represent regression coefficients, and ∈ is the error term.
[0037] The search recommendation page is updated along with the user's order record. Specifically, the user's order process is monitored in real time, and the type of agricultural products ordered by the user in real time is marked based on the obtained user order record. At this time, a high score is given to the recommendation score of the agricultural product type. For example, the recommendation score of this type of agricultural product is 60 before the order is placed. After real-time monitoring shows that the user has placed an order for this type of agricultural product, the order gain score is increased by 10 points based on the initial recommendation score, and the recommendation score of this type of agricultural product is 70. The recommendation scores of the agricultural products on the shelves in each category are re-sorted to realize the update of the search recommendation page.
[0038] The total number of historical searches and orders for agricultural products in each category is obtained by querying and analyzing the historical search and order data using data analysis tools or business analysis systems, or directly obtaining the historical search and order data from the backend management system of the e-commerce platform; the total number of sales in the current quarter is obtained by querying and analyzing the total number of sales of agricultural products in the current quarter using the real-time sales data monitoring system or the real-time sales data function of the e-commerce platform.
[0039] By analyzing users' historical behavior data and current quarter's sales data, we can more accurately predict users' needs and preferences, thereby improving the accuracy of recommendations. Personalized recommendation pages display agricultural products that users are interested in, which helps to improve users' shopping experience, increase user satisfaction and stickiness, and accurately recommend products that users may be interested in, which can increase product exposure and click-through rate, thereby increasing sales conversion rate.
[0040] Specifically, the storage status information of the agricultural products ordered by the user specifically includes the expiring date of the agricultural products ordered by the user and the storage quantity of the agricultural products ordered by the user in each warehouse where the agricultural products ordered by the user are stored; the weather conditions in the transportation route specifically include the amount of rainfall on the way from the warehouse where the agricultural products ordered by the user are stored to the place where the user places the order; the expiring date of the agricultural products ordered by the user, the storage quantity of the agricultural products ordered by the user and the amount of rainfall on the way are used as the input variables of the model, and the transportation path score is used as the output variable of the model to construct a decision tree model; the transportation path and mode of the agricultural products ordered by the user are specifically selected based on the size of the transportation path score output by the decision tree model. When it is monitored in real time that the weather conditions in the transportation route change, that is, the amount of rainfall on the way increases, the input variables of the decision tree are updated, and the transportation path and mode of transportation are selected using the updated transportation path score.
[0041] In the present embodiment, the expiring period of the user-ordered agricultural products stored in each warehouse including the user-ordered agricultural products represents the validity period of the user-ordered agricultural products stored in each warehouse, which is used to evaluate the freshness and shelf life of the products in each warehouse, and the information is provided through the warehouse management system or the order system of the e-commerce platform; the storage quantity of the user-ordered agricultural products represents the quantity of the user-ordered agricultural products stored in each warehouse, which is used to evaluate the inventory situation and supply of each warehouse, and is recorded and extracted through the warehouse management system or the order system of the e-commerce platform; the amount of rainfall on the way from each warehouse storing the user-ordered agricultural products to the user order location represents the amount of rainfall on the transportation route from each warehouse to the user order location, which is used to evaluate the weather conditions during transportation, so as to select the most suitable transportation route, and is obtained through the real-time rainfall data provided by the meteorological station or weather forecast system.
[0042] The specific analysis of using the decision tree model to output the transportation path score is as follows: the expiration date of the agricultural products ordered by the user, the storage quantity of the agricultural products ordered by the user, and the amount of rainfall along the way are constructed as a decision data set. After normalizing the data in the decision data set, 70% of the decision data set is randomly divided into a training set, and 30% is randomly divided into a test set. The training set is used to build the model, and the test set is used to verify the model. A decision tree is built, and samples are extracted from the training set through replacement sampling to split, find the best split point, and finally generate a decision tree model, and then use the data of the test set as input for verification. The decision tree model makes judgments along the branches of the tree according to the input real-time data, and finally reaches the leaf node. At the leaf node, the decision tree outputs the transportation path score. Based on the update of real-time data, the output of the decision tree for the transportation path score is continuously updated. The update of real-time data specifically includes the increase in rainfall in the transportation route monitored in real time.
[0043] The transport path score is specifically the score of each path corresponding to each transport mode. The transport modes specifically include air transport, water transport, and land transport. For example, air transport corresponds to two paths, which are recorded as Y1 and Y2 respectively; water transport corresponds to two paths, which are recorded as Y3 and Y4 respectively; and land transport corresponds to two paths, which are recorded as Y5 and Y6 respectively. The decision tree is used to output the values corresponding to Y1, Y2, Y3, Y4, Y5, and Y6, and the transport path and transport mode corresponding to the largest value are taken for transportation.
[0044] Through the decision tree model, combined with factors such as the expiration date of the agricultural products ordered by the user, the storage quantity and the amount of rainfall along the way, the suitability of each transportation route can be evaluated more accurately, so as to select the most appropriate transportation route; according to the real-time monitored changes in the amount of rainfall along the way, the input variables of the decision tree model are updated in time, the scores of each transportation route are re-evaluated, and the transportation route with the largest re-output transportation path score is selected, thereby improving transportation efficiency and being able to promptly discover potential transportation risks, such as slippery roads, reduced visibility, etc., and promptly adjust the transportation route to reduce the risk of transportation accidents.
[0045] Specifically, the specific analysis through fuzzy reasoning on the user's search recommendation page feedback data and order completion data is as follows: obtaining the agricultural product transaction process evaluation of each monitoring period of the e-commerce platform; the user's search recommendation page feedback data specifically includes the search recommendation page conversion rate in each monitoring period, and the order completion data specifically includes the average order completion time in each monitoring period; the search recommendation page conversion rate in each monitoring period and the average order completion time in each monitoring period are divided into different fuzzy sets, and fuzzy rules are established. The fuzzy rules are specifically as follows: the search recommendation page conversion rate is proportional to the transaction evaluation value, and the average order completion time is inversely proportional to the transaction evaluation value; according to the established fuzzy rules, fuzzy reasoning is performed on the fuzzy sets corresponding to the search recommendation page conversion rate in each monitoring period and the average order completion time in each monitoring period to obtain a fuzzy set of transaction evaluation values, and then the fuzzy set of transaction evaluation values is defuzzified to obtain the transaction evaluation value, and the transaction evaluation value is used to quantify the quality of the agricultural product transaction process of the e-commerce platform.
[0046] In this implementation scheme, the specific analysis of fuzzy reasoning based on the established fuzzy rules and the fuzzy sets corresponding to the search recommendation page conversion rate in each monitoring period and the average order completion time in each monitoring period is as follows: the search recommendation page conversion rate in each monitoring period and the average order completion time in each monitoring period are defined as input variables, and are divided into different fuzzy sets, such as "Low", "Med i um", "High" for the search recommendation page conversion rate in each monitoring period, "Short", "Med i um", "Long" for the average order completion time in each monitoring period, and the transaction evaluation value is defined as the output variable, and is divided into different fuzzy sets, such as "Low", "Med i um", "H igh" for the transaction evaluation value. Fuzzy rules are established based on the fact that the search recommendation page conversion rate in each monitoring period is proportional to the transaction evaluation value, and the average order completion time in each monitoring period is inversely proportional to the transaction evaluation value. Examples of fuzzy rules are:
[0047] Mark the search recommendation page conversion rate in each monitoring period as Q, the average order completion time in each monitoring period as G, and the transaction evaluation value as R, then we can define:
[0048] Ru le 1:IF(Q is H i gh)AND(G is Short)THEN(R is H i gh)
[0049] Ru le 2:IF(T is Low)AND(G is Long)THEN(R is Low) ...
[0051] It should be noted that the division of fuzzy sets can be adjusted according to actual conditions. For example, although this embodiment takes three fuzzy sets as examples, in fact, the search recommendation page conversion rate in each monitoring period, the average order completion time definition in each monitoring period, and the transaction evaluation value can be divided into more than three sets to facilitate better evaluation of agricultural product transactions on e-commerce platforms.
[0052] For the judgment of whether the search recommendation page conversion rate is high, medium or low in each monitoring period, and whether the average order completion time is long, medium or short in each monitoring period, thresholds can be set according to actual conditions. For example, when the search recommendation page conversion rate exceeds 70% in the monitoring period, it will be marked as "High"; when the average order completion time in the monitoring period is higher than 14 days, it will be marked as "Long", and so on. I will not go into details here.
[0053] The search recommendation page conversion rate within each monitoring period specifically refers to the ratio of agricultural products displayed through the search recommendation page and ultimately purchased by users within each monitoring period. It is an important indicator for measuring the effectiveness of the search recommendation page, reflecting the degree of influence of the search recommendation page on the user's purchasing behavior. It is obtained through the data statistics function provided by the e-commerce platform or website analysis tool. The average order completion time within each monitoring period refers to the average time from the time a user places an order to purchase agricultural products to the time the order is finally completed within each monitoring period. It is an important indicator for measuring order processing efficiency and customer service level, reflecting the operating efficiency of the platform or logistics. It is obtained by recording the creation time and completion time of each order through the order system of the e-commerce platform, and then calculating the average completion time of all orders in each monitoring period.
[0054] See also Figure 2, an agricultural product transaction management system for an e-commerce platform, applying the above-mentioned agricultural product transaction management method for an e-commerce platform, including: an agricultural product selection module, used to collect agricultural product category information submitted by suppliers, and determine the agricultural products on the current e-commerce platform by evaluating the agricultural product category information; a search recommendation page update module, used to generate a personalized search recommendation page for the user based on regression analysis of the user's e-commerce platform record and the demand record of the agricultural products on the shelves in the current quarter, and the search recommendation page is updated with the user's order record; a transportation route planning module, used to count the storage status information of the agricultural products ordered by the user, and perform decision tree analysis in combination with the weather conditions in the transportation route, and plan and manage the transportation route and transportation method of the agricultural products ordered by the user; a feedback evaluation module, used to obtain the user's search recommendation page feedback data and order completion data, and evaluate the agricultural product transaction process of the e-commerce platform by performing fuzzy reasoning on the user's search recommendation page feedback data and order completion data.
[0055] In summary, this application has at least the following effects:
[0056] By evaluating the category information of agricultural products and determining the agricultural products to be put on the shelves, the quality and diversity of products can be improved to meet the diverse needs of users; regression analysis is performed based on the user's e-commerce platform records and demand records to generate personalized search recommendation pages, improve user experience, and increase user stickiness to the platform; statistics are collected on the storage status information of agricultural products ordered by users, and decision tree analysis is performed in combination with weather conditions on the transportation routes, so that the transportation routes and methods of agricultural products ordered by users can be planned and managed, transaction efficiency can be improved, and inventory backlogs can be reduced; through decision tree analysis and planning and management of transportation routes, logistics distribution can be optimized, operating costs can be reduced, transportation efficiency can be improved, and products can be delivered in a timely and safe manner; obtaining users' search recommendation page feedback data and order completion data, and conducting comprehensive analysis through fuzzy reasoning, problems in the transaction process of the e-commerce platform can be discovered in a timely manner, providing guidance and reference for continuous improvement.
[0057] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods and systems. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0058] The present invention is described with reference to the flowcharts and structure diagrams of the methods and systems according to the embodiments of the present invention. It should be understood that each process and combination of modules in the flowcharts and structure diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 process or processes and structures Figure 1 A device that specifies functionality in a module or modules.
[0059] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 process or processes and structures Figure 1 A function specified in a module or multiple modules.
[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 process or processes and structures Figure 1 Steps to specify functionality in a module or multiple modules.
[0061] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.
[0062] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.
Claims
1. A method for managing agricultural product transactions on an e-commerce platform, characterized in that: The following steps are involved: Collect agricultural product category information submitted by suppliers, and determine the agricultural products that are currently available on the e-commerce platform by evaluating the agricultural product category information; Based on the regression analysis of the user's e-commerce platform records and the demand records of agricultural products on the shelves in the current quarter, a personalized search recommendation page is generated for the user, and the search recommendation page is updated with the user's order records; Collect data on the storage status of agricultural products ordered by users, conduct decision tree analysis based on weather conditions along the transportation routes, and plan and manage the transportation routes and methods of agricultural products ordered by users; Obtain users' search recommendation page feedback data and order completion data, and evaluate the agricultural product transaction process of the e-commerce platform by performing fuzzy reasoning on the users' search recommendation page feedback data and order completion data.
2. The agricultural product transaction management method of an e-commerce platform according to claim 1, characterized in that: By evaluating the information of agricultural product categories, the specific analysis of agricultural products listed on current e-commerce platforms is determined as follows: Based on the product selection needs of the e-commerce platform, the agricultural product category information submitted by the supplier is pre-processed and feature extracted to obtain the product selection evaluation data of each category of agricultural products. The product selection evaluation data specifically includes the single product profit of each category of agricultural products, the historical sales volume of each category of agricultural products, the pesticide residue detection content of each category of agricultural products, and the supply cycle of each category of agricultural products; The priority diagram method is used to assign weights to single product profits, historical sales volume, pesticide residue detection content and supply cycle. Then, through the logic that single product profits and historical sales volume are proportional to the product selection and shelf score, and pesticide residue detection content and supply cycle are inversely proportional to the product selection and shelf score, a weighted comprehensive method is used to obtain the product selection and shelf score of each category of agricultural products. The product selection and listing scores of each category of agricultural products are compared with the e-commerce platform product selection and listing benchmark scores obtained based on the e-commerce platform's product selection needs, and the agricultural products whose product selection and listing scores exceed the e-commerce platform product selection and listing benchmark scores are marked as the agricultural products on the current e-commerce platform.
3. The agricultural product transaction management method of an e-commerce platform according to claim 2, characterized in that: The specific analysis steps for assigning weights to single product profits, historical sales volume, pesticide residue detection content and supply cycle by using the priority diagram method are as follows: Based on the product selection needs of the e-commerce platform, the agricultural product selection evaluation data indicators of the current e-commerce platform are obtained. The agricultural product selection evaluation data indicators of the current e-commerce platform specifically include single product profit indicators, sales quantity indicators, pesticide residue detection content indicators, and supply cycle indicators; By comparing the single product profit of each category of agricultural products, the historical sales volume of each category of agricultural products, the pesticide residue detection content of each category of agricultural products, and the supply cycle of each category of agricultural products with the single product profit index, sales volume index, pesticide residue detection content index, and supply cycle index, we can obtain the profit matching degree, sales matching degree, pesticide residue detection matching degree, and supply cycle matching degree; Compare the profit matching degree, sales matching degree, pesticide residue detection matching degree, and supply cycle matching degree, and then draw a priority diagram based on the profit matching degree, sales matching degree, pesticide residue detection matching degree, and supply cycle matching degree to obtain the weight values of single product profit, historical sales quantity, pesticide residue detection content, and supply cycle.
4. The agricultural product transaction management method of an e-commerce platform according to claim 1, characterized in that: Based on the regression analysis of the user's e-commerce platform records and the demand records of agricultural products on the shelves in the current quarter, the specific analysis steps for generating personalized search recommendation pages for users are as follows: Get the total number of agricultural products displayed on the search recommendation page; Extract the user's e-commerce platform records to obtain the total number of historical search orders for agricultural products on the shelves; extract the demand records for agricultural products on the shelves in the current quarter to obtain the total number of sales of agricultural products on the shelves in the current quarter; The total number of historical search orders for agricultural products in each category and the total number of sales in the current quarter of each category of agricultural products on the shelves are analyzed using linear regression to obtain a recommendation score regression model and obtain the recommendation score of each category of agricultural products on the shelves; Based on the total number of agricultural products displayed on the search recommendation page, the categories of agricultural products on the shelves that are equal to the total number of agricultural products displayed on the search recommendation page are selected according to the size of the recommendation score and generated into the search recommendation page, thereby obtaining the user's search recommendation page.
5. The agricultural product transaction management method of an e-commerce platform according to claim 1, characterized in that: The storage status information of the agricultural products ordered by the user specifically includes the expiration date of the agricultural products ordered by the user and the storage quantity of the agricultural products ordered by the user in each warehouse storing the agricultural products ordered by the user; The weather conditions in the transportation route specifically refer to the amount of rainfall on the way from each warehouse storing the agricultural products ordered by the user to the location where the user places the order; A decision tree model is constructed by taking the expiration date of the agricultural products ordered by users, the storage quantity of the agricultural products ordered by users and the amount of rainfall along the way as the input variables of the model, and the transportation route score as the output variable of the model.
6. The agricultural product transaction management method of an e-commerce platform according to claim 5, characterized in that: The transportation route and mode of agricultural products ordered by users are selected based on the transportation route score output by the decision tree model. When real-time monitoring shows that the weather conditions on the transportation route change, that is, the amount of rainfall on the road increases, the input variables of the decision tree are updated, and the transportation route and mode are selected using the updated transportation path score.
7. The agricultural product transaction management method of an e-commerce platform according to claim 1, characterized in that: The specific analysis of fuzzy reasoning on the user's search recommendation page feedback data and order completion data is as follows: Obtain the agricultural product transaction process evaluation of each monitoring cycle on the e-commerce platform; The user's search recommendation page feedback data specifically includes the search recommendation page conversion rate in each monitoring period, and the order completion data specifically includes the average order completion time in each monitoring period; The search recommendation page conversion rate and the average order completion time in each monitoring period are divided into different fuzzy sets, and fuzzy rules are established. The specific fuzzy rules are as follows: the search recommendation page conversion rate is proportional to the transaction evaluation value, and the average order completion time is inversely proportional to the transaction evaluation value; Fuzzy reasoning is performed based on the established fuzzy rules and the fuzzy sets corresponding to the search recommendation page conversion rate and the average order completion time in each monitoring period to obtain the fuzzy set of transaction evaluation values. Then, the fuzzy set of transaction evaluation values is defuzzified to obtain the transaction evaluation value, which is used to quantify the quality of the agricultural product transaction process on the e-commerce platform.
8. An agricultural product transaction management system for an e-commerce platform, applying an agricultural product transaction management method for an e-commerce platform as claimed in any one of claims 1 to 7, characterized in that: include: The agricultural product selection module is used to collect agricultural product category information submitted by suppliers, and determine the agricultural products that are currently available on the e-commerce platform by evaluating the agricultural product category information; A search recommendation page update module is used to generate a personalized search recommendation page for a user based on a regression analysis of the user's e-commerce platform record and the demand record of the agricultural products on the shelves in the current quarter. The search recommendation page is updated along with the user's order record; The transportation route planning module is used to collect data on the storage status of agricultural products ordered by users, conduct decision tree analysis based on the weather conditions along the transportation route, and plan and manage the transportation routes and methods of agricultural products ordered by users; The feedback evaluation module is used to obtain the user's search recommendation page feedback data and order completion data, and evaluate the agricultural product transaction process of the e-commerce platform by performing fuzzy reasoning on the user's search recommendation page feedback data and order completion data.
