CN118396719A - Agricultural product sales lead intelligent rating and recommending method and system - Google Patents
Agricultural product sales lead intelligent rating and recommending method and system Download PDFInfo
- Publication number
- CN118396719A CN118396719A CN202410726191.3A CN202410726191A CN118396719A CN 118396719 A CN118396719 A CN 118396719A CN 202410726191 A CN202410726191 A CN 202410726191A CN 118396719 A CN118396719 A CN 118396719A
- Authority
- CN
- China
- Prior art keywords
- agricultural product
- sales
- data
- goods
- party
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Recommending goods or services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent grading and recommending method and system for agricultural product sales clues, which relate to the technical field of agricultural product recommendation, and the method comprises the following steps: s1: constructing a supply and demand blockchain, and acquiring sales lead data of agricultural products of a consumer based on the supply and demand blockchain; s2: preprocessing the sales lead data, and calculating sales lead indexes; s3: constructing a sales lead evaluation model, inputting the sales lead index, and outputting the agricultural product sales efficiency of the goods party; s4: matching agricultural product sales levels of the suppliers in the supply-demand blockchain based on the agricultural product sales efficiencies; s5: and matching the agricultural products and the agricultural product suppliers in the supply and demand blockchain according to the agricultural product sales grade of the suppliers. The invention can effectively find and utilize valuable agricultural product sales clues, effectively improve the conversion rate of the agricultural product sales clues, improve the sales efficiency and the profitability, realize the accurate matching of both the supply and demand of agricultural products and promote the healthy development of the agricultural product market.
Description
Technical Field
The invention relates to the technical field of agricultural product recommendation, in particular to an agricultural product sales lead intelligent rating and recommending method and system.
Background
The rating and recommendation of agricultural product sales leads lack scientific basis, traditional agricultural product sales often depends on experience and intuition, a scientific method and a model are lacked to evaluate sales capacity and potential of a cargo party, and potential value of sales lead data cannot be fully mined; this results in greater subjectivity and uncertainty in sales decisions, and it is difficult to accurately meet the needs of the shipper to increase sales efficiency. In addition, existing agricultural product recommendation systems tend to focus on the historical behavior of the shipper, but have strong seasonal characteristics for the agricultural product, resulting in immediate demand changes for the user, while focusing on the historical behavior of the shipper will result in ineffective utilization of sales leads.
The prior chinese patent with publication number CN111144938a discloses a method and system for marketing clue rating suitable for the automotive industry, comprising: collecting network clues from a network, calculating the rating score of each network clue through a rating model algorithm, displaying, sequencing and screening the rating score, and collecting feedback information of the network clues; unified management is carried out on external data sources related to network cue rating, standard data packages and data interfaces are formulated, appointed external data are transmitted to a cue management module, and counting accounting statistics is carried out on the external data; and combining the network clues acquired by the clue management module and the external data acquired by the data interface module, generating a derivative variable list required by the rating model algorithm based on the network clue service scene of the industry, and supplementing feedback data serving as data optimized by the rating model algorithm variable to form a complete clue data closed loop. By adopting the machine learning technology, the clue enters the store and the achievement is guided to effect feedback data, and the accuracy and the effect of clue grading are improved.
The traditional Chinese patent with the authority bulletin number of CN114219558B discloses an intelligent agricultural product recommendation system based on data mining, which comprises an agricultural product data acquisition module, an agricultural product data analysis module, an agricultural product intelligent matching module and an agricultural product intelligent recommendation module; the agricultural product data acquisition module is used for acquiring the initial freshness of the agricultural products, the freshness of the agricultural products at each time point, the purchase quantity of the agricultural products, the goods returning condition and the residual quantity of the agricultural products at each time period, constructing an agricultural product deterioration rate calculation formula for representing each time point according to the acquired initial freshness of the agricultural products and the freshness data of the agricultural products at each time point, and transmitting the acquired data and the deterioration rate calculation formula to the agricultural product data analysis module; according to the invention, the optimal selling time is determined according to the freshness of the agricultural products, so that the freshness of the agricultural products purchased by the customer is higher, a large number of goods returning situations are avoided, and the purchasing experience of the customer is further improved.
The problems presented in the background art exist in the above patents: the agricultural product sales lead is difficult to accurately grade, the potential value of the sales lead data cannot be fully mined, the sales lead of the agricultural product cannot be effectively combined with a cargo party, and the effective conversion rate of the sales lead is limited.
Disclosure of Invention
Aiming at the defects of the prior art, the invention aims to provide an intelligent grading and recommending method and system for agricultural product sales clues, which can construct a sales clue assessment model by calculating different sales clue indexes according to collected purchasing data of agricultural products of a commodity party, effectively discover and utilize valuable agricultural product sales clues, effectively improve the conversion rate of the agricultural product sales clues, improve the sales efficiency and the profitability, realize accurate matching of both supply and demand of agricultural products and promote the healthy development of the agricultural product market.
In order to achieve the above purpose, the present invention provides the following technical solutions:
In one aspect, the invention provides an intelligent grading and recommending method for agricultural product sales cues, which specifically comprises the following steps:
S1: constructing a supply and demand blockchain, and acquiring sales lead data of agricultural products of a consumer based on the supply and demand blockchain;
s2: preprocessing the sales lead data, and calculating sales lead indexes;
s3: constructing a sales lead evaluation model, inputting the sales lead index, and outputting the agricultural product sales efficiency of the goods party;
S4: matching agricultural product sales levels of the suppliers in the supply-demand blockchain based on the agricultural product sales efficiencies;
s5: and matching the agricultural products and the agricultural product suppliers in the supply and demand blockchain according to the agricultural product sales grade of the suppliers.
As a further improvement of the invention, one piece of sales cue data is purchasing data of a goods party and corresponding agricultural product information;
The purchase data is acquired through an internal enterprise resource system;
the agricultural product information includes the kind of agricultural product, the place of production, the quality grade, and the best selling month.
As a further improvement of the invention, the preprocessing comprises data cleaning, data integration and data standardization of sales lead data;
the sales cue indexes comprise agricultural product purchasing frequency indexes of order demand frequency sent by a supplier in a goods demand direction and attention indexes of the supplier and the supplier to agricultural products.
As a further improvement of the present invention, the agricultural product purchase frequency index is determined based on purchase data of a supplier in a demand direction, the purchase data including historical purchase data and plan purchase data; the historical purchase data comprises total purchase times of a goods requiring party for agricultural products and purchase times of each agricultural product; the plan procurement data includes a procurement frequency for each agricultural product in the procurement plan, a number of times the supplier is traversed based on the supply-demand blockchain.
As a further improvement of the present invention, the agricultural product purchasing frequency index is calculated by configuring a mathematical calculation formula, and the calculation formula of the agricultural product purchasing frequency index is as follows:
Wherein, Indicating the frequency of purchasing of the ith agricultural product by the consumer, i=1, 2, 3..n, N indicates the total number of agricultural products purchased by the consumer; representing the total purchasing times of all agricultural products by the goods-requiring party; representing the purchasing times of the i-th agricultural product by the goods requiring party; Representing the purchasing frequency of the ith agricultural product in the purchasing plan by the goods-requiring party; Representing the number of times the shipper traversed the ith agricultural product based on the supply and demand blockchain; A logarithmic function is represented and is used to represent, ，Is a weight coefficient.
As a further improvement of the present invention, the agricultural product supply and sales attention index is comprehensively determined based on the quality grade of the agricultural product and the seasonal characteristic of the agricultural product, and is calculated by configuring a mathematical formula, and the calculation formula of the agricultural product supply and sales attention index is:
Wherein, Indicating the attention degree index of the shipper to the ith agricultural product,Indicating the grade of quality of the i-th agricultural product,The current month of the year is indicated,Representing the best selling month of the ith agricultural product, expressed as the closest best selling month to the current month;， Representing the weight coefficient.
As a further improvement of the present invention, the sales lead evaluation model is built by a random forest algorithm, and the building of the sales lead evaluation model specifically further includes:
setting basic parameters of a random forest, including the number of trees, the maximum depth of the trees, the random sampling proportion of the features, the node splitting number and the minimum number of samples of leaf nodes;
traversing preset parameter combinations by combining a grid search method with k-fold cross verification, and searching for optimal parameter configuration;
Dividing the data set into k subsets by adopting k-fold cross validation, taking one subset as a test set and the rest as a training set each time in turn, repeating k times, and transforming roles of a validation set and the training set each time to perform iterative training and validation;
evaluating the evaluation performance of the sales lead by adopting the area, accuracy, recall rate and F1 fraction under the AUC-ROC curve;
and according to the evaluation result, selecting the model configuration under the optimal parameter configuration to complete the training of the sales cue evaluation model, and deploying and applying the trained model.
As a further improvement of the present invention, the S4 specifically further includes:
s41: based on the sales efficiency of the commodity party for each agricultural product, the total sales efficiency of the commodity party for the agricultural products is calculated according to the following calculation formula:
Wherein, Indicating the total sales efficiency of the commodity to the agricultural products by the commodity-requiring party, N indicating the total number of the commodity purchased by the commodity-requiring party,Represents sales efficiency of the i-th agricultural product by the shipper predicted by the sales lead assessment model,Representing the weight of the goods requiring party corresponding to the sales efficiency of the ith agricultural product;
S42: configuring a first level threshold and a second level threshold, and comparing the first level threshold and the second level threshold with the total value of the sales efficiency of the agricultural products;
If the sales efficiency total value of any one of the goods-requiring parties is not less than the first level threshold, dividing the goods-requiring party level into first-level goods-requiring parties;
if the sales efficiency total value of any one of the goods-requiring parties is smaller than the first level threshold and not smaller than the second level threshold, dividing the goods-requiring party level into second-level goods-requiring parties;
And if the sales efficiency total value of any of the goods-requiring parties is smaller than the second level threshold, classifying the goods-requiring party into a third-level goods-requiring party.
As a further improvement of the present invention, the matching agricultural product specifically includes:
Sorting the sales efficiency of each agricultural product from high to low according to any cargo demand, and recommending the first M agricultural products with the highest sales efficiency for any cargo demand;
the matched agricultural product supplier specifically comprises:
For the first-level goods-requiring party, matching the agricultural product supply party with the same historical purchase through the historical purchase data;
For the second-level commodity-needed party, matching the first-level commodity-needed party by matching the agricultural product supplier similar to the history purchase;
For third-level shippers, including matching means for second-level shippers, and matching agricultural product suppliers that match the shipper's business capabilities and resource limitations.
In a second aspect, the invention provides an agricultural product sales cue intelligent rating and recommending system, which comprises a data acquisition module, a data preprocessing module, a cue index calculation module, a cue evaluation module, a grading module and an agricultural product matching module, wherein:
the data acquisition module is used for acquiring agricultural product sales lead data;
The data preprocessing module is used for preprocessing the collected sales lead data, and comprises data cleaning, data integration and data standardization;
The cue index calculation module is used for calculating sales cue indexes through sales cue data, wherein the sales cue indexes comprise agricultural product purchasing frequency indexes and agricultural product attention indexes;
The cue evaluation module is used for constructing a sales cue evaluation model and outputting the sales efficiency of any goods party to each agricultural product by inputting sales cue indexes;
the grading module is used for grading the goods party into different grades;
The agricultural product matching module is used for matching the needed agricultural products for different grades of goods requiring parties and matching the goods supplying parties of the agricultural products.
In a third aspect, the present invention provides an electronic device comprising a memory for storing instructions; and the processor is used for executing the instructions to enable the equipment to execute the steps of realizing the intelligent grading and recommending method for the agricultural product sales clues.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method for intelligent rating and recommendation of agricultural product sales leads.
The invention has the beneficial effects that:
The method comprises the steps of constructing a sales lead evaluation model through acquired agricultural product sales lead data, calculating an agricultural product purchasing frequency index and an agricultural product attention index based on the agricultural product sales lead data to serve as input of the sales lead evaluation model, reducing training difficulty of the model, increasing training speed and accuracy of the model, effectively finding and utilizing valuable agricultural product sales leads through predicting total sales efficiency of any goods party on each agricultural product, effectively improving conversion rate of the agricultural product sales leads, and improving sales efficiency and profitability of the goods party;
The sales efficiency of each agricultural product is graded by the goods-requiring party, and proper agricultural products and agricultural product suppliers are matched for the goods-requiring parties of different grades, so that the agricultural product recommendation conforming to the preference of the goods-requiring party is provided for the goods-requiring parties of different grades, the purchasing strength of the goods-requiring party is enhanced, the more accurate and efficient matching between the agricultural product suppliers and the agricultural product suppliers is realized, the friction and the cost in the transaction process are reduced, and the healthy development of the agricultural product market is promoted.
Drawings
FIG. 1 is a flow chart of an intelligent grading and recommending method for agricultural product sales cues provided by the invention;
FIG. 2 is a block diagram of an intelligent rating and recommendation system for agricultural product sales cues provided by the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without creative efforts, based on the described embodiments of the present invention fall within the protection scope of the present invention.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", etc. are used merely to indicate relative positional relationships, which may also be changed when the absolute position of the object to be described is changed.
In order to keep the following description of the embodiments of the present invention clear and concise, the detailed description of known functions and known components thereof have been omitted.
Example 1
Referring to fig. 1, an embodiment of an intelligent grading and recommending method for agricultural product sales cues according to the present invention specifically includes the following steps:
S1: constructing a supply and demand blockchain, and acquiring sales lead data of agricultural products of a consumer based on the supply and demand blockchain;
In supply chain management, blockchain technology can provide a decentralized, non-tamperable distributed ledger and database, and a series of data are connected according to time data by a cryptography method to form a chain data structure. The supply and demand blockchain is constructed based on a supplier and a demand party of the agricultural products, and records purchasing data of the demand party, information data of the agricultural products, agricultural product information provided by the supplier and the like;
Wherein, one piece of sales cue data is purchasing data of a goods party and corresponding agricultural product information; the purchase data is acquired through an internal enterprise resource system;
The agricultural product information includes the kinds of agricultural products such as vegetables, fruits, grains, etc.; the agricultural product production place is favorable for analyzing the regional characteristics and market demands of the product; the quality grade of agricultural products, such as a first grade and a second grade, reflects the quality level of the products; the optimal selling month of agricultural products; the agricultural product information can be directly obtained through an agricultural product database;
s2: preprocessing sales lead data, and calculating sales lead indexes;
The preprocessing comprises data cleaning, data integration and data standardization of sales lead data;
Data cleansing includes deleting duplicate data entries by comparing records; avoiding data redundancy in subsequent analysis;
identifying abnormal values in the data by a statistical method, such as data with abnormally high or abnormally low sales price, and performing corresponding deletion, correction or marking;
The data integration is used for ensuring that the goods party and the agricultural products are matched and integrated to form a comprehensive and multidimensional sales lead data set;
the sales cue index includes an agricultural product purchasing frequency index of order demand frequency sent by a supplier in a demand direction, and a degree of interest index of the supplier and the consumer for the agricultural products, wherein:
The agricultural product purchasing frequency index is determined based on purchasing data of a supplier in a goods demand direction, and the purchasing data comprises historical purchasing data and plan purchasing data; the historical purchase data comprises total purchase times of a goods requiring party for agricultural products and purchase times of each agricultural product; the plan purchasing data comprises the purchasing frequency of a commodity needing party for each agricultural product in a purchasing plan and the number of times of traversing the commodity supplying party based on a supply and demand block chain; wherein the number of times the supplier is traversed based on the supply-demand blockchain represents the number of times the supplier looks at different suppliers in the supply-demand blockchain for each agricultural product;
the agricultural product purchasing frequency index is calculated by configuring a mathematical calculation formula, and the agricultural product purchasing frequency index is calculated by the following calculation formula:
Wherein, Indicating the frequency of purchasing of the ith agricultural product by the consumer, i=1, 2, 3..n, N indicates the total number of agricultural products purchased by the consumer; representing the total purchasing times of all agricultural products by the goods-requiring party; representing the purchasing times of the i-th agricultural product by the goods requiring party; Representing the purchasing frequency of the ith agricultural product in the purchasing plan by the goods-requiring party; Representing the number of times the shipper traversed the ith agricultural product based on the supply and demand blockchain; A logarithmic function is represented and is used to represent, ，Setting weight coefficients according to experience;
the agricultural product supply and sales attention index is comprehensively determined based on the quality grade of the agricultural product and the seasonal characteristic of the agricultural product, and is calculated by configuring a mathematical formula, and the calculation formula of the agricultural product supply and sales attention index is as follows:
Wherein, Indicating the attention degree index of the shipper to the ith agricultural product,Indicating the grade of quality of the i-th agricultural product,The current month of the year is indicated,Representing the best selling month of the ith agricultural product, expressed as the closest best selling month to the current month; for example, when the current month is 1 month and the optimal selling month of a certain agricultural product is 12 months, thenRepresenting the 12 months of the last year,The calculation result is 1;， Representing weight coefficients, and setting according to experience;
the quality grade is directly obtained from an agricultural product database and is converted into a numerical value; for example, a certain agricultural product is divided into five grades, namely a first grade, a second grade, a third grade, a fourth grade and a fifth grade, and is converted into a numerical value, wherein the first grade is 5 grades, the second grade is 4 grades, the third grade is 3 grades, the fourth grade is 2 grades, and the fifth grade is 1 grade.
S3: constructing a sales lead evaluation model, inputting the sales lead index, and outputting the agricultural product sales efficiency of the goods party;
establishing the sales lead evaluation model through a random forest algorithm; the random forest algorithm is an integrated learning method, a plurality of decision trees are constructed, each tree is trained on a feature subset and a sample subset which are extracted randomly, the prediction results of the trees are integrated through majority voting to obtain the final purchase probability of each agricultural product, and the random forest algorithm can process high-dimensional data and nonlinear relations and is suitable for prediction tasks in complex scenes.
The building of the sales lead evaluation model specifically further comprises:
Setting basic parameters of a random forest, including the number of trees, the maximum depth of the trees, the random sampling proportion of the features, the node splitting number and the minimum number of samples of leaf nodes; to find an optimal configuration;
Traversing preset parameter combinations by combining a grid search method with k-fold cross verification, and searching for optimal parameter configuration; the process ensures that the model can reach the optimal performance under different parameter combinations, and improves the prediction precision;
dividing a data set into k subsets by adopting k-fold cross validation, taking one subset as a test set and the rest as a training set in turn each time, repeating k times, transforming roles of a validation set and the training set each time, performing iterative training and validation, and evaluating the stability of a model and preventing overfitting by averaging k times of results;
The area under the AUC-ROC curve, the accuracy, the recall rate and the F1 fraction are adopted to evaluate the sales clue evaluation performance, and the closer the AUC-ROC value is to 1, the stronger the capability of the model to distinguish positive and negative samples is;
and according to the evaluation result, selecting the model configuration under the optimal parameter configuration to complete the training of the sales cue evaluation model, and deploying and applying the trained model.
The calculated sales lead index directly reflects the purchasing frequency index of the commodity party to the agricultural product and the attention index of the commodity party to the supplier and the commodity party, compared with the sales data of the commodity party only, the sales lead index can more accurately describe the sales efficiency of the commodity party, so that the model can more accurately predict the sales efficiency of the commodity party to each agricultural product, and the prediction precision is improved.
S4: matching agricultural product sales levels of the suppliers in the supply-demand blockchain based on the agricultural product sales efficiencies;
the step S4 specifically further comprises:
s41: based on the sales efficiency of the commodity party for each agricultural product, the total sales efficiency of the commodity party for the agricultural products is calculated according to the following calculation formula:
Wherein, Indicating the total sales efficiency of the commodity to the agricultural products by the commodity-requiring party, N indicating the total number of the commodity purchased by the commodity-requiring party,Represents sales efficiency of the i-th agricultural product by the shipper predicted by the sales lead assessment model,Representing the weight of the goods requiring party corresponding to the sales efficiency of the ith agricultural product, and setting according to experience;
s42: configuring a first level threshold and a second level threshold, wherein the first level threshold and the second level threshold are set according to experience of a person skilled in the art, and comparing the first level threshold and the second level threshold with the total value of the sales efficiency of the agricultural products;
If the sales efficiency total value of any one of the goods-requiring parties is not less than the first level threshold, dividing the goods-requiring party level into first-level goods-requiring parties;
if the sales efficiency total value of any one of the goods-requiring parties is smaller than the first level threshold and not smaller than the second level threshold, dividing the goods-requiring party level into second-level goods-requiring parties;
And if the sales efficiency total value of any of the goods-requiring parties is smaller than the second level threshold, classifying the goods-requiring party into a third-level goods-requiring party.
By summarizing the sales efficiencies of all the agricultural products by any one of the goods-requiring parties and carrying out weighted summation, the demand trends of the goods-requiring parties for different agricultural products are comprehensively considered, so that an integral goods-requiring party sales efficiency score is formed, the identification of the goods-requiring parties which all show higher sales efficiencies for various agricultural products is facilitated, and the matching precision and efficiency with the suppliers are improved.
S5: matching agricultural products and agricultural product suppliers in the supply and demand blockchain according to the sales grade of the agricultural products of the suppliers;
The matched agricultural product specifically comprises:
Sorting the sales efficiency of each agricultural product from high to low according to any cargo demand, and recommending the first M agricultural products with the highest sales efficiency for any cargo demand;
the matched agricultural product supplier specifically comprises:
For the first-level goods-requiring party, matching the agricultural product supply party with the same historical purchase through the historical purchase data;
For the second-level commodity-needed party, matching the first-level commodity-needed party by matching the agricultural product supplier similar to the history purchase;
For third-level shippers, including matching means for second-level shippers, and matching agricultural product suppliers that match the shipper's business capabilities and resource limitations.
Example 2
Referring to fig. 2, this embodiment is a second embodiment of the present invention; based on the same inventive concept as that of embodiment 1, this embodiment introduces a specific implementation manner of an agricultural product sales cue intelligent rating and recommendation system, which includes a data acquisition module, a data preprocessing module, a cue index calculation module, a cue evaluation module, a grading module, and an agricultural product matching module, wherein:
the data acquisition module is used for acquiring agricultural product sales cue data, wherein the sales cue data comprises purchasing data of a cargo party and corresponding agricultural product information;
The data preprocessing module is used for preprocessing the collected sales lead data, and comprises data cleaning, data integration and data standardization;
The cue index calculation module is used for calculating sales cue indexes through sales cue data, wherein the sales cue indexes comprise agricultural product purchasing frequency indexes and agricultural product attention indexes;
The cue evaluation module is used for constructing a sales cue evaluation model and outputting the sales efficiency of any goods party to each agricultural product by inputting sales cue indexes;
the grading module is used for grading the goods-requiring party into different grades, including a first grade, a second grade and a third grade;
The agricultural product matching module is used for matching the needed agricultural products for different grades of goods requiring parties and matching the goods supplying parties of the agricultural products.
Example 3
Based on the same inventive concept as the other embodiments, this embodiment introduces an electronic device, including a memory and a processor, where the memory is configured to store instructions, and the processor is configured to execute the instructions, so that the computer device performs steps for implementing a method for intelligent rating and recommending of agricultural product sales cues provided by the foregoing embodiments.
Since the electronic device described in this embodiment is an electronic device used for implementing the intelligent grading and recommending method for an agricultural product sales lead in the embodiment of the present application, based on the intelligent grading and recommending method for an agricultural product sales lead described in the embodiment of the present application, those skilled in the art can understand the specific implementation of the electronic device and various modifications thereof, so how to implement the method in the embodiment of the present application for this electronic device will not be described in detail herein. As long as the person skilled in the art implements the electronic device used for the intelligent grading and recommending method for the agricultural product sales clues in the embodiment of the application, the electronic device belongs to the scope of protection of the application.
Example 4
The present embodiment introduces a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the steps provided by the above embodiments for an intelligent rating and recommendation method for agricultural product sales cues, based on the same inventive concept as the other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The invention has the beneficial effects that:
The method comprises the steps of constructing a sales lead evaluation model through acquired agricultural product sales lead data, calculating an agricultural product purchasing frequency index and an agricultural product attention index based on the agricultural product sales lead data, and taking the agricultural product purchasing frequency index and the agricultural product attention index as input of the sales lead evaluation model, reducing training difficulty of the model, increasing training speed and accuracy of the model, effectively finding and utilizing valuable agricultural product sales leads by predicting total sales efficiency of any goods-requiring party on each agricultural product, effectively improving conversion rate of the agricultural product sales leads, and improving sales efficiency and profitability of the goods-requiring party;
The sales efficiency of each agricultural product is graded by the goods-requiring party, and proper agricultural products and agricultural product suppliers are matched for the goods-requiring parties of different grades, so that the agricultural product recommendation conforming to the preference of the goods-requiring party is provided for the goods-requiring parties of different grades, the purchasing strength of the goods-requiring party is enhanced, the more accurate and efficient matching between the agricultural product suppliers and the agricultural product suppliers is realized, the friction and the cost in the transaction process are reduced, and the healthy development of the agricultural product market is promoted.
Furthermore, although exemplary embodiments have been described in the present disclosure, the scope thereof includes any and all embodiments having equivalent elements, modifications, omissions, combinations (e.g., of the various embodiments across), adaptations or alterations as would be appreciated by those in the art. The elements in the claims are to be construed broadly based on the language employed in the claims and are not limited to examples described in the present specification or during the practice of the application, which examples are to be construed as non-exclusive. It is intended, therefore, that the specification and examples be considered as exemplary only, with a true scope and spirit being indicated by the following claims and their full scope of equivalents.
The above description is intended to be illustrative and not restrictive. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. For example, other embodiments may be used by those of ordinary skill in the art upon reading the above description. In addition, in the above detailed description, various features may be grouped together to streamline the invention. This is not to be interpreted as an intention that the disclosed features not being claimed are essential to any claim. Rather, inventive subject matter may lie in less than all features of a particular disclosed embodiment. Thus, the claims are hereby incorporated into the detailed description as examples or embodiments, with each claim standing on its own as a separate embodiment, and it is contemplated that these embodiments may be combined with one another in various combinations or permutations. The scope of the invention should be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled.
The above embodiments are only exemplary embodiments of the present invention and are not intended to limit the present invention, the scope of which is defined by the claims. Various modifications and equivalent arrangements of this invention will occur to those skilled in the art, and are intended to be within the spirit and scope of the invention.
Claims (12)
1. An intelligent grading and recommending method for agricultural product sales clues is characterized in that: the method specifically comprises the following steps:
S1: constructing a supply and demand blockchain, and acquiring sales lead data of agricultural products of a consumer based on the supply and demand blockchain;
s2: preprocessing the sales lead data, and calculating sales lead indexes;
s3: constructing a sales lead evaluation model, inputting the sales lead index, and outputting the agricultural product sales efficiency of the goods party;
S4: matching agricultural product sales levels of the suppliers in the supply-demand blockchain based on the agricultural product sales efficiencies;
s5: and matching the agricultural products and the agricultural product suppliers in the supply and demand blockchain according to the agricultural product sales grade of the suppliers.
2. The agricultural product sales lead intelligent rating and recommendation method according to claim 1, wherein: the sales cue data are purchasing data of a goods party and corresponding agricultural product information;
The purchase data is acquired through an internal enterprise resource system;
the agricultural product information includes the kind of agricultural product, the place of production, the quality grade, and the best selling month.
3. The agricultural product sales lead intelligent rating and recommendation method according to claim 2, wherein: the preprocessing comprises data cleaning, data integration and data standardization of sales lead data;
the sales cue indexes comprise agricultural product purchasing frequency indexes of order demand frequency sent by a supplier in a goods demand direction and attention indexes of the supplier and the supplier to agricultural products.
4. The agricultural product sales lead intelligent rating and recommendation method according to claim 3, wherein: the agricultural product purchasing frequency index is determined based on purchasing data of a supplier in a goods demand direction, and the purchasing data comprises historical purchasing data and plan purchasing data; the historical purchase data comprises total purchase times of a goods requiring party for agricultural products and purchase times of each agricultural product; the plan procurement data includes a procurement frequency for each agricultural product in the procurement plan, a number of times the supplier is traversed based on the supply-demand blockchain.
5. The agricultural product sales lead intelligent rating and recommendation method according to claim 4, wherein: the agricultural product purchasing frequency index is calculated by configuring a mathematical calculation formula, and the agricultural product purchasing frequency index is calculated by the following calculation formula:
；
Wherein, Indicating the frequency of purchasing of the ith agricultural product by the consumer, i=1, 2, 3..n, N indicates the total number of agricultural products purchased by the consumer; representing the total purchasing times of all agricultural products by the goods-requiring party; representing the purchasing times of the i-th agricultural product by the goods requiring party; Representing the purchasing frequency of the ith agricultural product in the purchasing plan by the goods-requiring party; Representing the number of times the shipper traversed the ith agricultural product based on the supply and demand blockchain; A logarithmic function is represented and is used to represent, ，Is a weight coefficient.
6. The agricultural product sales lead intelligent rating and recommendation method according to claim 5, wherein: the agricultural product supply and sales attention index is comprehensively determined based on the quality grade of the agricultural product and the seasonal characteristic of the agricultural product, and is calculated by configuring a mathematical formula, and the calculation formula of the agricultural product supply and sales attention index is as follows:
；
Wherein, Indicating the attention degree index of the shipper to the ith agricultural product,Indicating the grade of quality of the i-th agricultural product,The current month of the year is indicated,Representing the best selling month of the ith agricultural product, expressed as the closest best selling month to the current month;， Representing the weight coefficient.
7. The agricultural product sales lead intelligent rating and recommendation method according to claim 6, wherein: the sales cue evaluation model is established through a random forest algorithm, and the establishment of the sales cue evaluation model specifically further comprises the following steps:
setting basic parameters of a random forest, including the number of trees, the maximum depth of the trees, the random sampling proportion of the features, the node splitting number and the minimum number of samples of leaf nodes;
traversing preset parameter combinations by combining a grid search method with k-fold cross verification, and searching for optimal parameter configuration;
Dividing the data set into k subsets by adopting k-fold cross validation, taking one subset as a test set and the rest as a training set each time in turn, repeating k times, and transforming roles of a validation set and the training set each time to perform iterative training and validation;
evaluating the evaluation performance of the sales lead by adopting the area, accuracy, recall rate and F1 fraction under the AUC-ROC curve;
and according to the evaluation result, selecting the model configuration under the optimal parameter configuration to complete the training of the sales cue evaluation model, and deploying and applying the trained model.
8. The agricultural product sales lead intelligent rating and recommendation method according to claim 7, wherein: the step S4 specifically further comprises:
s41: based on the sales efficiency of the commodity party for each agricultural product, the total sales efficiency of the commodity party for the agricultural products is calculated according to the following calculation formula:
；
Wherein, Indicating the total sales efficiency of the commodity to the agricultural products by the commodity-requiring party, N indicating the total number of the commodity purchased by the commodity-requiring party,Represents sales efficiency of the i-th agricultural product by the shipper predicted by the sales lead assessment model,Representing the weight of the goods requiring party corresponding to the sales efficiency of the ith agricultural product;
S42: configuring a first level threshold and a second level threshold, and comparing the first level threshold and the second level threshold with the total value of the sales efficiency of the agricultural products;
If the sales efficiency total value of any one of the goods-requiring parties is not less than the first level threshold, dividing the goods-requiring party level into first-level goods-requiring parties;
if the sales efficiency total value of any one of the goods-requiring parties is smaller than the first level threshold and not smaller than the second level threshold, dividing the goods-requiring party level into second-level goods-requiring parties;
And if the sales efficiency total value of any of the goods-requiring parties is smaller than the second level threshold, classifying the goods-requiring party into a third-level goods-requiring party.
9. The agricultural product sales lead intelligent rating and recommendation method according to claim 8, wherein: the matched agricultural product specifically comprises:
Sorting the sales efficiency of each agricultural product from high to low according to any cargo demand, and recommending the first M agricultural products with the highest sales efficiency for any cargo demand;
the matched agricultural product supplier specifically comprises:
For the first-level goods-requiring party, matching the agricultural product supply party with the same historical purchase through the historical purchase data;
For the second-level commodity-needed party, matching the first-level commodity-needed party by matching the agricultural product supplier similar to the history purchase;
For third-level shippers, including matching means for second-level shippers, and matching agricultural product suppliers that match the shipper's business capabilities and resource limitations.
10. An intelligent grading and recommending system for agricultural product sales clues, which is realized by the intelligent grading and recommending method for agricultural product sales clues according to any one of claims 1-9, and is characterized in that: the system comprises a data acquisition module, a data preprocessing module, a clue index calculation module, a clue evaluation module, a grading module and an agricultural product matching module, wherein:
the data acquisition module is used for acquiring agricultural product sales lead data;
The data preprocessing module is used for preprocessing the collected sales lead data, and comprises data cleaning, data integration and data standardization;
The cue index calculation module is used for calculating sales cue indexes through sales cue data, wherein the sales cue indexes comprise agricultural product purchasing frequency indexes and agricultural product attention indexes;
The cue evaluation module is used for constructing a sales cue evaluation model and outputting the sales efficiency of any goods party to each agricultural product by inputting sales cue indexes;
the grading module is used for grading the goods party into different grades;
The agricultural product matching module is used for matching the needed agricultural products for different grades of goods requiring parties and matching the goods supplying parties of the agricultural products.
11. An electronic device, comprising: a memory for storing instructions; a processor for executing the instructions to cause the device to perform steps for implementing a method for intelligent rating and recommendation of agricultural product sales cues according to any one of claims 1-9.
12. A computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of a method for intelligent rating and recommendation of agricultural product sales cues according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410726191.3A CN118396719A (en) | 2024-06-06 | 2024-06-06 | Agricultural product sales lead intelligent rating and recommending method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410726191.3A CN118396719A (en) | 2024-06-06 | 2024-06-06 | Agricultural product sales lead intelligent rating and recommending method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118396719A true CN118396719A (en) | 2024-07-26 |
Family
ID=91987941
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410726191.3A Pending CN118396719A (en) | 2024-06-06 | 2024-06-06 | Agricultural product sales lead intelligent rating and recommending method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118396719A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119204862A (en) * | 2024-11-27 | 2024-12-27 | 上海银行股份有限公司 | A method for mining potential customers |
-
2024
- 2024-06-06 CN CN202410726191.3A patent/CN118396719A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119204862A (en) * | 2024-11-27 | 2024-12-27 | 上海银行股份有限公司 | A method for mining potential customers |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109063945B (en) | Value evaluation system-based 360-degree customer portrait construction method for electricity selling company | |
| Sensini | Selection of Determinants in Corporate Financial Distress | |
| CN113051291A (en) | Work order information processing method, device, equipment and storage medium | |
| CN110956273A (en) | Credit scoring method and system integrating multiple machine learning models | |
| CN114741592B (en) | Product recommendation method, device and medium based on multi-model fusion | |
| Chen et al. | Extracting performance rules of suppliers in the manufacturing industry: An empirical study | |
| CN118691233B (en) | A digital supply chain information management platform and method | |
| US20170124459A1 (en) | Method and system for generating predictive models for scoring and prioritizing leads | |
| CN116523301A (en) | System for predicting risk rating based on big data of electronic commerce | |
| CN114118793B (en) | A local exchange risk warning method, device and equipment | |
| CN116385151A (en) | Method and computing device for risk rating prediction based on big data | |
| Hu | Predicting and improving invoice-to-cash collection through machine learning | |
| CN117973846A (en) | Enterprise risk prediction method and system based on industrial chain | |
| CN118396719A (en) | Agricultural product sales lead intelligent rating and recommending method and system | |
| CN116384751A (en) | Method and computing device for carrying out standardized risk index and risk rating prediction | |
| Pham et al. | Predictive analysis of the supply chain management using Machine learning approaches: Review and Taxonomy | |
| CN113379211A (en) | Block chain-based logistics information platform default risk management and control system and method | |
| Petersone et al. | A data-driven framework for identifying investment opportunities in private equity | |
| CN113379212A (en) | Block chain-based logistics information platform default risk assessment method, device, equipment and medium | |
| CN119338426A (en) | Intelligent talent management method and system for chain enterprises | |
| CN118537136A (en) | Product recommendation method and device | |
| Alizadeh et al. | An OWA-powered dynamic customer churn modeling in the banking industry based on customer behavioral vectors | |
| CN118586969A (en) | A business opportunity stage evaluation method, device and medium based on C139 model | |
| CN117114812A (en) | A method and device for recommending financial products for enterprises | |
| Dewi et al. | Modeling salesperson performance based on sales data clustering |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |