An order quotation method, device, equipment and medium of an e-commerce industry supply chain

Abstract

The application discloses an order quotation method and device for an e-commerce industry supply chain, equipment and a medium, relates to the technical field of power e-commerce intelligent quotation, and comprises the following steps: training a random forest model by using historical webpage data to obtain a trained random forest model; classifying current webpage data by using the trained random forest model to obtain a classification result; dynamically adjusting the crawling strategy of a crawler based on the classification result to obtain a crawler result; calculating a supplier credit value according to the crawler result and supplier information of the e-commerce industry supply chain; obtaining order information of a user, sending the order information to each supplier, so that each supplier returns basic quotation information; calculating a target quotation based on the basic quotation information, the order information and the supplier credit value, and sending the target quotation to the user for order quotation. The application can improve the efficiency and quotation process response speed of order quotation for the e-commerce industry supply chain, and realize diversified and intelligent order quotation for the e-commerce industry supply chain.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power e-commerce intelligent pricing, in particular to an order pricing method and device for an e-commerce industry supply chain, equipment and a medium. BACKGROUND

[0002] At present, the business mode of the power e-commerce industry is changing from the previous "self-operation" business mode to the "self-operation" + "matchmaking" business mode. The traditional procurement power industry platform pricing is based on a single inquiry pricing method, and the pricing path is: user inquiry - sales inquiry - operation processing - procurement inquiry - supplier pricing - procurement pricing - sales pricing - sales pricing - user confirmation. This method has the disadvantages of long chain, low efficiency, complex procedures, etc., and cannot meet the "matchmaking" business mode of multiple users and multiple suppliers. Moreover, the spare parts procurement business of the power industry has long been plagued by long supply cycle problems, and slow response in the pricing process exacerbates this problem.

[0003] From the above, how to improve the efficiency and response speed of the order pricing of the e-commerce industry supply chain and realize diversified and intelligent order pricing of the e-commerce industry supply chain is a problem to be solved in the field. SUMMARY

[0004] Therefore, the purpose of the present application is to provide an order pricing method, device, equipment and medium for an e-commerce industry supply chain, which can improve the efficiency and response speed of the order pricing of the e-commerce industry supply chain and realize diversified and intelligent order pricing of the e-commerce industry supply chain. The specific scheme is as follows:

[0005] In a first aspect, the present application discloses an order pricing method for an e-commerce industry supply chain, applied to an e-commerce industry pricing platform, comprising:

[0006] The historical webpage data for training the model is crawled by a crawler, and the historical webpage data is used to train a random forest model to obtain a trained random forest model;

[0007] The trained random forest model is used to classify current webpage data to obtain a classification result, the crawling strategy of the crawler is dynamically adjusted based on the classification result to obtain a crawler result, and a supplier credit value is calculated based on the crawler result and supplier information of the e-commerce industry supply chain;

[0008] The order information of a user is obtained, and the order information is sent to each supplier so that each supplier returns basic pricing information, a corresponding target price is calculated based on the basic pricing information, the order information and the supplier credit value, and the target price is sent to the user for order pricing.

[0009] Optionally, the historical webpage data for training the model is crawled by a crawler based on a hypertext transfer protocol request.

[0010] The historical webpage data for training the model and related to enterprise credit rating is crawled by a crawler based on a hypertext transfer protocol request.

[0011] The historical webpage data is preprocessed to obtain preprocessed historical webpage data, and the preprocessed historical webpage data is feature extracted to obtain webpage data classification features.

[0012] Optionally, the historical webpage data is preprocessed to obtain preprocessed historical webpage data, and the preprocessed historical webpage data is feature extracted to obtain webpage data classification features, including:

[0013] The historical webpage data is subjected to outlier and error value identification and noise processing, missing value processing, duplicate data processing, and data format standardization processing to obtain preprocessed historical webpage data.

[0014] The preprocessed historical webpage data is feature extracted to obtain webpage data classification features; the features include text content, keyword density, and webpage structure.

[0015] Optionally, the current webpage data is classified using the trained random forest model to obtain a classification result, and the crawling strategy of the crawler is dynamically adjusted based on the classification result to obtain a crawler result, including:

[0016] The current webpage data is classified using the trained random forest model, and the correlation between the current webpage data and credit rating is determined to obtain a classification result and credit rating correlation.

[0017] The crawling strategy is set, and the parameters in the crawling strategy are dynamically adjusted based on the classification result and the credit rating correlation to obtain a crawler result.

[0018] The crawling strategy is monitored and optimized in real time and iteratively updated in real time.

[0019] Optionally, the supplier credit value is calculated according to the crawler result and supplier information of the e-commerce industry supply chain, including:

[0020] Based on the model establishment index selected based on the crawler result, an enterprise credit rating model is established.

[0021] The supplier information and the crawler result are input into the enterprise credit rating model for calculation to obtain a supplier credit value.

[0022] Optionally, the formula for calculating the supplier credit score is as follows:

[0023] ;

[0024] in, , , , , For weights, Let the historical delivery cycle score be the score of the i-th supplier. Let be the supply cycle of the i-th supplier for the j-th product transaction. This is the platform's historical average delivery cycle. Let be the total number of transactions for the i-th supplier on e-commerce industry quotation platforms. Let the historical price score be the number of the i-th supplier. This refers to the historical average supply price of the j-th product on an e-commerce industry pricing platform. Let be the historical supply price of the i-th supplier for the j-th product. Let be the historical after-sales rate of the i-th supplier. This represents the platform's historical average after-sales rate. For the results of the web crawler, This represents the supplier's credit score.

[0025] Optionally, the formula for calculating the target price is:

[0026] ;

[0027] in, This refers to the price coefficient provided by e-commerce industry pricing platforms for supplier quotes. For the i-th supplier targeting the i-th Basic price of each product For shipping costs, The distance between the user and the shipping location, This refers to the price discount based on the number of orders placed by the user. For the number of orders placed by the user, The price subsidy portion is based on the supplier's credit score. As the supplier's credit score, The target price.

[0028] Secondly, this application discloses an order quotation device for the e-commerce industry supply chain, applied to an e-commerce industry quotation platform, comprising:

[0029] The model training module is configured to: crawl historical webpage data for training a model by using a crawler; and train a random forest model by using the historical webpage data, to obtain the trained random forest model.

[0030] The credit value calculation module is configured to: classify current webpage data by using the trained random forest model, to obtain a classification result; dynamically adjust a crawling strategy of the crawler based on the classification result, to obtain a crawler result; and calculate a supplier credit value according to the crawler result and supplier information of an e-commerce industry supply chain.

[0031] The order quotation module is configured to: acquire order information of a user; send the order information to each supplier, so that each supplier returns basic quotation information; calculate corresponding target quotation information based on the basic quotation information, the order information, and the supplier credit value; and send the target quotation information to the user for order quotation.

[0032] In a third aspect, the present application discloses an electronic device, comprising:

[0033] A memory is configured to save a computer program.

[0034] A processor is configured to execute the computer program, to implement the order quotation method for an e-commerce industry supply chain as described above.

[0035] In a fourth aspect, the present application discloses a computer storage medium configured to save a computer program; when the computer program is executed by a processor, the steps of the order quotation method for an e-commerce industry supply chain as described above are implemented.

[0036] It can be seen that the application provides an order quotation method for an e-commerce industry supply chain, comprising the following steps: crawling historical webpage data for training a model through a crawler, training a random forest model by using the historical webpage data, so as to obtain the trained random forest model; classifying current webpage data by using the trained random forest model, so as to obtain a classification result; dynamically adjusting a crawling strategy of the crawler based on the classification result, so as to obtain a crawler result; calculating a supplier credit value according to the crawler result and supplier information of the e-commerce industry supply chain; obtaining order information of a user, and sending the order information to each supplier, so that each supplier returns basic quotation information; calculating a corresponding target quotation based on the basic quotation information, the order information and the supplier credit value, and sending the target quotation to the user for order quotation. The application is applied to an e-commerce industry quotation platform, historical webpage data is crawled by using a crawler, so that a random forest model is trained, so as to dynamically adjust the crawling strategy of the crawler, the calculation of the supplier credit value is more scientific, the topic drift phenomenon generated by a traditional crawler algorithm is reduced, the supplier returns basic quotation information according to the order information of the user, and then the target quotation is calculated based on the supplier credit value, the order information and the basic quotation information, the intelligent generation of the differentiated target quotation for different suppliers and different users is realized, diversified and intelligent order quotation of the e-commerce industry supply chain is realized, and the efficiency of the order quotation of the e-commerce industry supply chain and the response speed of the quotation process are improved. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0038] Figure 1 A flow chart of an order quotation method for an e-commerce industry supply chain disclosed by the present application;

[0039] Figure 2 A flow chart of an order quotation method for an e-commerce industry supply chain disclosed by the present application;

[0040] Figure 3 A specific flow chart of an order quotation disclosed by the present application;

[0041] Figure 4 A structural schematic diagram of an order quotation device for an e-commerce industry supply chain disclosed by the present application;

[0042] Figure 5 A structural diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0044] At present, the business mode of the electric power e-commerce industry is changing from the previous "self-operation" business mode to a "self-operation" + "matchmaking" business mode. The traditional procurement power industry platform quotation is based on a single inquiry quotation method, and the quotation path is: user inquiry-seller inquiry-operation processing-purchasing inquiry-supplier quotation-purchasing pricing-seller pricing-seller quotation-user confirmation. This method has the disadvantages of long chain, low efficiency, and complex procedures, and cannot meet the "matchmaking" business mode of multiple users and multiple suppliers. Moreover, the spare parts procurement business of the power industry has long been plagued by long delivery cycle, and slow response in the quotation process exacerbates this problem. As can be seen from the above, how to improve the efficiency of the e-commerce industry supply chain order quotation and the response speed of the quotation process, and realize diversified and intelligent e-commerce industry supply chain order quotation is a problem to be solved in the field.

[0045] Reference Figure 1 As shown in the drawings, the embodiments of the present application disclose an order quotation method of an e-commerce industry supply chain, which is applied to an e-commerce industry quotation platform, and specifically can include:

[0046] Step S11: crawling historical webpage data for training a model through a crawler, and training a random forest model using the historical webpage data to obtain the trained random forest model.

[0047] In this embodiment, the crawler based on the hypertext transfer protocol request crawls historical webpage data for training a model and related to enterprise credit rating; the historical webpage data is preprocessed to obtain preprocessed historical webpage data, the preprocessed historical webpage data is feature extracted to obtain webpage data classification features, and then the historical webpage data is used to train a random forest model to obtain the trained random forest model. Then, the historical webpage data is subjected to outlier and error value identification and noise processing, missing value processing, duplicate data processing, and data format standardization processing to obtain preprocessed historical webpage data; the preprocessed historical webpage data is feature extracted to obtain webpage data classification features; the features include text content, keyword density, and webpage structure.

[0048] Specifically, a crawler based on HTTP (Hypertext Transfer Protocol) requests is used to collect historical webpage data related to enterprise credit rating. The types of historical webpage data include enterprise basic information, financial information, credit records, operating status, equity changes and investment relationships, intellectual property, human resource information, news and announcements, social media information, market and customer information, compliance and regulatory information, transaction and cooperation information, and geographic location information.

[0049] The preprocessing procedure is as follows: (1) identify and correct outliers and error values in the data by Z-score (Z-standard score) method, and perform noise processing; the calculation formula of Z-score is:

[0050] ;

[0051] wherein X is a specific data point in the data set, is the average value of the data set, is the standard deviation of the data set. If Z=0, the data point is equal to the average value; if Z>0, the data point is higher than the average value; if Z<0, the data point is lower than the average value. If the Z-score of a data point is greater than 2 or 3, the data point is an outlier or an error value; (2) missing value processing: fill in missing values using the K-means++ algorithm (an improved version of the K-means algorithm); (3) duplicate data processing: identify and delete or merge duplicate records; (4) data format standardization: convert data to a unified format, such as date format, currency format, etc. Clean the collected data, remove noise, duplicate content and irrelevant information, and extract text, keywords, links and other key features.

[0052] In this embodiment, features for classification are extracted from the preprocessed webpage data, such as text content, keyword density, webpage structure, etc. The historical webpage data is used to train a random forest model, and the trained random forest model is used to classify the current webpage data and determine its relevance to credit rating.

[0053] Step S12: classifying the current webpage data using the trained random forest model to obtain a classification result, dynamically adjusting the crawling strategy of the crawler based on the classification result to obtain a crawler result, and calculating the supplier credit value according to the crawler result and the supplier information of the e-commerce industry supply chain.

[0054] In this embodiment, after obtaining the crawler result, a model establishment index is selected based on the crawler result, and an enterprise credit rating model is established according to the model establishment index; the supplier information and the crawler result are input into the enterprise credit rating model for calculation to obtain a supplier credit value.

[0055] The calculation formula of the supplier credit value is:

[0056] ;

[0057] Among them, , , , , is a weight number, is a historical supply cycle score of the i th supplier, is a supply cycle of the i th supplier for the j th product transaction, is a platform historical average supply cycle, is a total number of transactions of the i th supplier on the e-commerce industry quotation platform, is a historical price score of the i th supplier, is a historical average supply price of the e-commerce industry quotation platform for the j th product, is a historical supply price of the i th supplier for the j th product, is a historical after-sales rate of the i th supplier, is a platform historical average after-sales rate, is a crawler result, is a supplier credit value.

[0058] In this embodiment, a reasonable index is selected based on the crawler result to establish an enterprise credit rating model, a multi-scale convolutional neural network is used to establish an enterprise credit rating model, and then a supplier credit value is calculated based on supplier information; wherein the supplier information includes historical supply cycle, historical price information and historical after-sales information.

[0059] Step S13: Obtain order information of a user, and send the order information to each supplier, so that each supplier returns basic quotation information, calculates a corresponding target quotation based on the basic quotation information, the order information and the supplier credit value, and sends the target quotation to the user for order quotation.

[0060] In this embodiment, the calculation formula of the target quotation is:

[0061] ;

[0062] Among them, A price coefficient given by an e-commerce industry quotation platform for a supplier quotation, a basic quotation for the i-th supplier for the j-th product, a basic quotation for the i-th supplier for the j-th product, a freight, a distance between a user and a delivery location, a price discount part made according to a user order quantity, a user order quantity, a price subsidy part made according to a supplier credit value, a supplier credit value, a target quotation.

[0063] In this embodiment, a supplier on an e-commerce industry quotation platform will make a quotation for a marked product in user order information, which includes order geographical position information, order demand quantity, etc. Based on the basic quotation information returned by the supplier, the order information of the user and the supplier credit value, the optimal price corresponding to the user, i.e. the target quotation, is calculated.

[0064] In this embodiment, historical webpage data for training a model is crawled by a crawler, the random forest model is trained using the historical webpage data to obtain the trained random forest model, the current webpage data is classified using the trained random forest model to obtain a classification result, the crawling strategy of the crawler is dynamically adjusted based on the classification result to obtain a crawler result, the supplier credit value is calculated according to the crawler result and the supplier information of the e-commerce industry supply chain, the order information of the user is obtained and sent to each supplier so that each supplier returns basic quotation information, the target quotation corresponding to the order information of the user is calculated based on the basic quotation information, the order information and the supplier credit value, and the target quotation is sent to the user for order quotation. This application is applied to an e-commerce industry quotation platform, historical webpage data is crawled by a crawler, thereby training a random forest model, so as to dynamically adjust the crawling strategy of the crawler, which can make the calculation of the supplier credit value more scientific and reduce the topic drift phenomenon generated by the traditional crawler algorithm. The supplier returns the basic quotation information according to the order information of the user, and then calculates the target quotation based on the supplier credit value, the order information and the basic quotation information. Different target quotations are intelligently generated for different suppliers and different users, diversified and intelligent e-commerce industry supply chain order quotation is realized, and the efficiency and response speed of the e-commerce industry supply chain order quotation process are improved.

[0065] Referring to Figure 2 The embodiment of the present application discloses an order quotation method of an e-commerce industry supply chain, which is applied to an e-commerce industry quotation platform and can specifically include:

[0066] Step S21: crawling historical webpage data for training the model by the crawler, training the random forest model by using the historical webpage data to obtain the trained random forest model.

[0067] Step S22: classifying the current webpage data by using the trained random forest model, and judging the correlation between the current webpage data and the credit rating to obtain a classification result and a credit rating correlation, setting a crawling strategy, dynamically adjusting parameters in the crawling strategy based on the classification result and the credit rating correlation to obtain a crawler result, and real-time monitoring and optimizing the crawling strategy and real-time iterative updating.

[0068] In this embodiment, after obtaining the classification result, the PageRank crawler is initialized, and the flow is as follows: constructing a webpage graph, taking the collected webpages as nodes and the links between the webpages as edges to construct a directed graph; calculating the initial PageRank value, using the PageRank algorithm to calculate the initial PageRank value of each webpage based on the link relationship and link quality between the webpages. In order to realize the dynamic adjustment of the crawling strategy, the specific flow is as follows: (1) setting the adjustment rule: based on the classification result of the random forest on the webpage content, a set of rules for adjusting the crawling strategy of the PageRank crawler is set. If the webpage is classified as highly related to the credit rating, the PageRank value of the webpage is increased and the priority of the webpage being crawled is increased; otherwise, the PageRank value of the webpage is decreased and the priority of the webpage being crawled is decreased; (2) real-time updating the PageRank value: in the process of crawling the webpage by the crawler, the classification result of the random forest on the webpage content is obtained in real time, and the PageRank value of the corresponding webpage is updated according to the adjustment rule; (3) dynamically adjusting the crawling behavior of the crawler: according to the updated PageRank value, the crawling behavior of the crawler is dynamically adjusted. The webpage with a high PageRank value is preferentially crawled, and the parameters such as the crawling depth and breadth are adjusted as needed.

[0069] In addition, the crawling strategy can be monitored and optimized in real time and updated iteratively in real time. Among them, the real-time monitoring and optimization are: (1) monitoring the performance of the crawler: regularly monitoring the running state of the crawler, including the crawling speed, success rate, error rate and other indicators; (2) evaluating the classification accuracy: evaluating the accuracy of the random forest model in classifying web page content, and adjusting the model parameters or retraining the model as needed; (3) optimizing and adjusting the rules: according to the actual performance of the crawler and the changes in data, constantly optimizing and adjusting the PageRank value adjustment rules to improve the efficiency and accuracy of the crawler. Iterative update is: (1) update web page data: as time goes by, new web page data will be generated. Regularly update the collected web page data and reprocess and classify them; (2) update the crawling strategy of the PageRank crawler: according to the new web page data and classification results, update the crawling strategy of the PageRank crawler to adapt to the changes in data and changes in business needs.

[0070] Step S23: calculating the supplier credit value according to the crawler results and the supplier information of the e-commerce industry supply chain.

[0071] Step S24: obtaining the order information of the user and sending the order information to each supplier, so that each supplier returns the basic quotation information, calculates the corresponding target quotation based on the basic quotation information, the order information and the supplier credit value, and sends the target quotation to the user for order quotation.

[0072] The specific process of the present application is shown in Figure 3 As shown in the figure, (1) using the classification results of random forest on web page content, dynamically adjusting the crawling strategy of PageRank algorithm crawler to obtain crawler results; (2) using a multi-scale convolutional neural network to establish an enterprise credit rating model, calculating the supplier credit value based on the crawler results and the supplier information of the e-commerce industry supply chain; (3) obtaining the order information of the user, and multiple suppliers returning basic quotation information based on the order information; (4) based on the basic quotation information, the order information of the user and the supplier credit value, and through the platform internal algorithm, the optimal quotation to the user, i.e. the target quotation, is calculated, and finally the target quotation is sent to the user for order quotation.

[0073] The application can solve the problems of long quotation link and low response efficiency in the process of changing the current industry business model from "self-operation" to "self-operation" + "matching" business model. The advantages are as follows: (1) improve the quotation efficiency and improve the response ability of the platform to user demand: improve the crawler algorithm of enterprise credit rating, so that the calculation of supplier credit value is more scientific; (2) intelligently combine supplier quotation and platform internal pricing algorithm to make quotation faster and price more reasonable; (3) intelligently generate differentiated pricing for different suppliers and users, combined with platform material procurement costs, to quote different prices for different users.

[0074] In the embodiment, the historical webpage data for training the model is crawled by the crawler, the random forest model is trained by using the historical webpage data, to obtain the trained random forest model; the current webpage data is classified by using the trained random forest model, to obtain a classification result, the crawling strategy of the crawler is dynamically adjusted based on the classification result, to obtain a crawler result, and the supplier credit value is calculated according to the crawler result and the supplier information of the e-commerce industry supply chain; the order information of a user is obtained, and the order information is sent to each supplier, so that each supplier returns basic quotation information, the corresponding target quotation is calculated based on the basic quotation information, the order information and the supplier credit value, and the target quotation is sent to the user for order quotation. The application is applied to an e-commerce industry quotation platform, historical webpage data is crawled by using a crawler, so that a random forest model is trained, the crawling strategy of the crawler is dynamically adjusted, the calculation of the supplier credit value is more scientific, the topic drift phenomenon generated by the traditional crawler algorithm is reduced, the supplier returns basic quotation information according to the order information of the user, the target quotation is calculated based on the supplier credit value, the order information and the basic quotation information, the differentiated target quotation is intelligently generated for different suppliers and users, diversified and intelligent e-commerce industry supply chain order quotation is realized, and the efficiency and response speed of the e-commerce industry supply chain order quotation are improved.

[0075] Referring to Figure 4 As shown in the figure, the embodiment of the application discloses an order quotation device for an e-commerce industry supply chain, which is applied to an e-commerce industry quotation platform and can specifically include:

[0076] The model training module 11 is configured to crawl historical webpage data for training a model by using a crawler, train a random forest model by using the historical webpage data, and obtain a trained random forest model;

[0077] The credit value calculation module 12 is configured to classify the current webpage data by using the trained random forest model to obtain a classification result, dynamically adjust the crawling strategy of the crawler based on the classification result to obtain a crawler result, and calculate a supplier credit value according to the crawler result and supplier information of an e-commerce industry supply chain.

[0078] The order quotation module 13 is configured to obtain order information of a user, send the order information to each supplier, so that each supplier returns basic quotation information, calculate corresponding target quotation information based on the basic quotation information, the order information and the supplier credit value, and send the target quotation information to the user for order quotation.

[0079] In this embodiment, the historical webpage data for training the model is crawled by the crawler, the random forest model is trained by using the historical webpage data to obtain the trained random forest model, the current webpage data is classified by using the trained random forest model to obtain a classification result, the crawling strategy of the crawler is dynamically adjusted based on the classification result to obtain a crawler result, and a supplier credit value is calculated according to the crawler result and supplier information of an e-commerce industry supply chain. The order information of a user is obtained, and the order information is sent to each supplier, so that each supplier returns basic quotation information. The corresponding target quotation is calculated based on the basic quotation information, the order information and the supplier credit value, and the target quotation is sent to the user for order quotation. The present application is applied to an e-commerce industry quotation platform. The historical webpage data is crawled by the crawler, so that the random forest model is trained, the crawling strategy of the crawler is dynamically adjusted, the calculation of the supplier credit value is more scientific, the topic drift phenomenon generated by the traditional crawler algorithm is reduced, the supplier returns the basic quotation information according to the order information of the user, the target quotation is calculated based on the supplier credit value, the order information and the basic quotation information, the differentiated target quotation is intelligently generated for different suppliers and different users, the diversified and intelligent e-commerce industry supply chain order quotation is realized, and the efficiency and response speed of the e-commerce industry supply chain order quotation are improved.

[0080] In some specific embodiments, the model training module 11 can specifically include:

[0081] The data crawling module is configured to crawl historical webpage data for training the model and related to enterprise credit rating by a crawler based on a hypertext transfer protocol request;

[0082] The preprocessing and feature extraction module is configured to preprocess the historical webpage data to obtain preprocessed historical webpage data, and extract features from the preprocessed historical webpage data to obtain webpage data classification features.

[0083] In some embodiments, the model training module 11 can specifically include:

[0084] a preprocessing module for identifying outliers and error values and performing noise processing, missing value processing, duplicate data processing, and data format standardization processing on the historical webpage data to obtain preprocessed historical webpage data;

[0085] a feature extraction module for extracting features from the preprocessed historical webpage data to obtain webpage data classification features; the features include text content, keyword density, and webpage structure.

[0086] In some embodiments, the credit value calculation module 12 can specifically include:

[0087] a classification module for classifying current webpage data using the trained random forest model and determining the relevance between the current webpage data and the credit rating to obtain a classification result and credit rating relevance;

[0088] a crawler result acquisition module for setting a crawling strategy, dynamically adjusting parameters in the crawling strategy based on the classification result and the credit rating relevance, and obtaining a crawler result;

[0089] a crawling strategy monitoring and updating module for real-time monitoring and optimization of the crawling strategy and real-time iterative updating.

[0090] In some embodiments, the credit value calculation module 12 can specifically include:

[0091] a model establishment module for selecting a model establishment index based on the crawler result and establishing an enterprise credit rating model according to the model establishment index;

[0092] a credit value calculation module for inputting the supplier information and the crawler result into the enterprise credit rating model for calculation to obtain a supplier credit value.

[0093] In some embodiments, the calculation formula of the supplier credit value is:

[0094] ;

[0095] wherein, , , , , is a weight number, is the historical supply cycle score of the i-th supplier, a delivery cycle of the i-th supplier for the j-th product transaction, a platform historical average delivery cycle, a total number of transactions of the i-th supplier on the e-commerce industry quotation platform, a historical price rating score of the i-th supplier, a historical average delivery price of the e-commerce industry quotation platform for the j-th product, a historical delivery price of the i-th supplier for the j-th product, a historical after-sales rate of the i-th supplier, a platform historical average after-sales rate, a crawler result, a supplier credit value.

[0096] In some specific embodiments, the calculation formula of the target quotation is:

[0097] ;

[0098] wherein, a price coefficient given by the e-commerce industry quotation platform for the supplier quotation, a base quotation of the i-th supplier for the j-th product, a shipping fee, a distance between the user and the delivery location, a price discount part made according to the user order quantity, a user order quantity, a price subsidy part made according to the supplier credit value, a supplier credit value, a target quotation.

[0099] Figure 5 A structural schematic diagram of an electronic device provided by an embodiment of the present application. The electronic device 20 can specifically include at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the related steps in the order quotation method of the e-commerce industry supply chain executed by the electronic device disclosed in any of the preceding embodiments.

[0100] ​In this embodiment, the power supply 23 is configured to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 is configured to create a data transmission channel between the electronic device 20 and external devices, and the communication protocol followed by the communication interface 24 can be any communication protocol applicable to the technical solution of the present application, which will not be specifically limited herein; the input / output interface 25 is configured to obtain external input data or output data to the outside, and the specific interface type can be selected according to the specific application needs, which will not be specifically limited herein.

[0101] In addition, the memory 22 as a carrier for storing resources can be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., and the resources stored thereon include an operating system 221, a computer program 222 and data 223, etc., and the storage mode can be temporary storage or permanent storage.

[0102] The operating system 221 is configured to manage and control each hardware device on the electronic device 20 and the computer program 222, so as to realize the operation and processing of the processor 21 on the data 223 in the memory 22, and the operating system 221 can be Windows, Unix, Linux, etc. In addition to the computer program capable of completing the order pricing method of the e-commerce industry supply chain executed by the electronic device 20 disclosed in any one of the preceding embodiments, the computer program 222 can further include a computer program capable of completing other specific work. In addition to the data transmitted by the external device and received by the order pricing device of the e-commerce industry supply chain, the data 223 can also include the data collected by the input / output interface 25 itself and the like.

[0103] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0104] Further, the present application also discloses a computer readable storage medium, wherein the storage medium stores a computer program, and the computer program is loaded and executed by a processor to realize the order pricing method of the e-commerce industry supply chain disclosed in any one of the preceding embodiments.

[0105] Finally, it needs to be pointed out that in this paper, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0106] The above describes in detail the order quotation method, device, equipment and storage medium of the e-commerce industry supply chain provided by the application. The principles and implementation manners of the application are described by applying specific examples in this paper. The above example is only used to help understand the method and core idea of the application. Meanwhile, for those skilled in the art, according to the idea of the application, the specific implementation manner and application range will be changed. In summary, the content of the specification should not be understood as a limitation of the application.

Claims

1. A method for order quotation in the e-commerce industry supply chain, characterized in that, Applications include: Pricing platforms used in the e-commerce industry Historical web page data used for training the model is crawled by a web crawler, and the random forest model is trained using the historical web page data to obtain the trained random forest model. The trained random forest model is used to classify the current web page data to obtain classification results. The crawling strategy of the crawler is dynamically adjusted based on the classification results to obtain crawling results. The supplier credit value is calculated based on the crawling results and supplier information in the e-commerce industry supply chain. Obtain the user's order information and send the order information to each supplier so that each supplier can return basic quotation information. Calculate the corresponding target quotation based on the basic quotation information, the order information, and the supplier's credit value, and send the target quotation to the user for order quotation. The formula for calculating supplier credit score is: ； in, , , , , For weights, Let the historical delivery cycle score be the score of the i-th supplier. Let be the supply cycle of the i-th supplier for the j-th product transaction. This is the platform's historical average delivery cycle. Let be the total number of transactions for the i-th supplier on e-commerce industry quotation platforms. Let the historical price score be the number of the i-th supplier. This refers to the historical average supply price of the j-th product on an e-commerce industry pricing platform. Let be the historical supply price of the i-th supplier for the j-th product. Let be the historical after-sales rate of the i-th supplier. This represents the platform's historical average after-sales rate. For the results of the web crawler, Supplier credit score; The formula for calculating the target price is: ； in, This refers to the price coefficient provided by e-commerce industry pricing platforms for supplier quotes. For the i-th supplier targeting the i-th Basic price of each product For shipping costs, The distance between the user and the shipping location, This refers to the price discount based on the number of orders placed by the user. For the number of orders placed by the user, The price subsidy portion is based on the supplier's credit score. As the supplier's credit score, The target price.

2. The order quotation method for the e-commerce industry supply chain according to claim 1, characterized in that, The process of crawling historical web page data used for training the model includes: The system crawls historical web page data related to corporate credit ratings by using a crawler based on Hypertext Transfer Protocol requests. The historical webpage data is preprocessed to obtain preprocessed historical webpage data, and features are extracted from the preprocessed historical webpage data to obtain features for webpage data classification.

3. The order quotation method for the e-commerce industry supply chain according to claim 2, characterized in that, The process of preprocessing the historical webpage data to obtain preprocessed historical webpage data, and extracting features from the preprocessed historical webpage data to obtain features for webpage data classification, includes: The historical webpage data is subjected to outlier and error value identification, noise processing, missing value processing, duplicate data processing, and data format standardization to obtain the preprocessed historical webpage data. Feature extraction is performed on the preprocessed historical webpage data to obtain features for webpage data classification; the features include text content, keyword density, and webpage structure.

4. The order quotation method for the e-commerce industry supply chain according to claim 1, characterized in that, The process of classifying the current webpage data using the trained random forest model to obtain classification results, and dynamically adjusting the crawling strategy of the crawler based on the classification results to obtain crawling results, includes: The trained random forest model is used to classify the current web page data and determine the correlation between the current web page data and the credit rating, so as to obtain the classification result and the correlation between the credit rating. A crawling strategy is set, and the parameters in the crawling strategy are dynamically adjusted based on the correlation between the classification results and the credit rating to obtain the crawling results; The crawling strategy is monitored, optimized, and iteratively updated in real time.

5. The order quotation method for the e-commerce industry supply chain according to claim 1, characterized in that, The calculation of supplier credit scores based on the crawler results and supplier information from the e-commerce industry supply chain includes: Based on the crawling results, select indicators for model establishment, and establish an enterprise credit rating model based on the indicators for model establishment. The supplier information and the crawler results are input into the enterprise credit rating model for calculation to obtain the supplier credit value.

6. An order quotation device for an e-commerce industry supply chain, characterized in that, Applications include: Pricing platforms used in the e-commerce industry The model training module is used to crawl historical web page data for training the model, and use the historical web page data to train the random forest model to obtain the trained random forest model. The credit score calculation module is used to classify the current web page data using the trained random forest model to obtain classification results, dynamically adjust the crawling strategy of the crawler based on the classification results to obtain crawling results, and calculate the supplier credit score based on the crawling results and supplier information in the e-commerce industry supply chain. The order quotation module is used to obtain the user's order information and send the order information to each supplier so that each supplier can return basic quotation information. Based on the basic quotation information, the order information and the supplier credit value, the module calculates the corresponding target quotation information and sends the target quotation information to the user for order quotation. The formula for calculating supplier credit score is: ； in, , , , , For weights, Let the historical delivery cycle score be the score of the i-th supplier. Let be the supply cycle of the i-th supplier for the j-th product transaction. This is the platform's historical average delivery cycle. Let be the total number of transactions for the i-th supplier on e-commerce industry quotation platforms. Let the historical price score be the number of the i-th supplier. This refers to the historical average supply price of the j-th product on an e-commerce industry pricing platform. Let be the historical supply price of the i-th supplier for the j-th product. Let be the historical after-sales rate of the i-th supplier. This represents the platform's historical average after-sales rate. For the results of the web crawler, Supplier credit score; The formula for calculating the target price is: ； in, This refers to the price coefficient provided by e-commerce industry pricing platforms for supplier quotes. For the i-th supplier targeting the i-th Basic price of each product For shipping costs, The distance between the user and the shipping location, This refers to the price discount based on the number of orders placed by the user. For the number of orders placed by the user, The price subsidy portion is based on the supplier's credit score. As the supplier's credit score, The target price.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the order quoting method for the e-commerce industry supply chain as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store computer programs; wherein, when the computer programs are executed by a processor, they implement the order quotation method for the e-commerce industry supply chain as described in any one of claims 1 to 5.

Images