Order quotation method and device for e-commerce industry supply chain, equipment and medium

Abstract

The invention discloses an order quotation method and device for an e-commerce industry supply chain, equipment and a medium, and relates to the technical field of power e-commerce intelligent quotation, and the method comprises the steps: training a random forest model through employing historical webpage data, and obtaining a trained random forest model; classifying the current webpage data by using the trained random forest model to obtain a classification result, dynamically adjusting a crawling strategy of a crawler based on the classification result to obtain a crawler result, and calculating a supplier credit value according to the crawler result and supplier information of an e-commerce industry supply chain; and obtaining order information of the 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. According to the invention, the efficiency of e-commerce industry supply chain order quotation and the response speed of the quotation process can be improved, and diversified and intelligent e-commerce industry supply chain order quotation is realized.

Description

Technical Field

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

[0002] At present, the business model of the electric power e-commerce industry is shifting from the previous "self-operated" business model to the "self-operated" + "matchmaking" business model. The traditional procurement platform quotation of the electric power industry is based on a quotation method of one order and one inquiry. The quotation path is: user inquiry-sales inquiry-operation processing-purchase inquiry-supplier quotation-purchase pricing-sales pricing-sales quotation-user confirmation. This method has the disadvantages of long links, low efficiency, and complicated procedures. It cannot meet the "matching" business model of multiple users and multiple suppliers. In addition, the spare parts procurement business of the power industry itself has long had the problem of long supply cycle, and the slow response of the quotation process has exacerbated this problem.

[0003] From the above, it can be seen that how to improve the efficiency of 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 this field. Summary of the invention

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

[0005] In the first aspect, the present application discloses an order quotation method for the supply chain of the e-commerce industry, which is applied to the quotation platform of the e-commerce industry, including:

[0006] Crawling historical web page data used for training the model through a crawler, and using the historical web page data to train the random forest model to obtain the trained random forest model;

[0007] Using the trained random forest model to classify the current web page data 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;

[0008] Obtain the user's order information and send the order information to each supplier so that each supplier returns basic quotation information, calculates the corresponding target quotation based on the basic quotation information, the order information and the supplier's credit value, and sends the target quotation to the user for order quotation.

[0009] Optionally, crawling historical web page data for training the model by crawling includes:

[0010] Crawling historical web page data related to corporate credit rating and used for training models through crawlers based on hypertext transfer protocol requests;

[0011] The historical web page data is preprocessed to obtain the preprocessed historical web page data, and feature extraction is performed on the preprocessed historical web page data to obtain features for web page data classification.

[0012] Optionally, the preprocessing of the historical web page data to obtain the preprocessed historical web page data, and feature extraction of the preprocessed historical web page data to obtain features for web page data classification include:

[0013] Performing abnormal value and error value identification and noise processing, missing value processing, duplicate data processing, and data format standardization processing on the historical web page data to obtain the pre-processed historical web page data;

[0014] Feature extraction is performed on the preprocessed historical web page data to obtain features for web page data classification; the features include text content, keyword density and web page structure.

[0015] Optionally, the using the trained random forest model to classify the current web page data to obtain a classification result, and dynamically adjusting the crawling strategy of the crawler based on the classification result to obtain a crawler result, includes:

[0016] Using the trained random forest model to classify the current web page data, and determining the correlation between the current web page data and the credit rating, so as to obtain the classification result and the credit rating correlation;

[0017] Setting a crawling strategy, and dynamically adjusting parameters in the crawling strategy based on the classification result and the credit rating correlation to obtain a crawling result;

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

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

[0020] Selecting model establishment indicators based on the crawler results, and establishing a corporate credit rating model according to the model establishment indicators;

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

[0022] Optionally, the calculation formula of the supplier credit value is:

[0023] ;

[0024] in, , , , , is the weight number, is the historical supply cycle score of the i-th supplier, is the supply cycle of the i-th supplier for the j-th product transaction, is the historical average supply cycle of the platform, is the total number of transactions of the i-th supplier on the e-commerce industry quotation platform, is the historical price score of the i-th supplier, is the historical average supply price of the jth product on the e-commerce industry quotation platform. is the historical supply price of the i-th supplier for the j-th product, is the historical after-sales rate of the i-th supplier, is the historical average after-sales rate of the platform, For crawler results, The supplier's credit value.

[0025] Optionally, the target price is calculated as follows:

[0026] ;

[0027] in, The price coefficient given by the e-commerce industry quotation platform for suppliers' quotations. For the i-th supplier Basic quotation for each product. For shipping, is the distance between the user and the place of shipment, The price discount is based on the order quantity of the user. The quantity of the order placed by the user. This is the price subsidy based on the supplier's credit value. is the supplier's credit value, Quote for the target.

[0028] In the second aspect, the present application discloses an order quotation device for the supply chain of the e-commerce industry, which is applied to the quotation platform of the e-commerce industry, including:

[0029] A model training module, used to crawl historical web page data used for training the model through a crawler, and train the random forest model using the historical web page data to obtain the trained random forest model;

[0030] A credit value calculation module, used to classify the current web page data 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 the supplier credit value based on the crawler result and the supplier information of the e-commerce industry supply chain;

[0031] 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 returns basic quotation information, calculates the corresponding target quotation information based on the basic quotation information, the order information and the supplier's credit value, and sends the target quotation information to the user for order quotation.

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

[0033] Memory, used to store computer programs;

[0034] The processor is used to execute the computer program to implement the order quotation method for the supply chain of the e-commerce industry.

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

[0036] It can be seen that the present application provides an order quotation method for the supply chain of the e-commerce industry, including crawling historical web page data used to train a model through a crawler, using the historical web page data to train a random forest model to obtain the trained random forest model; using the trained random forest model to classify current web page data to obtain classification results, dynamically adjusting the crawling strategy of the crawler based on the classification results to obtain crawler results, and calculating the supplier credit value based on the crawler results and supplier information of the e-commerce industry supply chain; obtaining the user's order information, and sending the order information to each supplier so that each supplier returns basic quotation information, calculating the 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. This application is applied to the quotation platform of the e-commerce industry. A crawler is used to crawl historical web page data to train a random forest model so as to dynamically adjust the crawling strategy of the crawler. This can make the calculation of the supplier's credit value more scientific and reduce the topic drift phenomenon caused by the traditional crawler algorithm. The supplier returns basic quotation information based on the user's order information, and then calculates the target quotation based on the supplier's credit value, order information and basic quotation information. Differentiated target quotations are intelligently generated for different suppliers and different users, realizing diversified and intelligent e-commerce industry supply chain order quotations, and improving the efficiency of e-commerce industry supply chain order quotations and the response speed of the quotation process. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0038] Figure 1 This is a flow chart of an order quotation method for an e-commerce industry supply chain disclosed in this application;

[0039] Figure 2 This is a flow chart of an order quotation method for an e-commerce industry supply chain disclosed in this application;

[0040] Figure 3 A specific flow chart of an order quotation disclosed in this application;

[0041] Figure 4 This is a schematic diagram of the structure of an order quotation device for the supply chain of the e-commerce industry disclosed in this application;

[0042] Figure 5 A structural diagram of an electronic device provided for this application. DETAILED DESCRIPTION

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0044] At present, the business model of the electric power e-commerce industry is shifting from the previous "self-operated" business model to the "self-operated" + "matching" business model. The traditional power industry procurement platform quotation is based on a one-order one-inquiry quotation method, and the quotation path is: user inquiry-sales inquiry-operation processing-purchase inquiry-supplier quotation-purchase pricing-sales pricing-sales quotation-user confirmation. This method has the disadvantages of long links, low efficiency, and complicated procedures. It cannot meet the "matching" business model of multiple users and multiple suppliers. The spare parts procurement business of the power industry itself has long had the problem of long supply cycle, and the slow response of the quotation process has exacerbated this problem. From the above, it can be seen that how to improve the efficiency of 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 this field.

[0045] See also Figure 1 As shown, the embodiment of the present invention discloses an order quotation method for the supply chain of the e-commerce industry, which is applied to the quotation platform of the e-commerce industry and may specifically include:

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

[0047] In this embodiment, historical web page data related to the training model and corporate credit rating is crawled by a crawler based on a hypertext transfer protocol request; the historical web page data is preprocessed to obtain the preprocessed historical web page data, and feature extraction is performed on the preprocessed historical web page data to obtain features for web page data classification, and then the random forest model is trained using the historical web page data to obtain the trained random forest model. Then, the historical web page data is subjected to abnormal value and error value identification and noise processing, missing value processing, duplicate data processing, and data format standardization processing to obtain the preprocessed historical web page data; feature extraction is performed on the preprocessed historical web page data to obtain features for web page data classification; the features include text content, keyword density, and web page structure.

[0048] Specifically, we use a crawler based on HTTP (Hypertext Transfer Protocol) requests to collect historical web page data related to corporate credit ratings. The types of historical web page data include basic corporate information, financial information, credit records, operating conditions, equity changes and investment relations, intellectual property rights, human resources 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 process is as follows: (1) Use the Z-score (Z-standard score, Z score) method to identify and correct outliers and error values ​​in the data and perform noise processing; the calculation formula of Z-score is:

[0050] ;

[0051] Where X is a specific data point in the data set. is the mean value of the data set, is the standard deviation of the data set. If Z=0, the data point is equal to the mean; if Z>0, the data point is above the mean; if Z<0, the data point is below the mean. 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: Use the K-means++ algorithm (an improved version of the K-means algorithm) to fill in missing values; (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 key features such as text, keywords, and links.

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

[0053] Step S12: Use the trained random forest model to classify the current web page data to obtain classification results, dynamically adjust the crawler's crawling strategy based on the classification results to obtain crawler results, and calculate the supplier credit value based on the crawler results and supplier information of the e-commerce industry supply chain.

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

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

[0056] ;

[0057] in, , , , , is the weight number, is the historical supply cycle score of the i-th supplier, is the supply cycle of the i-th supplier for the j-th product transaction, is the historical average supply cycle of the platform, is the total number of transactions of the i-th supplier on the e-commerce industry quotation platform, is the historical price score of the i-th supplier, is the historical average supply price of the jth product on the e-commerce industry quotation platform. is the historical supply price of the i-th supplier for the j-th product, is the historical after-sales rate of the i-th supplier, is the historical average after-sales rate of the platform, For crawler results, The supplier's credit value.

[0058] In this embodiment, reasonable indicators are selected based on the crawler results to establish a corporate credit rating model. This solution uses a multi-scale convolutional neural network to establish the corporate credit rating model, and then calculates the supplier credit value based on the supplier information; wherein the supplier information includes historical supply cycles, historical price information, and historical after-sales information.

[0059] Step S13: Obtain the user's order information and send the order information to each supplier so that each supplier returns basic quotation information, calculates the corresponding target quotation based on the basic quotation information, the order information and the supplier's 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] in, The price coefficient given by the e-commerce industry quotation platform for suppliers' quotations. For the i-th supplier Basic quotation for each product. For shipping, is the distance between the user and the place of shipment, The price discount is based on the order quantity of the user. The quantity of the order placed by the user. This is the price subsidy based on the supplier's credit value. is the supplier's credit value, Quote for the target.

[0063] In this embodiment, suppliers on the e-commerce industry quotation platform will quote for the standard products in the user's order information respectively; the user's order information includes the ordering geographical location information, order demand quantity, etc., and the corresponding optimal price pushed to the user is calculated based on the basic quotation information returned by the supplier, the user's order information and the supplier's credit value, that is, the target quotation.

[0064] In this embodiment, historical web page data used for training the model is crawled by a crawler, and the random forest model is trained using the historical web page data to obtain the trained random forest model; the current web page 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, and the supplier credit value is calculated based on the crawler result and the supplier information of the e-commerce industry supply chain; the user's order information is obtained, and the order information is sent to each supplier so that each supplier returns basic quotation information, and 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. This application is applied to the quotation platform of the e-commerce industry. A crawler is used to crawl historical web page data to train a random forest model so as to dynamically adjust the crawling strategy of the crawler. This can make the calculation of the supplier's credit value more scientific and reduce the topic drift phenomenon caused by the traditional crawler algorithm. The supplier returns basic quotation information based on the user's order information, and then calculates the target quotation based on the supplier's credit value, order information and basic quotation information. Differentiated target quotations are intelligently generated for different suppliers and different users, realizing diversified and intelligent e-commerce industry supply chain order quotations, and improving the efficiency of e-commerce industry supply chain order quotations and the response speed of the quotation process.

[0065] See also Figure 2 As shown, the embodiment of the present invention discloses an order quotation method for the supply chain of the e-commerce industry, which is applied to the quotation platform of the e-commerce industry and may specifically include:

[0066] Step S21: crawling historical web page data used for training the model through a crawler, and using the historical web page data to train the random forest model to obtain the trained random forest model.

[0067] Step S22: Use the trained random forest model to classify the current web page data, and determine the correlation between the current web page data and the credit rating to obtain the classification result and the credit rating correlation, set the crawling strategy, dynamically adjust the parameters in the crawling strategy based on the classification result and the credit rating correlation to obtain the crawler result, and monitor and optimize the crawling strategy in real time and iterate and update it in real time.

[0068] In this embodiment, after obtaining the classification results, the PageRank crawler is initialized. The process is as follows: construct a web page graph, use the collected web pages as nodes, and the links between web pages as edges to construct a directed graph; calculate the initial PageRank value, and use the PageRank algorithm to calculate the initial PageRank value of each web page based on the link relationship and link quality between web pages. In order to achieve dynamic adjustment of the crawling strategy, the specific process is as follows: (1) Setting adjustment rules: Based on the classification results of the web page content by the random forest, set a set of rules for adjusting the crawling strategy of the PageRank crawler. If the web page is classified as highly relevant to the credit rating, increase its PageRank value and increase its crawling priority; otherwise, reduce its PageRank value and reduce its crawling priority; (2) Real-time update of PageRank value: In the process of the crawler crawling web pages, obtain the classification results of the web page content by the random forest in real time, and update the PageRank value of the corresponding web page according to the adjustment rules; (3) Dynamically adjust the crawler behavior: According to the updated PageRank value, dynamically adjust the crawler's crawling behavior. Crawling web pages with high PageRank values ​​is prioritized, and the crawling depth, breadth and other parameters are adjusted as needed.

[0069] In addition, the crawling strategy can be monitored and optimized in real time, as well as updated iteratively in real time. Real-time monitoring and optimization include: (1) Monitoring crawler performance: Regularly monitor the running status of the crawler, including crawling speed, success rate, error rate and other indicators; (2) Evaluating classification accuracy: Evaluate the accuracy of the random forest model in classifying web page content, and adjust model parameters or retrain the model as needed; (3) Optimize adjustment rules: According to the actual performance of the crawler and data changes, continuously optimize and adjust the PageRank value adjustment rules to improve the efficiency and accuracy of the crawler. Iterative updates include: (1) Update web page data: As time goes by, new web page data will continue to be generated. Regularly update the collected web page data, and re-preprocess and classify it; (2) Update crawler strategy: According to the new web page data and classification results, update the crawling strategy of the PageRank crawler to adapt to changes in data and changes in business needs.

[0070] Step S23: Calculate the supplier credit value based on the crawler results and the supplier information of the e-commerce industry supply chain.

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

[0072] The specific process of this application is as follows Figure 3 As shown in the figure, (1) the classification results of web page content by random forest are used to dynamically adjust the crawling strategy of PageRank algorithm crawler to obtain crawling results; (2) a multi-scale convolutional neural network is used to establish an enterprise credit rating model, and the supplier credit value is calculated based on the crawler results and supplier information of the e-commerce industry supply chain; (3) the user's order information is obtained, and multiple suppliers return basic quotation information based on the order information; (4) based on the basic quotation information, the user's order information and the supplier's credit value, and the internal algorithm of the platform, the optimal quotation to the user, that is, the target quotation, is calculated, and finally the target quotation is sent to the user for order quotation.

[0073] This application can solve the problems of long quotation links and low response efficiency caused by the current industry business model changing from "self-operated" to "self-operated" + "matchmaking" business model. The advantages are as follows: (1) It can improve quotation efficiency and improve the platform's responsiveness to user needs: the crawler algorithm for corporate credit rating has been improved, making the calculation of supplier credit value more scientific; (2) Intelligently combining supplier quotations and platform internal pricing algorithms to make quotations faster and prices more reasonable; (3) Intelligently generate differentiated pricing for different suppliers and different users, combined with the platform's material procurement costs, to quote different prices for different users.

[0074] In this embodiment, historical web page data used for training the model is crawled by a crawler, and the random forest model is trained using the historical web page data to obtain the trained random forest model; the current web page 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, and the supplier credit value is calculated based on the crawler result and the supplier information of the e-commerce industry supply chain; the user's order information is obtained, and the order information is sent to each supplier so that each supplier returns basic quotation information, and 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. This application is applied to the quotation platform of the e-commerce industry. A crawler is used to crawl historical web page data to train a random forest model so as to dynamically adjust the crawling strategy of the crawler. This can make the calculation of the supplier's credit value more scientific and reduce the topic drift phenomenon caused by the traditional crawler algorithm. The supplier returns basic quotation information based on the user's order information, and then calculates the target quotation based on the supplier's credit value, order information and basic quotation information. Differentiated target quotations are intelligently generated for different suppliers and different users, realizing diversified and intelligent e-commerce industry supply chain order quotations, and improving the efficiency of e-commerce industry supply chain order quotations and the response speed of the quotation process.

[0075] See also Figure 4 As shown, the embodiment of the present invention discloses an order quotation device for the supply chain of the e-commerce industry, which is applied to the quotation platform of the e-commerce industry and may specifically include:

[0076] The model training module 11 is used to crawl historical web page data used for training the model through a crawler, and train the random forest model using the historical web page data to obtain the trained random forest model;

[0077] A credit value calculation module 12 is used to classify the current web page data 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 the supplier credit value according to the crawler result and the supplier information of the e-commerce industry supply chain;

[0078] The order quotation module 13 is used to obtain the user's order information and send the order information to each supplier so that each supplier returns basic quotation information, calculates the corresponding target quotation information based on the basic quotation information, the order information and the supplier's credit value, and sends the target quotation information to the user for order quotation.

[0079] In this embodiment, historical web page data used for training the model is crawled by a crawler, and the random forest model is trained using the historical web page data to obtain the trained random forest model; the current web page 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, and the supplier credit value is calculated based on the crawler result and the supplier information of the e-commerce industry supply chain; the user's order information is obtained, and the order information is sent to each supplier so that each supplier returns basic quotation information, and 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. This application is applied to the quotation platform of the e-commerce industry. A crawler is used to crawl historical web page data to train a random forest model so as to dynamically adjust the crawling strategy of the crawler. This can make the calculation of the supplier's credit value more scientific and reduce the topic drift phenomenon caused by the traditional crawler algorithm. The supplier returns basic quotation information based on the user's order information, and then calculates the target quotation based on the supplier's credit value, order information and basic quotation information. Differentiated target quotations are intelligently generated for different suppliers and different users, realizing diversified and intelligent e-commerce industry supply chain order quotations, and improving the efficiency of e-commerce industry supply chain order quotations and the response speed of the quotation process.

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

[0081] A data crawling module, used for crawling historical web page data related to enterprise credit rating and used for training models through a crawler based on a hypertext transfer protocol request;

[0082] The preprocessing and feature extraction module is used to preprocess the historical web page data to obtain the preprocessed historical web page data, and to extract features from the preprocessed historical web page data to obtain features for classifying the web page data.

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

[0084] A preprocessing module, used for performing abnormal value and error value identification and noise processing, missing value processing, duplicate data processing, and data format standardization processing on the historical web page data to obtain the preprocessed historical web page data;

[0085] The feature extraction module is used to extract features from the pre-processed historical web page data to obtain features for web page data classification; the features include text content, keyword density and web page structure.

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

[0087] A classification module, used to classify the current web page data using the trained random forest model, and determine the correlation between the current web page data and the credit rating, so as to obtain the classification result and the credit rating correlation;

[0088] A crawler result acquisition module, used for setting a crawling strategy, and dynamically adjusting the parameters in the crawling strategy based on the classification result and the credit rating correlation to obtain a crawler result;

[0089] The crawling strategy monitoring and updating module is used to monitor and optimize the crawling strategy in real time and to iterate and update it in real time.

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

[0091] A model building module, used for selecting model building indicators based on the crawler results, and building an enterprise credit rating model according to the model building indicators;

[0092] The credit value calculation module is used to input the supplier information and the crawler results into the enterprise credit rating model for calculation to obtain the supplier credit value.

[0093] In some specific embodiments, the supplier credit value is calculated as follows:

[0094] ;

[0095] in, , , , , is the weight number, is the historical supply cycle score of the i-th supplier, is the supply cycle of the i-th supplier for the j-th product transaction, is the historical average supply cycle of the platform, is the total number of transactions of the i-th supplier on the e-commerce industry quotation platform, is the historical price score of the i-th supplier, is the historical average supply price of the jth product on the e-commerce industry quotation platform. is the historical supply price of the i-th supplier for the j-th product, is the historical after-sales rate of the i-th supplier, is the historical average after-sales rate of the platform, For crawler results, The supplier's credit value.

[0096] In some specific embodiments, the target price is calculated as follows:

[0097] ;

[0098] in, The price coefficient given by the e-commerce industry quotation platform for suppliers' quotations. For the i-th supplier Basic quotation for each product. For shipping, is the distance between the user and the place of shipment, The price discount is based on the order quantity of the user. The quantity of the order placed by the user. This is the price subsidy based on the supplier's credit value. is the supplier's credit value, Quote for the target.

[0099] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device 20 may 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 relevant steps in the order quotation method for the supply chain of the e-commerce industry performed by the electronic device disclosed in any of the aforementioned embodiments.

[0100] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

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

[0102] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20 to realize the operation and processing of the data 223 in the memory 22 by the processor 21, which can be Windows, Unix, Linux, etc. In addition to including a computer program that can be used to complete the order quotation method of the e-commerce industry supply chain executed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can also further include a computer program that can be used to complete other specific tasks. In addition to data transmitted from an external device received by the order quotation device of the e-commerce industry supply chain, the data 223 can also include data collected by its own input and output interface 25, etc.

[0103] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may 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] Furthermore, an embodiment of the present application also discloses a computer-readable storage medium, in which a computer program is stored. When the computer program is loaded and executed by a processor, the order quotation method steps for the e-commerce industry supply chain disclosed in any of the aforementioned embodiments are implemented.

[0105] Finally, it should be noted that, in this article, relational terms such as first and second, etc. 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 these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0106] The above is a detailed introduction to the order quotation method, device, equipment and storage medium for the supply chain of the e-commerce industry provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. An order quotation method for the supply chain of the e-commerce industry, characterized in that: Applied to the e-commerce industry quotation platform, including: Crawling historical web page data used for training the model through a crawler, and using the historical web page data to train the random forest model to obtain the trained random forest model; Using the trained random forest model to classify the current web page data 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; Obtain the user's order information and send the order information to each supplier so that each supplier returns basic quotation information, calculates the corresponding target quotation based on the basic quotation information, the order information and the supplier's credit value, and sends the target quotation to the user for order quotation.

2. The order quotation method for the supply chain of the e-commerce industry according to claim 1 is characterized in that: The crawling of historical web page data for training the model by crawling includes: Crawling historical web page data related to corporate credit rating and used for training models through crawlers based on hypertext transfer protocol requests; The historical web page data is preprocessed to obtain the preprocessed historical web page data, and feature extraction is performed on the preprocessed historical web page data to obtain features for web page data classification.

3. The order quotation method for the supply chain of the e-commerce industry according to claim 2 is characterized in that: The preprocessing of the historical web page data to obtain the preprocessed historical web page data, and feature extraction of the preprocessed historical web page data to obtain features for web page data classification include: Performing abnormal value and error value identification and noise processing, missing value processing, duplicate data processing, and data format standardization processing on the historical web page data to obtain the pre-processed historical web page data; Feature extraction is performed on the preprocessed historical web page data to obtain features for web page data classification; the features include text content, keyword density and web page structure.

4. The order quotation method for the supply chain of the e-commerce industry according to claim 1 is characterized in that: The method of using the trained random forest model to classify the current web page data to obtain a classification result, and dynamically adjusting the crawling strategy of the crawler based on the classification result to obtain a crawler result includes: Using the trained random forest model 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 credit rating correlation; Setting a crawling strategy, and dynamically adjusting parameters in the crawling strategy based on the classification result and the credit rating correlation to obtain a crawling result; The crawling strategy is monitored and optimized in real time and updated iteratively in real time.

5. The order quotation method for the supply chain of the e-commerce industry according to claim 1 is characterized in that: The calculating of the supplier credit value according to the crawler result and the supplier information of the e-commerce industry supply chain includes: Selecting model establishment indicators based on the crawler results, and establishing a corporate credit rating model according to the model establishment indicators; The supplier information and the crawler results are input into the enterprise credit rating model for calculation to obtain the supplier credit value.

6. The order quotation method for the supply chain of the e-commerce industry according to claim 5 is characterized in that: The calculation formula of the supplier credit value is: ； in, , , , , is the weight number, is the historical supply cycle score of the i-th supplier, is the supply cycle of the i-th supplier for the j-th product transaction, is the historical average supply cycle of the platform, is the total number of transactions of the i-th supplier on the e-commerce industry quotation platform, is the historical price score of the i-th supplier, is the historical average supply price of the jth product on the e-commerce industry quotation platform. is the historical supply price of the i-th supplier for the j-th product, is the historical after-sales rate of the ith supplier, is the historical average after-sales rate of the platform, For crawler results, The supplier's credit value.

7. The order quotation method for the supply chain of the e-commerce industry according to any one of claims 1 to 6, characterized in that: The target price is calculated as follows: ； in, The price coefficient given by the e-commerce industry quotation platform for suppliers' quotations. For the i-th supplier Basic quotation for each product. For shipping, is the distance between the user and the place of shipment, The price discount is based on the order quantity of the user. The quantity of the order placed by the user. This is the price subsidy based on the supplier's credit value. is the supplier's credit value, Quote for the target.

8. An order quotation device for the supply chain of the e-commerce industry, characterized in that: Applied to the e-commerce industry quotation platform, including: A model training module, used to crawl historical web page data used for training the model through a crawler, and train the random forest model using the historical web page data to obtain the trained random forest model; A credit value calculation module, used to classify the current web page data 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 the supplier credit value based on the crawler result and the supplier information of 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 returns basic quotation information, calculates the corresponding target quotation information based on the basic quotation information, the order information and the supplier's credit value, and sends the target quotation information to the user for order quotation.

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

10. A computer-readable storage medium, characterized in that: Used to store computer programs; wherein, when the computer program is executed by a processor, it implements the order quotation method for the supply chain of the e-commerce industry as described in any one of claims 1 to 7.

Images