CN113781107A - E-commerce promotion pricing decision-making auxiliary method and system based on big data - Google Patents
E-commerce promotion pricing decision-making auxiliary method and system based on big data Download PDFInfo
- Publication number
- CN113781107A CN113781107A CN202110995391.5A CN202110995391A CN113781107A CN 113781107 A CN113781107 A CN 113781107A CN 202110995391 A CN202110995391 A CN 202110995391A CN 113781107 A CN113781107 A CN 113781107A
- Authority
- CN
- China
- Prior art keywords
- data
- decision
- sales
- promotion pricing
- promotion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Artificial Intelligence (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an E-commerce promotion pricing decision-making auxiliary method based on big data, which comprises the following steps: step S1) collecting historical price data of each product type in each quarter in recent years, corresponding sales data and point data from a cloud computing big data platform; step S2) preprocessing the collected historical data; step S3), dividing the preprocessed data into training set data and testing set data, and learning by a neural network method to obtain a promotion pricing decision-making auxiliary model; step S4), after the decision maker verifies that the login obtains the authority, the real-time quarter and the product type are used as the input of a promotion pricing decision-making auxiliary model, and the promotion pricing decision-making auxiliary model outputs reference pricing under different sales volume/comment weight ratios. According to the invention, a large amount of historical data support is obtained through a cloud computing big data platform, reference pricing of various product types is obtained through a sales promotion pricing decision auxiliary model, and sales promotion pricing decision auxiliary is provided for the e-commerce enterprises.
Description
Technical Field
The invention relates to the technical field of digital economy, in particular to an E-commerce promotion pricing decision-making auxiliary method and system based on big data.
Background
In the world, with the improvement of the consumption capacity of people, the e-commerce industry develops rapidly, and a plurality of promotion activities appear. The sales promotion is an important component of an enterprise marketing combination strategy, and is a marketing activity which is characterized in that enterprises communicate production and consumption information between producers and customers by various means, grasp the requirements and preferences of the customers, stimulate the customers to generate good feeling and trust for the enterprises and products thereof, and further arouse the purchasing interest and purchasing behavior of the customers. The promotion provides a series of benefits which are vital to manufacturers and consumers, and is an important link in brand communication, and the promotion is more and more important in brand communication and is increasingly frequently used by enterprises along with the change of market environments. The most critical link in the promotion activities is promotion pricing, a proper promotion price, the benefits of enterprises and consumers are considered at the same time, the product sales volume and the consumer satisfaction degree are guaranteed, and as the electric business industry usually sells products in various types and frequently changes the cost, the problem that how to determine the optimal price for the product in the promotion activities becomes a decision maker is very headache.
Disclosure of Invention
The invention mainly aims to solve the problem that the electric commerce and enterprise are difficult to determine the optimal promotion price strategy of products on the premise of considering both the sales volume and the customer satisfaction degree, and provides an electric commerce and sales promotion pricing decision-making auxiliary method and system based on big data.
In order to achieve the purpose, the invention adopts the following technical scheme:
an E-commerce promotion pricing decision-making auxiliary method based on big data comprises the following steps: step S1) collecting historical price data of each product type in each quarter in recent years, corresponding sales data and point data from a cloud computing big data platform; step S2) preprocessing the collected historical data; step S3), dividing the preprocessed data into training set data and testing set data, and learning by a neural network method to obtain a promotion pricing decision-making auxiliary model; step S4), after the decision maker verifies that the login obtains the authority, the real-time quarter and the product type are used as the input of the promotion pricing decision-making auxiliary model, and the promotion pricing decision-making auxiliary model outputs the reference pricing under different sales volume/comment weight ratios. According to the method, a large amount of historical data support is obtained through the cloud computing big data platform, the reliability and the accuracy of the generated sales promotion pricing decision-making auxiliary model are improved, and the efficiency and the reliability of sales promotion pricing decision-making assistance provided by the scheme are further ensured. The specific process is as follows: the cloud computing big data platform is connected with each basic server of the e-commerce enterprise, collects and stores price data of each product type of the e-commerce enterprise in each quarter in recent years and corresponding sales data and comment data, the sales data indirectly reflect the income condition of the enterprise, the comment data reflect the acceptance of a consumer to the price, and indirectly reflect the satisfaction of the consumer, namely the income condition of the consumer; in order to generate a sales promotion pricing decision-making auxiliary model, historical price data of various product types in different seasons in recent years and corresponding sales volume data and rating data are collected from a cloud computing large data platform, then the collected historical data are preprocessed, normalization processing is carried out on the historical price data, rating data are graded to obtain sales volume grade labels, keyword extraction processing is carried out on the rating data, rating star grade processing is carried out according to the extracted keywords to obtain rating star grade labels, the sales volume grade labels and the rating star grade labels are vectorized, one-hot format in classified coding is adopted to express each label as a full zero vector, the preprocessed historical data are divided into a training set and a testing set, a fuzzy neural network is constructed through a neural network learning method, training is carried out through the training set, verifying by using a test set to generate a sales promotion pricing decision auxiliary model; when a decision maker needs promotion pricing decision assistance, after login obtaining authority is verified through a mobile terminal, real-time quarters and product types are input, and a promotion pricing decision assistance model outputs reference prices under different sales volume/comment weight ratios. Because the electric commerce enterprise generally sells products of various types, the cost changes frequently, and the best promotion price is difficult to set on the premise of simultaneously considering the sales volume and the customer satisfaction in the promotion activity, the scheme provides an electric commerce promotion pricing decision auxiliary method based on big data by means of a cloud computing big data platform, obtains the reference pricing of various product types under different sales volume/point rating weight ratios by constructing a promotion pricing decision auxiliary model, provides promotion pricing decision assistance for the electric commerce enterprise, ensures to set the best promotion price on the premise of considering the sales volume and the customer satisfaction, and improves the pricing accuracy and the response speed.
Preferably, the data preprocessing in step S2 includes the steps of: step S21) carrying out normalization processing on the historical price data of each product type in each quarter; step S22) grading the corresponding sales data to obtain sales grades corresponding to historical price data of various product types; step S23) performing keyword extraction processing on the corresponding comment data, and performing rating star grading processing according to the extracted keywords to obtain rating star grades corresponding to the historical price data of various product types; step S24) vectorizing the sales level label obtained in step S22 and the criticizing star level label obtained in step S23, and representing each label as an all-zero vector in a one-hot format in classification coding. According to the scheme, after historical data are collected from a cloud computing big data platform, the collected historical data are preprocessed, the normalization processing is carried out on the historical price data to obtain normalized historical price data, the grading processing is carried out on the sales data to obtain sales volume grade tags, the keyword extraction processing is carried out on the comment data, the comment grade processing is carried out according to the extracted keywords to obtain comment star grade tags, the sales volume grade tags and the comment star grade tags are vectorized, and one-hot formats in classification coding are adopted to express each tag as a full zero vector.
Preferably, the learning through the neural network method in step S3 to obtain the promotional pricing decision-making auxiliary model includes the following steps: step S31) constructing a fuzzy neural network; step S32) initializing the network parameters of the fuzzy neural network; step S33) carrying out supervised pre-training on the initialized fuzzy neural network by using training set data; step S34), parameters of the fuzzy neural network after supervised pre-training are reserved, and the full connection layer of the fuzzy neural network is replaced by the deep belief network; step S35) carrying out unsupervised pre-training on the deep belief network by using the training set data; step S36), parameters of the deep confidence network after unsupervised pre-training are reserved, and a softmax layer is added behind an output layer of the existing network; step S37), carrying out supervised training on the whole network by using the training set data and generating a promotion pricing decision-making auxiliary model; step S38) verifies the generated promotional pricing decision-making auxiliary model with the test set data. In step S3, learning is performed by a neural network method, and the process of obtaining the sales promotion pricing decision-making auxiliary model is as follows: firstly, a fuzzy neural network is constructed, parameters of the fuzzy neural network are initialized, then supervised pre-training is carried out on the initialized fuzzy neural network by using training set data, the parameters of the fuzzy neural network after the supervised pre-training are reserved, a full connection layer of the fuzzy neural network is replaced by using a deep belief network, then unsupervised pre-training is carried out on the deep belief network by using the training set data, the parameters of the deep belief network after the unsupervised pre-training are reserved, a softmax layer is added behind an output layer of the existing network, the whole network is subjected to supervised training by using the training set data to generate a promotion pricing decision auxiliary model, finally, the generated promotion pricing auxiliary model is verified by using test set data, and if the verification is successful, the generated promotion pricing auxiliary model can be used for providing promotion pricing auxiliary decision.
Preferably, the output of the softmax layer is the credibility of the reference pricing at different sales/comment weight ratios output by the promotion pricing decision-making auxiliary model, and the credibility value is within the (0,1) interval. The output of the softmax layer is the credibility of the reference pricing under different sales volume/comment weight ratios output by the promotion pricing decision-making auxiliary model, so that the referenceable degree of the reference pricing is provided for the decision maker.
Preferably, the method for verifying the promotional pricing decision-making auxiliary model generated in step S37 by using the test set data in step S38 is as follows: inputting the normalized historical price data of each product category of the test set in each quarter into the promotion pricing decision auxiliary model generated in the step S37, judging the credibility output by the model softmax layer, when the credibility value is greater than 0.5, determining that the input normalized historical price data of each product category of the test set in each quarter corresponds to the sales level and the evaluation star level output by the promotion pricing decision auxiliary model, and finally matching the output sales level and the evaluation star level with the corresponding sales level label and the evaluation star level label in the test set data so as to verify the promotion pricing decision auxiliary model. And when the output sales volume level and the evaluation star level are successfully matched with the corresponding sales volume level labels and evaluation star level labels in the test set data, proving that the generated promotion pricing decision auxiliary model can be used for providing promotion pricing decision auxiliary.
Preferably, the reference pricing influencing factors output by the promotion pricing decision-making auxiliary model further comprise a sales volume/comment weight ratio. With respect to promotional pricing, the e-commerce industry needs to consider both the benefits of the enterprise and the consumer, i.e., both sales and customer satisfaction, wherein the customer satisfaction is fed back through the review data. The decision maker in different stages has different weights for considering the sales volume and the customer satisfaction degree, sometimes emphasizes the sales volume and sometimes emphasizes the customer satisfaction degree, so the reference pricing improved by the sales promotion pricing decision auxiliary model of the scheme is also the reference pricing under a plurality of sales volume/comment weight ratios, and the practicability and the reliability of the invention are improved.
An E-commerce promotion pricing decision auxiliary system based on big data, which adopts the E-commerce promotion pricing decision auxiliary method based on big data as claimed in any one of claims 1 to 6, and comprises a cloud computing big data platform, a data acquisition unit, a data preprocessing unit, a data analysis unit and a mobile terminal, wherein the cloud computing big data platform is connected with an E-commerce server and is used for collecting and storing historical price data of various product types in various seasons and corresponding sales data and evaluation data of the E-commerce server in recent years; the data acquisition unit is connected with the cloud computing big data platform and is used for acquiring historical price data of each product type in recent years of a manufacturer, sales data and evaluation data corresponding to the historical price data and the sales data from the cloud computing big data platform; the data preprocessing unit is connected with the data acquisition unit and is used for preprocessing the historical data acquired by the data acquisition unit; the data analysis unit is connected with the data preprocessing unit and is used for generating a promotion pricing decision-making auxiliary model; the mobile terminal is connected with the data analysis unit, and a decision maker inputs a real-time quarter and a product type to the promotion pricing decision auxiliary model through the mobile terminal and obtains reference pricing under different sales volume/comment weight ratios corresponding to the real-time quarter and the product type through the mobile terminal. When a decision maker needs promotion pricing decision assistance, after login obtaining authority is verified through a mobile terminal, real-time quarters and product types are input, and a promotion pricing decision assistance model outputs reference prices under different sales volume/comment weight ratios. Because the electric commerce industry often sells products of various types, the cost changes frequently, and in the promotion activity, the optimal promotion price is difficult to set on the premise of simultaneously considering the sales volume and the customer satisfaction degree, therefore, the system obtains the reference pricing of various product types under different sales volume/point rating weight ratios by constructing a promotion pricing decision auxiliary model by means of a cloud computing big data platform, provides promotion pricing decision assistance for the electric commerce industry, ensures that the optimal promotion price is set on the premise of considering the sales volume and the customer satisfaction degree, and improves the pricing accuracy and the response speed.
Therefore, the invention has the advantages that:
(1) by constructing a sales promotion pricing decision-making auxiliary model, reference pricing of various product types under different sales volume/comment weight ratios is obtained, sales promotion pricing decision-making assistance is provided for the e-commerce industry, the best sales promotion price is determined on the premise of considering both the sales volume and the customer satisfaction, the pricing accuracy and response speed are improved, and the practicability and reliability are achieved;
(2) through a cloud computing big data platform, a large amount of historical data support is obtained, the reliability and the accuracy of the generated sales promotion pricing decision-making auxiliary model are improved, and the efficiency and the reliability of sales promotion pricing decision-making assistance provided by the scheme are further ensured.
Drawings
FIG. 1 is a flow chart of a big data-based E-commerce promotion pricing decision-making assistance method provided by the invention.
Fig. 2 is a schematic block diagram of a big data-based e-commerce promotion pricing decision-making assistance system provided by the invention.
1. The system comprises a cloud computing big data platform 2, a data acquisition unit 3, a data preprocessing unit 4, a data analysis unit 5, a mobile terminal 6 and an e-commerce server.
Detailed Description
The invention is further described with reference to the following detailed description and accompanying drawings.
As shown in fig. 1, a big data-based e-commerce promotion pricing decision-making assisting method includes the following steps: step S1) collecting historical price data of each product type in each quarter in recent years, corresponding sales data and point data from the cloud computing big data platform 1; step S2) preprocessing the collected historical data; step S3), dividing the preprocessed data into training set data and testing set data, and learning by a neural network method to obtain a promotion pricing decision-making auxiliary model; step S4), after the decision maker verifies that the login obtains the authority, the real-time quarter and the product type are used as the input of a promotion pricing decision-making auxiliary model, and the promotion pricing decision-making auxiliary model outputs reference pricing under different sales volume/comment weight ratios. The specific process is as follows: the cloud computing big data platform 1 is connected with the e-commerce server 6, collects and stores price data of various product types of e-commerce enterprises in various seasons in recent years, corresponding sales data and comment data, wherein the sales data indirectly reflect the income condition of the enterprises, the comment data reflect the acceptance of consumers to the price, and indirectly reflect the satisfaction of the consumers, namely the income condition of the consumers; in order to generate a sales promotion pricing decision-making auxiliary model, historical price data of various product types in different seasons in recent years and corresponding sales volume data and point rating data are collected from a cloud computing big data platform 1, then the collected historical data are preprocessed, normalization processing is carried out on the historical price data, grading processing is carried out on the sales volume data to obtain sales volume grade labels, keyword extraction processing is carried out on the point rating data, star grading processing is carried out according to the extracted keywords to obtain point rating star grade labels, the sales volume grade labels and the point rating star grade labels are vectorized, one-hot formats in classified codes are adopted to represent each label as a full zero vector, the preprocessed historical data are divided into a training set and a test set, a fuzzy neural network is constructed through a neural network learning method, training is carried out through the training set, verifying by using a test set to generate a sales promotion pricing decision auxiliary model; when a decision maker needs promotion pricing decision assistance, after login obtaining authority is verified through the mobile terminal 5, real-time quarters and product types are input, and a promotion pricing decision assistance model outputs reference prices under different sales volume/comment weight ratios.
The data preprocessing in step S2 includes the steps of: step S21) carrying out normalization processing on the historical price data of each product type in each quarter; step S22) grading the corresponding sales data to obtain sales grades corresponding to historical price data of various product types; step S23) performing keyword extraction processing on the corresponding comment data, and performing rating star grading processing according to the extracted keywords to obtain rating star grades corresponding to the historical price data of various product types; step S24) vectorizing the sales level label obtained in step S22 and the criticizing star level label obtained in step S23, and representing each label as an all-zero vector in a one-hot format in classification coding. According to the scheme, after historical data are collected from a cloud computing big data platform 1, the collected historical data are preprocessed, the steps of normalizing the historical price data to obtain normalized historical price data, grading the sales data to obtain sales volume grade tags, extracting keywords from the comment data, conducting rating treatment according to the extracted keywords to obtain rating star grade tags, vectorizing the sales volume grade tags and the rating star grade tags, and representing each tag as a full zero vector by adopting a one-hot format in classification coding are included.
In step S3, learning is performed by a neural network method, and obtaining a promotional pricing decision-making auxiliary model includes the following steps: step S31) constructing a fuzzy neural network; step S32) initializing the network parameters of the fuzzy neural network; step S33) carrying out supervised pre-training on the initialized fuzzy neural network by using training set data; step S34), parameters of the fuzzy neural network after supervised pre-training are reserved, and the full connection layer of the fuzzy neural network is replaced by the deep belief network; step S35) carrying out unsupervised pre-training on the deep belief network by using the training set data; step S36), parameters of the deep confidence network after unsupervised pre-training are reserved, and a softmax layer is added behind an output layer of the existing network; step S37), carrying out supervised training on the whole network by using the training set data and generating a promotion pricing decision-making auxiliary model; step S38) verifies the generated promotional pricing decision-making auxiliary model with the test set data. In step S3, learning is performed by a neural network method, and the process of obtaining the sales promotion pricing decision-making auxiliary model is as follows: firstly, a fuzzy neural network is constructed, parameters of the fuzzy neural network are initialized, then supervised pre-training is carried out on the initialized fuzzy neural network by using training set data, the parameters of the fuzzy neural network after the supervised pre-training are reserved, a full connection layer of the fuzzy neural network is replaced by using a deep belief network, then unsupervised pre-training is carried out on the deep belief network by using the training set data, the parameters of the deep belief network after the unsupervised pre-training are reserved, a softmax layer is added behind an output layer of the existing network, the whole network is subjected to supervised training by using the training set data to generate a promotion pricing decision auxiliary model, finally, the generated promotion pricing auxiliary model is verified by using test set data, and if the verification is successful, the generated promotion pricing auxiliary model can be used for providing promotion pricing auxiliary decision.
The output of the softmax layer is the credibility of the reference pricing under different sales volume/comment weight ratios output by the promotion pricing decision-making auxiliary model, and the credibility value is in the (0,1) interval. The output of the softmax layer is the credibility of the reference pricing under different sales volume/comment weight ratios output by the promotion pricing decision-making auxiliary model, so that the referenceable degree of the reference pricing is provided for the decision maker.
The method for verifying the promotional pricing decision-making auxiliary model generated in the step S37 by using the test set data in the step S38 is as follows: inputting the normalized historical price data of each product category of the test set in each quarter into the promotion pricing decision auxiliary model generated in the step S37, judging the credibility output by the model softmax layer, when the credibility value is greater than 0.5, determining that the input normalized historical price data of each product category of the test set in each quarter corresponds to the sales level and the evaluation star level output by the promotion pricing decision auxiliary model, and finally matching the output sales level and the evaluation star level with the corresponding sales level label and the evaluation star level label in the test set data, thereby verifying the promotion pricing decision auxiliary model. And when the output sales volume level and the evaluation star level are successfully matched with the corresponding sales volume level labels and evaluation star level labels in the test set data, proving that the generated promotion pricing decision auxiliary model can be used for providing promotion pricing decision auxiliary.
The reference pricing influencing factors output by the promotion pricing decision-making auxiliary model also comprise a sales volume/comment weight ratio. With respect to promotional pricing, the e-commerce industry needs to consider both the benefits of the enterprise and the consumer, i.e., both sales and customer satisfaction, wherein the customer satisfaction is fed back through the review data. Decision makers in different stages are different in weight considering both sales volume and customer satisfaction, sometimes emphasis is placed on sales volume, sometimes emphasis is placed on customer satisfaction, so the reference pricing improved by the auxiliary sales promotion pricing decision model of the scheme is also the reference pricing under multiple sales volume/comment weight ratios.
As shown in fig. 2, a big data-based e-commerce promotion pricing decision auxiliary system, which adopts a big data-based e-commerce promotion pricing decision auxiliary method according to any one of claims 1 to 6, comprises a cloud computing big data platform 1, a data acquisition unit 2, a data preprocessing unit 3, a data analysis unit 4 and a mobile terminal 5, wherein the cloud computing big data platform 1 is connected with an e-commerce server 6 and is used for collecting and storing historical price data of each product category in each quarter in recent years of an e-commerce and corresponding sales data and point rating data thereof; the data acquisition unit 2 is connected with the cloud computing big data platform 1 and is used for acquiring historical price data of each product type in recent years of a supplier and corresponding sales data and comment data of each product type in each quarter from the cloud computing big data platform 1; the data preprocessing unit 3 is connected with the data acquisition unit 2 and is used for preprocessing the historical data acquired by the data acquisition unit 2; the data analysis unit 4 is connected with the data preprocessing unit 3 and is used for generating a promotion pricing decision-making auxiliary model; the mobile terminal 5 is connected with the data analysis unit 4, and the decision maker inputs the real-time quarter and the product type to the promotion pricing decision auxiliary model through the mobile terminal 5, and obtains reference pricing under different sales volume/comment weight ratios corresponding to the real-time quarter and the product type through the mobile terminal 5. When a decision maker needs promotion pricing decision assistance, after login obtaining authority is verified through the mobile terminal 5, real-time quarters and product types are input, and a promotion pricing decision assistance model outputs reference prices under different sales volume/comment weight ratios.
Claims (7)
1. An E-commerce promotion pricing decision-making auxiliary method based on big data is characterized by comprising the following steps:
step S1: historical price data of each product type in each quarter in recent years, corresponding sales data and point data are collected from a cloud computing big data platform;
step S2: preprocessing the collected historical data;
step S3: dividing the preprocessed data into training set data and testing set data, and learning by a neural network method to obtain a promotion pricing decision-making auxiliary model;
step S4: and after the decision maker verifies the login acquisition authority, taking the real-time quarter and the product type as the input of the promotion pricing decision-making auxiliary model, and outputting the reference pricing under different sales volume/comment weight ratios by the promotion pricing decision-making auxiliary model.
2. The big-data-based E-commerce promotion pricing decision-making assisting method as claimed in claim 1, wherein the data preprocessing in step S2 comprises the following steps:
step S21: carrying out normalization processing on historical price data of each product type in each quarter;
step S22: grading the corresponding sales data to obtain sales grades corresponding to historical price data of various product types;
step S23: performing keyword extraction processing on the corresponding comment data, and performing rating star grading processing according to the extracted keywords to obtain rating star grades corresponding to historical price data of various product types;
step S24: and vectorizing the sales level label obtained in the step S22 and the criticizing star level label obtained in the step S23, and representing each label as an all-zero vector by adopting a one-hot format in classification coding.
3. The big-data-based E-commerce promotion pricing decision-making auxiliary method as claimed in claim 1, wherein the learning through neural network method in step S3 to obtain the promotion pricing decision-making auxiliary model comprises the following steps:
step S31: constructing a fuzzy neural network;
step S32: initializing network parameters of the fuzzy neural network;
step S33: carrying out supervised pre-training on the initialized fuzzy neural network by using training set data;
step S34: preserving parameters of the fuzzy neural network after the supervised pre-training, and replacing a full connection layer of the fuzzy neural network by using a deep belief network;
step S35: carrying out unsupervised pre-training on the deep belief network by using training set data;
step S36: reserving parameters of the deep belief network after unsupervised pre-training, and adding a softmax layer behind an output layer of the existing network;
step S37: carrying out supervised training on the whole network by using training set data and generating a sales promotion pricing decision auxiliary model;
step S38: and verifying the generated promotion pricing decision-making auxiliary model by using the test set data.
4. The big-data-based E-commerce promotion pricing decision-making auxiliary method according to claim 3, wherein the output of the softmax layer is the credibility of the reference pricing under different sales volume/review weight ratios output by the promotion pricing decision-making auxiliary model, and the credibility value is within the (0,1) interval.
5. The big-data-based E-commerce promotion pricing decision-making assistance method as claimed in claim 3, wherein the step S38 of validating the promotion pricing decision-making assistance model generated in the step S37 with the test set data comprises: inputting the normalized historical price data of each product category of the test set in each quarter into the promotion pricing decision auxiliary model generated in the step S37, judging the credibility output by the model softmax layer, when the credibility value is greater than 0.5, determining that the input normalized historical price data of each product category of the test set in each quarter corresponds to the sales level and the evaluation star level output by the promotion pricing decision auxiliary model, and finally matching the output sales level and the evaluation star level with the corresponding sales level label and the evaluation star level label in the test set data so as to verify the promotion pricing decision auxiliary model.
6. The big-data-based E-commerce promotion pricing decision-making auxiliary method according to claim 1, wherein the reference pricing influencing factors output by the promotion pricing decision-making auxiliary model further include a sales/review weight ratio.
7. A big data-based e-commerce promotion pricing decision auxiliary system, which adopts a big data-based e-commerce promotion pricing decision auxiliary method according to any one of claims 1 to 6, and is characterized by comprising:
cloud computing big data platform: the system is connected with an e-commerce server and used for collecting and storing historical price data of each product type in each quarter of recent years of an e-commerce company, and corresponding sales data and point rating data;
a data acquisition unit: the cloud computing big data platform is connected with the cloud computing big data platform, and historical price data of each product type in each quarter in recent years, corresponding sales data and evaluation data of the product type are acquired from the cloud computing big data platform;
a data preprocessing unit: the data acquisition unit is connected with the data acquisition unit and used for preprocessing historical data acquired by the data acquisition unit;
a data analysis unit: the data preprocessing unit is connected with the data processing unit and is used for generating a sales promotion pricing decision-making auxiliary model;
a mobile terminal: and the decision maker inputs the real-time quarter and the product type to the promotion pricing decision auxiliary model through the mobile terminal and obtains reference pricing under different sales volume/comment weight ratios corresponding to the real-time quarter and the product type through the mobile terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110995391.5A CN113781107A (en) | 2021-08-27 | 2021-08-27 | E-commerce promotion pricing decision-making auxiliary method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110995391.5A CN113781107A (en) | 2021-08-27 | 2021-08-27 | E-commerce promotion pricing decision-making auxiliary method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113781107A true CN113781107A (en) | 2021-12-10 |
Family
ID=78839950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110995391.5A Pending CN113781107A (en) | 2021-08-27 | 2021-08-27 | E-commerce promotion pricing decision-making auxiliary method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113781107A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292661A (en) * | 2017-06-02 | 2017-10-24 | 网易无尾熊（杭州）科技有限公司 | The computer implemented method and apparatus based on data analysis auxiliary pricing |
| CN108491377A (en) * | 2018-03-06 | 2018-09-04 | 中国计量大学 | A kind of electric business product comprehensive score method based on multi-dimension information fusion |
| CN108537382A (en) * | 2018-04-09 | 2018-09-14 | 成都易商商盟数据服务有限公司 | A kind of electric business upward price trend prediction technique and system |
| CN111160968A (en) * | 2019-12-27 | 2020-05-15 | 清华大学 | SKU-level commodity sales prediction method and device |
| CN112613953A (en) * | 2020-12-29 | 2021-04-06 | 北京环球国广媒体科技有限公司 | Commodity selection method, system and computer readable storage medium |
-
2021
- 2021-08-27 CN CN202110995391.5A patent/CN113781107A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107292661A (en) * | 2017-06-02 | 2017-10-24 | 网易无尾熊（杭州）科技有限公司 | The computer implemented method and apparatus based on data analysis auxiliary pricing |
| CN108491377A (en) * | 2018-03-06 | 2018-09-04 | 中国计量大学 | A kind of electric business product comprehensive score method based on multi-dimension information fusion |
| CN108537382A (en) * | 2018-04-09 | 2018-09-14 | 成都易商商盟数据服务有限公司 | A kind of electric business upward price trend prediction technique and system |
| CN111160968A (en) * | 2019-12-27 | 2020-05-15 | 清华大学 | SKU-level commodity sales prediction method and device |
| CN112613953A (en) * | 2020-12-29 | 2021-04-06 | 北京环球国广媒体科技有限公司 | Commodity selection method, system and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110222272B (en) | Potential customer mining and recommending method | |
| CN107169806B (en) | Method and device for determining influence degree of commodity attribute on purchase decision | |
| CN108921602B (en) | User purchasing behavior prediction method based on integrated neural network | |
| CN110111175A (en) | A kind of internet platform of commodity and service online order and management | |
| CN111047412A (en) | Big data electricity merchant operation platform | |
| CN107403345A (en) | Best-selling product Forecasting Methodology and system, storage medium and electric terminal | |
| CN111882420A (en) | Generation method of response rate, marketing method, model training method and device | |
| CN109993544A (en) | Data processing method, system, computer system and computer readable storage medium | |
| CN113469730A (en) | Customer repurchase prediction method and device based on RF-LightGBM fusion model under non-contract scene | |
| CN114861050A (en) | Feature fusion recommendation method and system based on neural network | |
| CN114266443A (en) | Data evaluation method and device, electronic equipment and storage medium | |
| CN107067282A (en) | A kind of consumer goods rebating sale marketing management system and its application method | |
| CN111861679A (en) | Commodity recommendation method based on artificial intelligence | |
| CN116187808A (en) | Electric power package recommendation method based on virtual power plant user-package label portrait | |
| CN111177581A (en) | Multi-platform-based social e-commerce website commodity recommendation method and device | |
| CN115511582B (en) | Commodity recommendation system and method based on artificial intelligence | |
| CN115482014B (en) | Method and device for identifying false car source of second-hand car | |
| CN112035624A (en) | Text recommendation method and device and storage medium | |
| CN113781107A (en) | E-commerce promotion pricing decision-making auxiliary method and system based on big data | |
| CN114996579A (en) | Information pushing method and device, electronic equipment and computer readable medium | |
| Kiran et al. | Analysis on the prediction of sales using various machine learning testing algorithms | |
| US11430033B2 (en) | Methods and systems of utilizing machine learning to provide trust scores in an online automobile marketplace | |
| CN114266594A (en) | Big data analysis method based on southeast Asia cross-border e-commerce platform | |
| CN113360845A (en) | Vehicle source transaction probability prediction method and device, electronic device and storage medium | |
| CN114155057A (en) | Commodity recommendation system for electronic commerce platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |