CN112907299A - Automatic generation method of e-commerce promotion scheme - Google Patents
Automatic generation method of e-commerce promotion scheme Download PDFInfo
- Publication number
- CN112907299A CN112907299A CN202110316775.XA CN202110316775A CN112907299A CN 112907299 A CN112907299 A CN 112907299A CN 202110316775 A CN202110316775 A CN 202110316775A CN 112907299 A CN112907299 A CN 112907299A
- Authority
- CN
- China
- Prior art keywords
- promotion
- data
- popularization
- effect
- commerce
- 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.)
- Withdrawn
Links
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
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0253—During e-commerce, i.e. online transactions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
-
- 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
-
- 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
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an automatic generation method of an e-commerce promotion scheme, which is used for establishing a database for the existing e-commerce promotion data, and enabling the data in the database to be as follows: the method comprises the following steps of 1, dividing the ratio into a training set and a test set, constructing a promotion effect prediction model by adopting training set data, inputting the test set data into the constructed promotion effect prediction model to predict promotion effects, judging the accuracy of the prediction model, classifying promotion modes and promotion product categories of promotion products to be tested, inputting the promotion effect prediction model to obtain promotion effects under various promotion modes, screening the promotion effect data in the step five, and obtaining the optimal promotion mode combination of the promotion products to be tested so as to determine a promotion scheme. The method and the system can predict the promotion effect of a product more accurately, and can provide a more accurate promotion expectation for a client, so that the client can conveniently select whether to promote correspondingly.
Description
Technical Field
The invention relates to an automatic scheme generation method, in particular to an automatic e-commerce promotion scheme generation method, and belongs to the field of e-commerce software.
Background
Electronic commerce is a direct product of internet explosion-type development and is a brand new development direction of network technology application. The characteristics of openness, globality, low cost and high efficiency of the internet itself also become the intrinsic characteristics of electronic commerce, and make the electronic commerce greatly surpass the value of a new trade form, which not only changes the production, operation and management activities of enterprises, but also influences the economic operation and structure of the whole society. The 'electronic' technical platform based on the internet provides an unprecedented development space for traditional business activities, and the outstanding advantages of the 'electronic' technical platform based on the internet are incomparable with traditional media means. With the development of the e-commerce industry, many enterprise customers also realize the business prospect of the e-commerce, so that the investment on the e-commerce part is increased at a glance, but many enterprises never concern the e-commerce field and do not have any experience of e-commerce popularization, and at this moment, a professional e-commerce operation company needs to be searched for third-party operation of the e-commerce. The third-party e-commerce operation company needs to firstly determine the promotion scheme to negotiate and cooperate with the enterprise, but the promotion effect of the product is uncertain, which is the place most concerned by the enterprise, so that how to predict the promotion effect of the corresponding scheme so as to obtain the optimal promotion scheme becomes the problem which needs to be solved urgently at present.
Disclosure of Invention
The invention aims to solve the technical problem of providing an automatic generation method of an e-commerce promotion scheme, predicting the promotion effect of promoted commodities through a neural network and obtaining an optimal promotion scheme.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
an automatic generation method of an e-commerce promotion scheme is characterized by comprising the following steps:
the method comprises the following steps: establishing a database for the existing e-commerce promotion data;
step two: the data in the database are processed according to the following steps of 9: 1 into a training set and a test set;
step three: constructing a popularization effect prediction model by adopting training set data;
step four: the method comprises the steps of inputting test set data into a constructed popularization effect prediction model to predict the popularization effect, and judging the accuracy of the prediction model;
step five: the method comprises the steps of classifying promotion modes and promotion product categories of promotion products to be detected, and inputting the promotion modes and the promotion product categories into a promotion effect prediction model to obtain promotion effects under the promotion modes;
step six: and D, screening the popularization effect data in the step five, and obtaining the optimal popularization mode combination of the popularization product to be detected so as to determine the popularization scheme.
Further, the step one is specifically
Storing the existing data promoted by the prior E-commerce according to the name of a promoted product, the type of the promoted product, the promotion mode and the format of the promotion effect, and establishing a database; the categories of the promoted products are correspondingly divided according to the corresponding promotion modes, and the promotion effects comprise promotion link click rate, actual commodity transaction amount, sales income and sales profit rate.
Further, the second step is specifically
Arrange the data in the database in order, because the product of a popularization can adopt different popularization methods in the actual popularization case, each popularization method can produce different popularization effect, consequently regard a data of promoting the product name as a data module, classify and according to 9 according to the data module with all data in the database: 1 into a training set and a test set, and then scattering the data modules in the training set and the test set to store the minimum unit of the popularization data.
Further, the third step is specifically
And constructing a four-layer convolutional neural network structure, and extracting minimum unit data in a training set to train the popularization effect prediction model.
Further, the fourth step is specifically
And inputting test set data into the constructed popularization effect prediction model to predict the popularization effect, comparing the prediction result with the actual effect of the test machine data, and judging that the accuracy of the popularization effect prediction model constructed in the step three reaches the standard when the similarity of the prediction effects of all the test set data is more than 95%.
Further, the fifth step is specifically that
The method comprises the steps of classifying promotion modes and promotion product categories of promotion products to be tested, inputting the promotion modes into a promotion effect prediction model to obtain promotion effects under the promotion modes, and finally obtaining a group of promotion effect data sets of the products because each promotion mode of each promotion product to be tested can generate a prediction of the promotion effect.
Further, the sixth step is specifically that
And D, because the effect data obtained in the step five is a set of the prediction results of the promotion effects of the promotion products to be tested in different promotion modes, sequencing the data in the data set according to the promotion effects from good to bad, selecting the promotion mode with the top three ranking as a primary selection promotion mode, then calculating the proportion of the effect of each promotion mode to the promotion cost in the rest promotion effect data, sequencing according to the proportion in the sequence from big to small, selecting the promotion mode with the top three ranking as a secondary selection promotion mode, and combining the primary selection promotion mode and the secondary selection promotion mode to obtain the final promotion mode combination, namely the final promotion scheme of the promotion products to be tested.
Compared with the prior art, the invention has the following advantages and effects: the automatic generation method of the E-commerce promotion scheme integrates the data of the completed promotion service, establishes a database according to a specific format, then constructs a promotion effect prediction model according to the data, predicts the promotion effect of a later product through the model, and then determines the optimal promotion scheme based on the predicted promotion effect; the method can predict the promotion effect of a product more accurately, and can provide a more accurate promotion expectation for a client, so that the client can conveniently select whether to promote correspondingly; meanwhile, the invention can automatically obtain an optimal popularization scheme, thereby greatly saving the labor, and the obtained scheme is more reasonable and has more ideal effect.
Detailed Description
To elaborate on technical solutions adopted by the present invention to achieve predetermined technical objects, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, it is obvious that the described embodiments are only partial embodiments of the present invention, not all embodiments, and technical means or technical features in the embodiments of the present invention may be replaced without creative efforts, and the present invention will be described in detail below with reference to the embodiments.
The invention discloses an automatic generation method of an e-commerce promotion scheme, which comprises the following steps:
the method comprises the following steps: establishing a database for the existing e-commerce promotion data;
storing the existing data promoted by the prior E-commerce according to the name of a promoted product, the type of the promoted product, the promotion mode and the format of the promotion effect, and establishing a database; the categories of the promoted products are correspondingly divided according to the corresponding promotion modes, and the promotion effects comprise promotion link click rate, actual commodity transaction amount, sales income and sales profit rate. To better quantify the promotional effect, a promotional effect = p sales profit margin (transaction amount of actual good/promotional link click amount) sales revenue is defined. p is a correction coefficient.
Step two: the data in the database are processed according to the following steps of 9: 1 into a training set and a test set;
arrange the data in the database in order, because the product of a popularization can adopt different popularization methods in the actual popularization case, each popularization method can produce different popularization effect, consequently regard a data of promoting the product name as a data module, classify and according to 9 according to the data module with all data in the database: 1 into a training set and a test set, and then scattering the data modules in the training set and the test set to store the minimum unit of the popularization data. The accuracy of the predicted model is proportional to the number of data in the training set of the database, and the larger the data amount is, the higher the accuracy of the model obtained by final training is, so that it is necessary to ensure that the data in the whole database has a certain number basis.
Step three: constructing a popularization effect prediction model by adopting training set data; and constructing a four-layer convolutional neural network structure, and extracting minimum unit data in a training set to train the popularization effect prediction model.
Step four: the method comprises the steps of inputting test set data into a constructed popularization effect prediction model to predict the popularization effect, and judging the accuracy of the prediction model;
and inputting test set data into the constructed popularization effect prediction model to predict the popularization effect, comparing the prediction result with the actual effect of the test machine data, and judging that the accuracy of the popularization effect prediction model constructed in the step three reaches the standard when the similarity of the prediction effects of all the test set data is more than 95%. The threshold of the similarity of the prediction effect can be determined according to actual conditions, for example, under the condition that the total data of the database is less, the model accuracy is not high, the model accuracy can be set to be less than 90%, and if the database data volume is large, the model accuracy can be set to be higher, so that a more accurate prediction effect is obtained.
Step five: the method comprises the steps of classifying promotion modes and promotion product categories of promotion products to be detected, and inputting the promotion modes and the promotion product categories into a promotion effect prediction model to obtain promotion effects under the promotion modes;
the method comprises the steps of classifying promotion modes and promotion product categories of promotion products to be tested, inputting the promotion modes into a promotion effect prediction model to obtain promotion effects under the promotion modes, and finally obtaining a group of promotion effect data sets of the products because each promotion mode of each promotion product to be tested can generate a prediction of the promotion effect.
Step six: and D, screening the popularization effect data in the step five, and obtaining the optimal popularization mode combination of the popularization product to be detected so as to determine the popularization scheme.
And D, because the effect data obtained in the step five is a set of the prediction results of the promotion effects of the promotion products to be tested in different promotion modes, sequencing the data in the data set according to the promotion effects from good to bad, selecting the promotion mode with the top three ranking as a primary selection promotion mode, then calculating the proportion of the effect of each promotion mode to the promotion cost in the rest promotion effect data, sequencing according to the proportion in the sequence from big to small, selecting the promotion mode with the top three ranking as a secondary selection promotion mode, and combining the primary selection promotion mode and the secondary selection promotion mode to obtain the final promotion mode combination, namely the final promotion scheme of the promotion products to be tested. The combination mode of the final scheme can be changed according to the actual situation, for example, only two popularization schemes are selected for initial selection, and 4-6 popularization modes are selected for secondary selection.
The automatic generation method of the E-commerce promotion scheme integrates the data of the completed promotion service, establishes a database according to a specific format, then constructs a promotion effect prediction model according to the data, predicts the promotion effect of a later product through the model, and then determines the optimal promotion scheme based on the predicted promotion effect; the method can predict the promotion effect of a product more accurately, and can provide a more accurate promotion expectation for a client, so that the client can conveniently select whether to promote correspondingly; meanwhile, the invention can automatically obtain an optimal popularization scheme, thereby greatly saving the labor, and the obtained scheme is more reasonable and has more ideal effect.
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (7)
1. An automatic generation method of an e-commerce promotion scheme is characterized by comprising the following steps:
the method comprises the following steps: establishing a database for the existing e-commerce promotion data;
step two: the data in the database are processed according to the following steps of 9: 1 into a training set and a test set;
step three: constructing a popularization effect prediction model by adopting training set data;
step four: the method comprises the steps of inputting test set data into a constructed popularization effect prediction model to predict the popularization effect, and judging the accuracy of the prediction model;
step five: the method comprises the steps of classifying promotion modes and promotion product categories of promotion products to be detected, and inputting the promotion modes and the promotion product categories into a promotion effect prediction model to obtain promotion effects under the promotion modes;
step six: and D, screening the popularization effect data in the step five, and obtaining the optimal popularization mode combination of the popularization product to be detected so as to determine the popularization scheme.
2. The method for automatically generating the e-commerce promotion scheme according to claim 1, wherein: the step one is specifically
Storing the existing data promoted by the prior E-commerce according to the name of a promoted product, the type of the promoted product, the promotion mode and the format of the promotion effect, and establishing a database; the categories of the promoted products are correspondingly divided according to the corresponding promotion modes, and the promotion effects comprise promotion link click rate, actual commodity transaction amount, sales income and sales profit rate.
3. The method for automatically generating the e-commerce promotion scheme according to claim 1, wherein: the second step is specifically that
Arrange the data in the database in order, because the product of a popularization can adopt different popularization methods in the actual popularization case, each popularization method can produce different popularization effect, consequently regard a data of promoting the product name as a data module, classify and according to 9 according to the data module with all data in the database: 1 into a training set and a test set, and then scattering the data modules in the training set and the test set to store the minimum unit of the popularization data.
4. The method for automatically generating the e-commerce promotion scheme according to claim 1, wherein: the third step is specifically that
And constructing a four-layer convolutional neural network structure, and extracting minimum unit data in a training set to train the popularization effect prediction model.
5. The method for automatically generating the e-commerce promotion scheme according to claim 1, wherein: the fourth step is specifically that
And inputting test set data into the constructed popularization effect prediction model to predict the popularization effect, comparing the prediction result with the actual effect of the test machine data, and judging that the accuracy of the popularization effect prediction model constructed in the step three reaches the standard when the similarity of the prediction effects of all the test set data is more than 95%.
6. The method for automatically generating the e-commerce promotion scheme according to claim 1, wherein: the fifth step is specifically that
The method comprises the steps of classifying promotion modes and promotion product categories of promotion products to be tested, inputting the promotion modes into a promotion effect prediction model to obtain promotion effects under the promotion modes, and finally obtaining a group of promotion effect data sets of the products because each promotion mode of each promotion product to be tested can generate a prediction of the promotion effect.
7. The method for automatically generating the e-commerce promotion scheme according to claim 1, wherein: the sixth step is specifically that
And D, because the effect data obtained in the step five is a set of the prediction results of the promotion effects of the promotion products to be tested in different promotion modes, sequencing the data in the data set according to the promotion effects from good to bad, selecting the promotion mode with the top three ranking as a primary selection promotion mode, then calculating the proportion of the effect of each promotion mode to the promotion cost in the rest promotion effect data, sequencing according to the proportion in the sequence from big to small, selecting the promotion mode with the top three ranking as a secondary selection promotion mode, and combining the primary selection promotion mode and the secondary selection promotion mode to obtain the final promotion mode combination, namely the final promotion scheme of the promotion products to be tested.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110316775.XA CN112907299A (en) | 2021-03-25 | 2021-03-25 | Automatic generation method of e-commerce promotion scheme |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110316775.XA CN112907299A (en) | 2021-03-25 | 2021-03-25 | Automatic generation method of e-commerce promotion scheme |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112907299A true CN112907299A (en) | 2021-06-04 |
Family
ID=76106722
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110316775.XA Withdrawn CN112907299A (en) | 2021-03-25 | 2021-03-25 | Automatic generation method of e-commerce promotion scheme |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112907299A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114997746A (en) * | 2022-07-28 | 2022-09-02 | 深圳要易云科技服务有限公司 | Information processing method, device and equipment based on medicine platform and storage medium |
-
2021
- 2021-03-25 CN CN202110316775.XA patent/CN112907299A/en not_active Withdrawn
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114997746A (en) * | 2022-07-28 | 2022-09-02 | 深圳要易云科技服务有限公司 | Information processing method, device and equipment based on medicine platform and storage medium |
CN114997746B (en) * | 2022-07-28 | 2022-11-11 | 深圳要易云科技服务有限公司 | Information processing method, device and equipment based on medicine platform and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106570778B (en) | A kind of method that data integration based on big data is calculated with line loss analyzing | |
Padhi et al. | Framework for selecting sustainable supply chain processes and industries using an integrated approach | |
JP6034890B2 (en) | Specification, estimation, causal driver discovery and market response elasticity or lift coefficient automation | |
JP2003316950A (en) | System and method for credit evaluation | |
CN112860769B (en) | Energy planning data management system | |
Hallak et al. | Productivity, quality and exporting behavior under minimum quality requirements | |
CN109767032A (en) | A kind of business finance operation digital management optimization system based on data analysis | |
CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
CN112561730A (en) | Power supply service analysis method based on double-layer clustering and fuzzy comprehensive evaluation | |
CN113537807B (en) | Intelligent wind control method and equipment for enterprises | |
CN108364191A (en) | Top-tier customer Optimum Identification Method and device based on random forest and logistic regression | |
CN111754317A (en) | Financial investment data evaluation method and system | |
CN115145993A (en) | Railway freight big data visualization display platform based on self-learning rule operation | |
CN112907299A (en) | Automatic generation method of e-commerce promotion scheme | |
Luo et al. | Supply Chain Flexibility Evaluation Based on Matter‐Element Extension | |
CN110717666A (en) | Market competitiveness evaluation method for enterprise products | |
CN111967684B (en) | Metering asset active distribution method based on big data analysis | |
CN116976948A (en) | Method and system for generating dynamic feedback flow diagram of full value chain of manufacturing enterprise | |
CN116188025A (en) | Screening method, device, equipment and medium of E-commerce platform provider | |
CN115587333A (en) | Failure analysis fault point prediction method and system based on multi-classification model | |
CN114676931A (en) | Electric quantity prediction system based on data relay technology | |
CN113361746A (en) | Power distribution network material class optimization method | |
CN117787569B (en) | Intelligent auxiliary bid evaluation method and system | |
Duan et al. | Risk assessment of complex product supply chain from the perspective of big data | |
CN117436718B (en) | Intelligent data management platform based on multidimensional engine |
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 | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210604 |