CN117557290A - E-business operation and maintenance management method and system based on machine learning - Google Patents
E-business operation and maintenance management method and system based on machine learning Download PDFInfo
- Publication number
- CN117557290A CN117557290A CN202311554714.2A CN202311554714A CN117557290A CN 117557290 A CN117557290 A CN 117557290A CN 202311554714 A CN202311554714 A CN 202311554714A CN 117557290 A CN117557290 A CN 117557290A
- Authority
- CN
- China
- Prior art keywords
- commodity
- sales
- strategy
- profit
- commodity sales
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 64
- 238000007726 management method Methods 0.000 title claims abstract description 31
- 238000010801 machine learning Methods 0.000 title claims abstract description 25
- 238000013210 evaluation model Methods 0.000 claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 31
- 238000012216 screening Methods 0.000 claims abstract description 21
- 238000012417 linear regression Methods 0.000 claims description 34
- 238000004364 calculation method Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 18
- 238000010276 construction Methods 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 10
- 238000007405 data analysis Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 4
- 230000002596 correlated effect Effects 0.000 description 3
- 230000000875 corresponding effect Effects 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G06Q30/02—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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Algebra (AREA)
- Bioinformatics & Computational Biology (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a machine learning-based E-commerce operation and maintenance management method and system, which relate to the technical field of data analysis and comprise the following steps: acquiring historical sales data of commodities in real time; determining influence indexes of each commodity sales strategy on commodity sales and commodity profit; screening a high-influence sales strategy set; determining an inventory of the commodity; constructing commodity sales limiting conditions; generating a plurality of commodity sales strategy execution degree schemes; constructing an E-business operation and maintenance evaluation model; evaluating the execution degree scheme of each commodity sales strategy to obtain an evaluation index; screening an optimal commodity sales strategy execution degree scheme; and downloading the optimal commodity sales strategy execution degree scheme to each E-commerce terminal. The invention has the advantages that: the method can realize the establishment of the optimized commodity sales strategy based on commodity sales and commodity profit, ensure that the commodity sales strategy meets established sales requirements, and provide efficient and accurate information prediction and decision assistance for commodity sales.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to an E-commerce operation and maintenance management method and system based on machine learning.
Background
In the prior art, when an operation and maintenance management scheme of an electronic commerce is formulated, intelligent analysis on correlation between commodity sales strategies and commodity sales volume and commodity profit is lacking, so that the formulation of the operation and maintenance management scheme of the electronic commerce cannot be ensured to obtain optimized commodity sales volume and commodity profit due to the fact that the formulation of the operation and maintenance management scheme of the electronic commerce is often dependent on personal experience of a decision maker, and the determination of the optimized operation and maintenance management scheme is difficult to realize, and the maximum sales data of commodities is generally difficult to ensure.
Disclosure of Invention
In order to solve the technical problems, the technical scheme solves the problems that in the prior art, the optimal operation and maintenance management scheme determination is difficult to realize and the commodity is difficult to ensure to reach the maximum sales data.
In order to achieve the above purpose, the invention adopts the following technical scheme:
an e-commerce operation and maintenance management method based on machine learning comprises the following steps:
acquiring commodity historical sales data in real time, and uploading the commodity historical sales data to a machine learning center, wherein the commodity historical sales data at least comprises commodity sales strategies, commodity sales and commodity profits;
the machine learning center analyzes the commodity historical sales data and determines the influence indexes of each commodity sales strategy on commodity sales and commodity profit;
judging whether the influence index of the commodity sales strategy on commodity sales or commodity profit is larger than a preset value, if so, marking the commodity sales strategy as a sales high-influence weight sales strategy or a profit high-influence weight sales strategy, and if not, marking the commodity sales strategy as a sales low-influence weight sales strategy or a profit low-influence weight sales strategy;
combining all sales high impact weight sales policies and profit high impact weight sales policies into a high impact sales policy set;
determining an inventory of the commodity;
constructing commodity sales limiting conditions based on the inventory of commodities;
under the condition of limiting commodity sales, generating a plurality of commodity sales strategy execution degree schemes;
constructing an E-business operation and maintenance evaluation model;
based on the E-commerce operation and maintenance evaluation model, evaluating the execution degree scheme of each commodity sales strategy to obtain an evaluation index;
screening out the commodity sales strategy execution degree scheme with the maximum evaluation index as an optimal commodity sales strategy execution degree scheme;
and the optimal commodity sales strategy execution degree scheme is downloaded to each E-commerce terminal, and each E-commerce terminal executes the commodity sales strategy according to the set execution degree.
Preferably, the machine learning center analyzes the historical sales data of the commodity, and determining the influence indexes of each commodity sales strategy on commodity sales and commodity profit specifically includes:
screening a plurality of commodity sales and commodity profits when the current commodity sales strategy is executed according to different degrees from historical commodity sales data, and recording the commodity sales and commodity profits as initial training data;
analyzing the initial training data by combining the historical sales data of the commodity to obtain commodity sales or commodity profit change rate when the current commodity sales strategy is executed according to different degrees, wherein the commodity sales or commodity profit change rate is used as standardized data;
based on the standardized data, calculating an influence index between the commodity sales strategy and commodity sales or commodity profit through a correlation calculation formula.
Preferably, the correlation calculation formula specifically includes:
wherein R is an influence index between commodity sales strategy and commodity sales or commodity profit, n is the total number of standardized data, and V j For the execution degree of commodity sales strategy in the j-th standardized data, p j For commodity sales or commodity profit margin change rate in jth standardized data, S p Is the standard deviation of the execution degree of the commodity sales strategy in the standardized data, S V Is standardized toStandard deviation of commodity sales or commodity profit change rate in the data.
Preferably, the analyzing the initial training data in combination with the historical sales data of the commodity to obtain commodity sales or commodity profit change rate when executing the current commodity sales strategy according to different degrees specifically includes:
acquiring all other commodity sales strategies executed at the moment corresponding to the initial training data of each execution degree of the commodity sales strategy, and marking the commodity sales strategies as comparison commodity sales strategies;
screening a plurality of comparison moments which are provided with and only execute comparison commodity sales strategies from historical commodity sales data, and determining commodity sales and commodity profits at the comparison moments;
averaging commodity sales and commodity profit at a plurality of comparison moments to obtain comparison standard data;
calculating commodity sales and commodity profit change rate according to a standardized calculation formula based on the initial training data and the comparison standard data;
the standardized calculation formula specifically comprises the following steps:
wherein p is commodity sales or commodity profit change rate, x is initial training data, x 0 Is the comparison standard data.
Preferably, the building commodity sales limiting conditions based on the commodity inventory specifically includes:
establishing a linear regression prediction model between the execution degree of each sales volume high-influence weight sales strategy and the commodity sales promotion rate, and marking the linear regression prediction model as a sales volume promotion regression prediction model;
lifting the regression prediction model and the inventory of the commodity based on the sales volume, and constructing commodity sales volume limiting conditions;
the commodity sales limit conditions are as follows:
wherein X is 0 For the basic sales of goods, M is the total number of the sales strategies with high influence weight,b for a linear regression prediction model between the execution degree of the first high impact weight sales strategy and the commodity sales promotion rate vl For the execution degree of the sales strategy with the high influence weight of the first sales quantity, K 0 Is an inventory of goods.
Preferably, the building the e-commerce operation and maintenance evaluation model specifically includes:
establishing a linear regression prediction model between the execution degree of each high-influence weight sales strategy and the commodity profit enhancement rate, and marking the linear regression prediction model as a profit enhancement regression prediction model;
determining the unit storage cost of the commodity;
constructing an e-commerce operation and maintenance evaluation model based on the profit lifting regression prediction model, the sales lifting regression prediction model and the storage cost of the commodity;
the electric Shang Yunwei evaluation model is:
wherein Y is an evaluation index, Q 1 To synthesize profit index, Q 2 To comprehensively store index, W 0 For the basic profit of the commodity,and storing the cost for units of the commodity for a linear regression prediction model between the execution degree of the first high-influence weight sales strategy and the commodity profit raising rate.
Further, an e-commerce operation and maintenance management system based on machine learning is provided, which is used for implementing the e-commerce operation and maintenance management method based on machine learning, and includes:
the electronic commerce terminal is used for executing a commodity sales strategy;
the data acquisition module is electrically connected with the e-commerce terminal, and is used for acquiring commodity historical sales data in real time and uploading the commodity historical sales data to a machine learning center;
the machine learning center is in communication connection with the data acquisition module in a wired or wireless mode, analyzes commodity historical sales data, determines influence indexes of each commodity sales strategy on commodity sales and commodity profit, judges whether the influence indexes of the commodity sales strategy on commodity sales or commodity profit are larger than a preset value, if so, marks the commodity sales strategy as sales strategies with high sales influence weight or sales strategies with high profit influence weight, if not, marks the commodity sales strategy as sales strategies with low sales influence weight or sales strategies with low profit influence weight, and combines all sales strategies with high sales influence weight into a high-influence sales strategy set;
the condition limiting module is used for constructing commodity sales limiting conditions based on the inventory of commodities and generating a plurality of commodity sales strategy execution degree schemes under the commodity sales limiting conditions;
the scheme evaluation module is electrically connected with the condition limiting module and is used for constructing an e-commerce operation and maintenance evaluation model, evaluating each commodity sales strategy execution degree scheme based on the e-commerce operation and maintenance evaluation model to obtain an evaluation index, and screening out the commodity sales strategy execution degree scheme with the maximum evaluation index as an optimal commodity sales strategy execution degree scheme;
the terminal operation and maintenance module is electrically connected with the scheme evaluation module and is used for downloading the optimal commodity sales strategy execution degree scheme to all the E-commerce terminals, and all the E-commerce terminals execute the commodity sales strategy according to the set execution degree.
Optionally, the machine learning center includes:
the first calculation unit is used for analyzing the commodity historical sales data and determining influence indexes of each commodity sales strategy on commodity sales and commodity profit;
the judging unit is used for judging whether the influence index of the commodity sales strategy on commodity sales or commodity profit is larger than a preset value, if so, marking the commodity sales strategy as a sales high-influence weight sales strategy or a profit high-influence weight sales strategy, and if not, marking the commodity sales strategy as a sales low-influence weight sales strategy or a profit low-influence weight sales strategy;
and the integration unit is used for combining all sales high-influence weight sales strategies and profit high-influence weight sales strategies into a high-influence sales strategy set.
Optionally, the condition limiting module includes:
the first regression unit is used for establishing a linear regression prediction model between the execution degree of each sales volume high-influence weight sales strategy and the commodity sales promotion rate, and marking the linear regression prediction model as a sales volume promotion regression prediction model;
the limitation construction unit is used for constructing commodity sales limiting conditions based on sales promotion regression prediction models and commodity inventory;
the scheme generation unit is used for generating a plurality of commodity sales strategy execution degree schemes under commodity sales limit conditions.
Optionally, the solution evaluation module includes:
the second regression unit is used for establishing a linear regression prediction model between the execution degree of each high-influence weight sales strategy and the commodity profit lifting rate, and marking the linear regression prediction model as a profit lifting regression prediction model;
the evaluation model unit is used for constructing an e-commerce operation and maintenance evaluation model based on the profit promotion regression prediction model, the sales promotion regression prediction model and the storage cost of the commodity;
the second calculation unit is used for respectively evaluating the execution degree scheme of each commodity sales strategy based on the E-commerce operation and maintenance evaluation model to obtain an evaluation index;
and the screening unit is used for screening out the commodity sales strategy execution degree scheme with the maximum evaluation index as the optimal commodity sales strategy execution degree scheme.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides an E-commerce operation and maintenance management method based on machine learning, which is characterized in that a plurality of high-influence sales strategy sets related to commodity sales and commodity profit are screened out through analysis of commodity historical sales data, comprehensive demands of commodity sales and commodity profit are intelligently analyzed based on commodity inventory, the execution degree of commodity sales strategies is intelligently analyzed based on the comprehensive demands of commodity sales and commodity profit, and operation and maintenance management of a finger-commerce is performed.
Drawings
FIG. 1 is a flow chart of a method for managing E-business operation and maintenance based on machine learning;
FIG. 2 is a flow chart of a method for determining the impact index of each commodity sales strategy on commodity sales and commodity profit according to the present invention;
FIG. 3 is a flow chart of a method of determining normalized data in the present invention;
FIG. 4 is a flow chart of a method of constructing commodity sales constraints in accordance with the present invention;
FIG. 5 is a flowchart of a method for constructing an E-business operation and maintenance evaluation model in the invention;
fig. 6 is a block diagram of a machine learning-based e-commerce operation and maintenance management system according to the present invention.
Detailed Description
The following description is presented to enable one of ordinary skill in the art to make and use the invention. The preferred embodiments in the following description are by way of example only and other obvious variations will occur to those skilled in the art.
Referring to fig. 1, an e-commerce operation and maintenance management method based on machine learning includes:
acquiring commodity historical sales data in real time, and uploading the commodity historical sales data to a machine learning center, wherein the commodity historical sales data at least comprises commodity sales strategies, commodity sales and commodity profits;
the machine learning center analyzes the commodity historical sales data and determines the influence indexes of each commodity sales strategy on commodity sales and commodity profit;
judging whether the influence index of the commodity sales strategy on commodity sales or commodity profit is larger than a preset value, if so, marking the commodity sales strategy as a sales high-influence weight sales strategy or a profit high-influence weight sales strategy, and if not, marking the commodity sales strategy as a sales low-influence weight sales strategy or a profit low-influence weight sales strategy;
combining all sales high impact weight sales policies and profit high impact weight sales policies into a high impact sales policy set;
determining an inventory of the commodity;
constructing commodity sales limiting conditions based on the inventory of commodities;
under the condition of limiting commodity sales, generating a plurality of commodity sales strategy execution degree schemes;
constructing an E-business operation and maintenance evaluation model;
based on the E-commerce operation and maintenance evaluation model, evaluating the execution degree scheme of each commodity sales strategy to obtain an evaluation index;
screening out the commodity sales strategy execution degree scheme with the maximum evaluation index as an optimal commodity sales strategy execution degree scheme;
and the optimal commodity sales strategy execution degree scheme is downloaded to each E-commerce terminal, and each E-commerce terminal executes the commodity sales strategy according to the set execution degree.
According to the scheme, through analysis of historical commodity sales data, a plurality of high-influence sales strategy sets related to commodity sales volume and commodity profit are screened out, comprehensive demands of commodity sales volume and commodity profit are intelligently analyzed based on inventory of commodities, execution degree of sales strategies of commodities is intelligently analyzed based on comprehensive demands of commodity sales volume and commodity profit, and operation and maintenance management of a finger-conduction merchant is performed.
Referring to fig. 2, the machine learning center analyzes the historical sales data of the commodity, and determining the influence indexes of each commodity sales strategy on the commodity sales and the commodity profit specifically includes:
screening a plurality of commodity sales and commodity profits when the current commodity sales strategy is executed according to different degrees from historical commodity sales data, and recording the commodity sales and commodity profits as initial training data;
analyzing the initial training data by combining the historical sales data of the commodity to obtain commodity sales or commodity profit change rate when the current commodity sales strategy is executed according to different degrees, wherein the commodity sales or commodity profit change rate is used as standardized data;
based on the standardized data, calculating an influence index between the commodity sales strategy and commodity sales or commodity profit through a correlation calculation formula.
Preferably, the correlation calculation formula specifically includes:
wherein R is an influence index between commodity sales strategy and commodity sales or commodity profit, n is the total number of standardized data, and V j For the execution degree of commodity sales strategy in the j-th standardized data, p j For commodity sales or commodity profit margin change rate in jth standardized data, S p Is the standard deviation of the execution degree of the commodity sales strategy in the standardized data, S V Is the standard deviation of commodity sales or commodity profit change rate in the standardized data.
It can be understood that the influence of different sales strategies on commodity sales and commodity profit is different, for example, the discount strategy is positively correlated with commodity sales, the advertisement strategy is positively correlated with commodity sales and negatively correlated with sales profit, so in the scheme, by calculating the correlation of each sales strategy on commodity sales and commodity profit as an influence index, the sales strategy with large influence on commodity sales and commodity profit can be rapidly and accurately identified as a high influence weight sales strategy.
Referring to fig. 3, the method for analyzing the initial training data in combination with the historical sales data of the commodity to obtain commodity sales or commodity profit margin variation rate when executing the current commodity sales strategy according to different degrees specifically includes, as standardized data:
acquiring all other commodity sales strategies executed at the moment corresponding to the initial training data of each execution degree of the commodity sales strategy, and marking the commodity sales strategies as comparison commodity sales strategies;
screening a plurality of comparison moments which are provided with and only execute comparison commodity sales strategies from historical commodity sales data, and determining commodity sales and commodity profits at the comparison moments;
averaging commodity sales and commodity profit at a plurality of comparison moments to obtain comparison standard data;
calculating commodity sales and commodity profit change rate according to a standardized calculation formula based on the initial training data and the comparison standard data;
the standardized calculation formula specifically comprises the following steps:
wherein p is commodity sales or commodity profit change rate, x is initial training data, x 0 Is the comparison standard data.
It can be understood that, because the commodity sales process is usually executed simultaneously by multiple strategies, when single strategy analysis is performed, the influence of other strategies needs to be removed, therefore, in the scheme, the commodity sales strategy is adopted to perform correlation calculation by taking commodity sales quantity or commodity profit change rate as an index, the influence of other strategies on commodity sales quantity or commodity profit change rate can be effectively reduced, and the accuracy of influence index calculation is ensured.
Referring to fig. 4, constructing commodity sales restriction conditions based on the inventory of commodities specifically includes:
establishing a linear regression prediction model between the execution degree of each sales volume high-influence weight sales strategy and the commodity sales promotion rate, and marking the linear regression prediction model as a sales volume promotion regression prediction model;
lifting the regression prediction model and the inventory of the commodity based on the sales volume, and constructing commodity sales volume limiting conditions;
the commodity sales limit conditions are as follows:
wherein X is 0 For the basic sales of goods, M is the total number of the sales strategies with high influence weight,b for a linear regression prediction model between the execution degree of the first high impact weight sales strategy and the commodity sales promotion rate vl For the execution degree of the sales strategy with the high influence weight of the first sales quantity, K 0 Is an inventory of goods.
Referring to fig. 5, constructing an e-commerce operation and maintenance evaluation model specifically includes:
establishing a linear regression prediction model between the execution degree of each high-influence weight sales strategy and the commodity profit enhancement rate, and marking the linear regression prediction model as a profit enhancement regression prediction model;
determining the unit storage cost of the commodity;
constructing an e-commerce operation and maintenance evaluation model based on the profit lifting regression prediction model, the sales lifting regression prediction model and the storage cost of the commodity;
the electric Shang Yunwei evaluation model is:
wherein Y is an evaluationPrice index, Q 1 To synthesize profit index, Q 2 To comprehensively store index, W 0 For the basic profit of the commodity,and storing the cost for units of the commodity for a linear regression prediction model between the execution degree of the first high-influence weight sales strategy and the commodity profit raising rate.
In the scheme, commodity sales limit conditions are built based on commodity inventory, so that under the execution of a high-influence weight sales strategy, commodity sales can not be subjected to the condition of explosion, meanwhile, an electronic commerce operation and maintenance evaluation model is built based on the total sales income of commodities, the execution degree of the high-influence weight sales strategy which enables the total sales income to be maximum is screened out, and the implementation degree of the high-influence weight sales strategy is used as an optimal commodity sales strategy execution degree scheme, so that the formulated optimal commodity sales strategy can be effectively ensured to realize the maximum promotion of the total sales income
Further, referring to fig. 6, based on the same inventive concept as the above-mentioned e-commerce operation and maintenance management method based on machine learning, the present disclosure further provides an e-commerce operation and maintenance management system based on machine learning, including:
the electronic commerce terminal is used for executing a commodity sales strategy;
the data acquisition module is electrically connected with the e-commerce terminal, and is used for acquiring commodity historical sales data in real time and uploading the commodity historical sales data to a machine learning center;
the machine learning center is in communication connection with the data acquisition module in a wired or wireless mode, analyzes commodity historical sales data, determines influence indexes of each commodity sales strategy on commodity sales and commodity profit, judges whether the influence indexes of the commodity sales strategy on commodity sales or commodity profit are larger than a preset value, if so, marks the commodity sales strategy as sales strategies with high sales influence weight or sales strategies with high profit influence weight, if not, marks the commodity sales strategy as sales strategies with low sales influence weight or sales strategies with low profit influence weight, and combines all sales strategies with high sales influence weight into a high-influence sales strategy set;
the condition limiting module is used for constructing commodity sales limiting conditions based on the inventory of commodities and generating a plurality of commodity sales strategy execution degree schemes under the commodity sales limiting conditions;
the scheme evaluation module is electrically connected with the condition limiting module and is used for constructing an e-commerce operation and maintenance evaluation model, evaluating each commodity sales strategy execution degree scheme based on the e-commerce operation and maintenance evaluation model to obtain an evaluation index, and screening out the commodity sales strategy execution degree scheme with the maximum evaluation index as an optimal commodity sales strategy execution degree scheme;
the terminal operation and maintenance module is electrically connected with the scheme evaluation module and is used for downloading the optimal commodity sales strategy execution degree scheme to all the E-commerce terminals, and all the E-commerce terminals execute the commodity sales strategy according to the set execution degree.
The machine learning center includes:
the first calculation unit is used for analyzing the commodity historical sales data and determining influence indexes of each commodity sales strategy on commodity sales and commodity profit;
the judging unit is used for judging whether the influence index of the commodity sales strategy on commodity sales or commodity profit is larger than a preset value, if so, marking the commodity sales strategy as a sales high-influence weight sales strategy or a profit high-influence weight sales strategy, and if not, marking the commodity sales strategy as a sales low-influence weight sales strategy or a profit low-influence weight sales strategy;
and the integration unit is used for combining all sales high-influence weight sales strategies and profit high-influence weight sales strategies into a high-influence sales strategy set.
The condition limiting module includes:
the first regression unit is used for establishing a linear regression prediction model between the execution degree of each sales volume high-influence weight sales strategy and the commodity sales promotion rate, and marking the linear regression prediction model as a sales volume promotion regression prediction model;
the limitation construction unit is used for constructing commodity sales limiting conditions based on sales promotion regression prediction models and commodity inventory;
the scheme generation unit is used for generating a plurality of commodity sales strategy execution degree schemes under commodity sales limit conditions.
The scheme evaluation module comprises:
the second regression unit is used for establishing a linear regression prediction model between the execution degree of each high-influence weight sales strategy and the commodity profit lifting rate, and marking the linear regression prediction model as a profit lifting regression prediction model;
the evaluation model unit is used for constructing an e-commerce operation and maintenance evaluation model based on the profit promotion regression prediction model, the sales promotion regression prediction model and the storage cost of the commodity;
the second calculation unit is used for respectively evaluating the execution degree scheme of each commodity sales strategy based on the E-commerce operation and maintenance evaluation model to obtain an evaluation index;
and the screening unit is used for screening out the commodity sales strategy execution degree scheme with the maximum evaluation index as the optimal commodity sales strategy execution degree scheme.
The using process of the e-commerce operation and maintenance management system based on machine learning is as follows:
step one: the data acquisition module acquires commodity historical sales data in real time and uploads the commodity historical sales data to the machine learning center;
step two: the first calculation unit analyzes the commodity historical sales data and determines the influence indexes of each commodity sales strategy on commodity sales volume and commodity profit;
step three: the judging unit is used for judging whether the influence index of the commodity sales strategy on commodity sales or commodity profit is larger than a preset value, if so, the commodity sales strategy is marked as a sales high-influence weight sales strategy or a profit high-influence weight sales strategy, and if not, the commodity sales strategy is marked as a sales low-influence weight sales strategy or a profit low-influence weight sales strategy;
step four: the integration unit merges all sales high-influence weight sales strategies and profit high-influence weight sales strategies into a high-influence sales strategy set;
step five: the first regression unit establishes a linear regression prediction model between the execution degree of each sales volume high-influence weight sales strategy and the commodity sales promotion rate, and marks the linear regression prediction model as a sales volume promotion regression prediction model;
step six: the limitation construction unit is used for constructing commodity sales limiting conditions based on sales promotion regression prediction models and commodity inventory;
step seven: the scheme generating unit generates a plurality of commodity sales strategy execution degree schemes under commodity sales limit conditions;
step eight: the second regression unit establishes a linear regression prediction model between the execution degree of each high-influence weight sales strategy and the commodity profit lifting rate, and marks the linear regression prediction model as a profit lifting regression prediction model;
step nine: the evaluation model unit builds an e-commerce operation and maintenance evaluation model based on the profit lifting regression prediction model, the sales lifting regression prediction model and the storage cost of the commodity;
step ten: the screening unit screens out the commodity sales strategy execution degree scheme with the maximum evaluation index as the optimal commodity sales strategy execution degree scheme;
step eleven: and the terminal operation and maintenance module downloads the optimal commodity sales strategy execution degree scheme to each E-commerce terminal, and each E-commerce terminal executes the commodity sales strategy according to the set execution degree.
In summary, the invention has the advantages that: the method can realize the establishment of the optimized commodity sales strategy based on commodity sales and commodity profit, ensure that the commodity sales strategy meets established sales requirements, and provide efficient and accurate information prediction and decision assistance for commodity sales.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made therein without departing from the spirit and scope of the invention, which is defined by the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. The E-commerce operation and maintenance management method based on machine learning is characterized by comprising the following steps of:
acquiring commodity historical sales data in real time, and uploading the commodity historical sales data to a machine learning center, wherein the commodity historical sales data at least comprises commodity sales strategies, commodity sales and commodity profits;
the machine learning center analyzes the commodity historical sales data and determines the influence indexes of each commodity sales strategy on commodity sales and commodity profit;
judging whether the influence index of the commodity sales strategy on commodity sales or commodity profit is larger than a preset value, if so, marking the commodity sales strategy as a sales high-influence weight sales strategy or a profit high-influence weight sales strategy, and if not, marking the commodity sales strategy as a sales low-influence weight sales strategy or a profit low-influence weight sales strategy;
combining all sales high impact weight sales policies and profit high impact weight sales policies into a high impact sales policy set;
determining an inventory of the commodity;
constructing commodity sales limiting conditions based on the inventory of commodities;
under the condition of limiting commodity sales, generating a plurality of commodity sales strategy execution degree schemes;
constructing an E-business operation and maintenance evaluation model;
based on the E-commerce operation and maintenance evaluation model, evaluating the execution degree scheme of each commodity sales strategy to obtain an evaluation index;
screening out the commodity sales strategy execution degree scheme with the maximum evaluation index as an optimal commodity sales strategy execution degree scheme;
and the optimal commodity sales strategy execution degree scheme is downloaded to each E-commerce terminal, and each E-commerce terminal executes the commodity sales strategy according to the set execution degree.
2. The machine learning-based e-commerce operation and maintenance management method of claim 1, wherein the machine learning center analyzes the historical sales data of the commodity, and determining the impact index of each commodity sales policy on the sales volume and the profit of the commodity specifically comprises:
screening a plurality of commodity sales and commodity profits when the current commodity sales strategy is executed according to different degrees from historical commodity sales data, and recording the commodity sales and commodity profits as initial training data;
analyzing the initial training data by combining the historical sales data of the commodity to obtain commodity sales or commodity profit change rate when the current commodity sales strategy is executed according to different degrees, wherein the commodity sales or commodity profit change rate is used as standardized data;
based on the standardized data, calculating an influence index between the commodity sales strategy and commodity sales or commodity profit through a correlation calculation formula.
3. The machine learning-based e-commerce operation and maintenance management method of claim 2, wherein the correlation calculation formula is specifically:
wherein R is an influence index between commodity sales strategy and commodity sales or commodity profit, n is the total number of standardized data, and V j For the execution degree of commodity sales strategy in the j-th standardized data, p j For commodity sales or commodity profit margin change rate in jth standardized data, S p Is the standard deviation of the execution degree of the commodity sales strategy in the standardized data, S V Is the standard deviation of commodity sales or commodity profit change rate in the standardized data.
4. The machine learning-based e-commerce operation and maintenance management method of claim 3, wherein the analyzing the initial training data in combination with the historical sales data of the commodity to obtain the commodity sales amount or commodity profit change rate when the current commodity sales policy is executed according to different degrees specifically includes, as the standardized data:
acquiring all other commodity sales strategies executed at the moment corresponding to the initial training data of each execution degree of the commodity sales strategy, and marking the commodity sales strategies as comparison commodity sales strategies;
screening a plurality of comparison moments which are provided with and only execute comparison commodity sales strategies from historical commodity sales data, and determining commodity sales and commodity profits at the comparison moments;
averaging commodity sales and commodity profit at a plurality of comparison moments to obtain comparison standard data;
calculating commodity sales and commodity profit change rate according to a standardized calculation formula based on the initial training data and the comparison standard data;
the standardized calculation formula specifically comprises the following steps:
wherein p is commodity sales or commodity profit change rate, x is initial training data, x 0 Is the comparison standard data.
5. The machine learning-based e-commerce operation and maintenance management method of claim 4, wherein the building commodity sales restriction conditions based on the commodity inventory specifically comprises:
establishing a linear regression prediction model between the execution degree of each sales volume high-influence weight sales strategy and the commodity sales promotion rate, and marking the linear regression prediction model as a sales volume promotion regression prediction model;
lifting the regression prediction model and the inventory of the commodity based on the sales volume, and constructing commodity sales volume limiting conditions;
the commodity sales limit conditions are as follows:
wherein X is 0 For the basic sales of goods, M is the total number of the sales strategies with high influence weight,b for a linear regression prediction model between the execution degree of the first high impact weight sales strategy and the commodity sales promotion rate vl For the execution degree of the sales strategy with the high influence weight of the first sales quantity, K 0 Is an inventory of goods.
6. The machine learning-based e-commerce operation and maintenance management method of claim 5, wherein the constructing the e-commerce operation and maintenance evaluation model specifically comprises:
establishing a linear regression prediction model between the execution degree of each high-influence weight sales strategy and the commodity profit enhancement rate, and marking the linear regression prediction model as a profit enhancement regression prediction model;
determining the unit storage cost of the commodity;
constructing an e-commerce operation and maintenance evaluation model based on the profit lifting regression prediction model, the sales lifting regression prediction model and the storage cost of the commodity;
the electric Shang Yunwei evaluation model is:
wherein Y is an evaluation index, Q 1 To synthesize profit index, Q 2 Is a healdStore index, W 0 For the basic profit of the commodity,and storing the cost for units of the commodity for a linear regression prediction model between the execution degree of the first high-influence weight sales strategy and the commodity profit raising rate.
7. A machine learning-based e-commerce operation and maintenance management system, configured to implement the machine learning-based e-commerce operation and maintenance management method according to any one of claims 1 to 6, comprising:
the electronic commerce terminal is used for executing a commodity sales strategy;
the data acquisition module is electrically connected with the e-commerce terminal, and is used for acquiring commodity historical sales data in real time and uploading the commodity historical sales data to a machine learning center;
the machine learning center is in communication connection with the data acquisition module in a wired or wireless mode, analyzes commodity historical sales data, determines influence indexes of each commodity sales strategy on commodity sales and commodity profit, judges whether the influence indexes of the commodity sales strategy on commodity sales or commodity profit are larger than a preset value, if so, marks the commodity sales strategy as sales strategies with high sales influence weight or sales strategies with high profit influence weight, if not, marks the commodity sales strategy as sales strategies with low sales influence weight or sales strategies with low profit influence weight, and combines all sales strategies with high sales influence weight into a high-influence sales strategy set;
the condition limiting module is used for constructing commodity sales limiting conditions based on the inventory of commodities and generating a plurality of commodity sales strategy execution degree schemes under the commodity sales limiting conditions;
the scheme evaluation module is electrically connected with the condition limiting module and is used for constructing an e-commerce operation and maintenance evaluation model, evaluating each commodity sales strategy execution degree scheme based on the e-commerce operation and maintenance evaluation model to obtain an evaluation index, and screening out the commodity sales strategy execution degree scheme with the maximum evaluation index as an optimal commodity sales strategy execution degree scheme;
the terminal operation and maintenance module is electrically connected with the scheme evaluation module and is used for downloading the optimal commodity sales strategy execution degree scheme to all the E-commerce terminals, and all the E-commerce terminals execute the commodity sales strategy according to the set execution degree.
8. The machine learning based e-commerce operation and maintenance management system of claim 7 wherein the machine learning center comprises:
the first calculation unit is used for analyzing the commodity historical sales data and determining influence indexes of each commodity sales strategy on commodity sales and commodity profit;
the judging unit is used for judging whether the influence index of the commodity sales strategy on commodity sales or commodity profit is larger than a preset value, if so, marking the commodity sales strategy as a sales high-influence weight sales strategy or a profit high-influence weight sales strategy, and if not, marking the commodity sales strategy as a sales low-influence weight sales strategy or a profit low-influence weight sales strategy;
and the integration unit is used for combining all sales high-influence weight sales strategies and profit high-influence weight sales strategies into a high-influence sales strategy set.
9. The machine learning based e-commerce operation and maintenance management system of claim 7 wherein the condition limiting module comprises:
the first regression unit is used for establishing a linear regression prediction model between the execution degree of each sales volume high-influence weight sales strategy and the commodity sales promotion rate, and marking the linear regression prediction model as a sales volume promotion regression prediction model;
the limitation construction unit is used for constructing commodity sales limiting conditions based on sales promotion regression prediction models and commodity inventory;
the scheme generation unit is used for generating a plurality of commodity sales strategy execution degree schemes under commodity sales limit conditions.
10. The machine learning based e-commerce operation and maintenance management system of claim 7, wherein the solution evaluation module comprises:
the second regression unit is used for establishing a linear regression prediction model between the execution degree of each high-influence weight sales strategy and the commodity profit lifting rate, and marking the linear regression prediction model as a profit lifting regression prediction model;
the evaluation model unit is used for constructing an e-commerce operation and maintenance evaluation model based on the profit promotion regression prediction model, the sales promotion regression prediction model and the storage cost of the commodity;
the second calculation unit is used for respectively evaluating the execution degree scheme of each commodity sales strategy based on the E-commerce operation and maintenance evaluation model to obtain an evaluation index;
and the screening unit is used for screening out the commodity sales strategy execution degree scheme with the maximum evaluation index as the optimal commodity sales strategy execution degree scheme.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311554714.2A CN117557290A (en) | 2023-11-21 | 2023-11-21 | E-business operation and maintenance management method and system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311554714.2A CN117557290A (en) | 2023-11-21 | 2023-11-21 | E-business operation and maintenance management method and system based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117557290A true CN117557290A (en) | 2024-02-13 |
Family
ID=89820140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311554714.2A Pending CN117557290A (en) | 2023-11-21 | 2023-11-21 | E-business operation and maintenance management method and system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117557290A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117934048A (en) * | 2024-03-14 | 2024-04-26 | 深圳美云集网络科技有限责任公司 | E-commerce commodity sales analysis method and system |
-
2023
- 2023-11-21 CN CN202311554714.2A patent/CN117557290A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117934048A (en) * | 2024-03-14 | 2024-04-26 | 深圳美云集网络科技有限责任公司 | E-commerce commodity sales analysis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110473083B (en) | Tree risk account identification method, device, server and storage medium | |
| CN111652657A (en) | Commodity sales prediction method and device, electronic equipment and readable storage medium | |
| CN107424070A (en) | A kind of loan user credit ranking method and system based on machine learning | |
| CN107818344A (en) | The method and system that user behavior is classified and predicted | |
| CN110956273A (en) | Credit scoring method and system integrating multiple machine learning models | |
| CN108711107A (en) | Intelligent financing services recommend method and its system | |
| CN117557290A (en) | E-business operation and maintenance management method and system based on machine learning | |
| CN106875206A (en) | Acquisition of information, assessment, questionnaire method, device and server | |
| CN106296669A (en) | A kind of image quality evaluating method and device | |
| CN105528465A (en) | Credit status assessment method and device | |
| CN113469730A (en) | Customer repurchase prediction method and device based on RF-LightGBM fusion model under non-contract scene | |
| CN110472695A (en) | A kind of the unusual service condition detection and classification method of industrial processes | |
| CN116452121B (en) | Intelligent enterprise inventory management system and management platform | |
| CN109345371A (en) | Personal reference report backtracking method and system | |
| CN116644984A (en) | Reliability evaluation method, device, equipment and storage medium for electric power optical communication network | |
| CN108492169A (en) | Risk Modeling method and system based on credit card approval scene are realized | |
| Singha et al. | Application of different machine learning models for supply chain demand forecasting: comparative analysis | |
| US20210117828A1 (en) | Information processing apparatus, information processing method, and program | |
| CN114970357A (en) | Energy-saving effect evaluation method, system, device and storage medium | |
| CN114139065A (en) | Talent screening and recommending method and system based on big data and readable storage medium | |
| CN109034552A (en) | Towards the uncertain socialization's manufacturing service matching process of supply and demand and system | |
| KR102406375B1 (en) | An electronic device including evaluation operation of originated technology | |
| CN112150179A (en) | Information pushing method and device | |
| CN116170330A (en) | Service package recommendation method and device and electronic equipment | |
| CN116167646A (en) | Evaluation method, device, equipment and storage medium based on transaction algorithm |
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 |