CN114971747A - Data analysis method and system based on big data commodity accurate marketing - Google Patents
Data analysis method and system based on big data commodity accurate marketing Download PDFInfo
- Publication number
- CN114971747A CN114971747A CN202210826883.6A CN202210826883A CN114971747A CN 114971747 A CN114971747 A CN 114971747A CN 202210826883 A CN202210826883 A CN 202210826883A CN 114971747 A CN114971747 A CN 114971747A
- Authority
- CN
- China
- Prior art keywords
- commodity
- data
- marketing
- target
- classification
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
Abstract
The invention relates to the technical field of commodity marketing, and discloses a data analysis method based on big data commodity accurate marketing, which comprises the following steps: s100, acquiring commodity data of a target commodity; s200, automatically determining a target user group according to the commodity data; s300, automatically determining a marketing model according to the commodity data and the target user group; s400, obtaining sales data; s500, determining the marketing effect of the marketing model according to the sales data; s600, the marketing model is adjusted according to the marketing effect, the commodity classification labels can be determined according to the commodity characteristics embodied by the commodity data, the shopping demands of the users can be analyzed in advance to obtain the corresponding user classification labels, a target user group can be found according to the corresponding relation between the commodity classification labels and the user classification labels, the corresponding marketing model is selected, after marketing output, the sales data of the target commodities are obtained, the effect is monitored and tracked, and after activities, re-inventory and optimization are carried out, so that the purpose of accurate marketing is achieved.
Description
Technical Field
The invention relates to the technical field of commodity marketing, in particular to a data analysis method and system based on big data commodity accurate marketing.
Background
With the rapid development of the internet technology, the entity marketing mode in the past day is gradually expanded to a mode in which network marketing and entity marketing are mutually matched, and with the expansion of marketing roads, the management and control of commodity marketing are gradually fussy.
Marketing refers to the enterprise discovery or excavates accurate consumer demand, removes to promote and sell the product from the construction of whole atmosphere and the construction of self product form, mainly digs the connotation of product deeply, accords with accurate consumer's demand to let the consumer understand the process that this product and then purchase deeply.
Under the condition of large commodity quantity, if commodity information which is popular at present in a current time period cannot be effectively predicted, when the commodity is in shortage, a merchant often cannot provide a second commodity at the first time to miss the commercial opportunity and the market, when the commodity is subsequently replenished, the commodity may have already reduced heat, the quantity of the commodity on the market is larger than that of the commodity, at the moment, some commodities stored in a warehouse cannot be effectively processed after being lost, the useless benefit and the occupied space of the warehouse are increased, and the merchant may have serious economic loss.
Therefore, big data marketing is produced, generally based on a large amount of data of multiple platforms, and applied to a marketing mode of the internet advertising industry on the basis of big data technology, and the core of the marketing is to enable network advertisements to be delivered to suitable people in a suitable mode through a suitable carrier at a suitable time. However, under the condition of insufficient analysis data, errors are easy to occur only by manually collecting and analyzing data, the workload is large, effective management and control cannot be achieved, online popularization cannot be conveniently known, whether offline purchase is affected or not cannot be conveniently achieved, high-quality potential customers cannot be conveniently found, and the purpose of sales promotion cannot be achieved.
Disclosure of Invention
The invention aims to provide a data analysis method and a data analysis system based on accurate marketing of big data commodities, which solve the following technical problems:
how to provide a method capable of improving marketing accuracy and degree of automation.
The purpose of the invention can be realized by the following technical scheme:
a data analysis method based on big data commodity accurate marketing comprises the following steps:
s100, acquiring commodity data of a target commodity;
s200, automatically determining a target user group according to the commodity data;
s300, automatically determining a marketing model according to the commodity data and the target user group;
s400, obtaining sales data;
s500, determining the marketing effect of the marketing model according to the sales data;
s600, adjusting the marketing model according to the marketing effect.
According to the technical scheme, the commodity classification labels can be determined according to the commodity characteristics embodied by the commodity data, the shopping demands of the users can be analyzed in advance to obtain the corresponding user classification labels, the target user groups can be found according to the corresponding relation between the commodity classification labels and the user classification labels, corresponding marketing models are selected, marketing output is carried out, the sales data of the target commodities are obtained, effects are monitored and tracked, re-inventory and optimization are carried out after activities, and the purpose of accurate marketing is achieved.
As a further scheme of the invention: before the step S100, the method further includes:
s001, collecting and acquiring commercial data;
s002, establishing a commodity label library corresponding to the commodity label system;
s003, establishing a customer label library corresponding to the customer label system;
s004, establishing a marketing model library;
wherein the business data comprises the commodity data, customer data, order data; the commodity label system is a set of commodity classification labels corresponding to different commodities; the client label system is a set of client classification labels corresponding to different clients.
According to the technical scheme, the commodity data, the customer data and the order data are collected for analysis and diagnosis, the positioning of the commodity data is analyzed, the corresponding customer groups and the corresponding potential customer groups are found, the customers are classified and labeled through the order data of the customer groups and the potential customer groups, and the overall analysis is carried out to carry out accurate and effective marketing activities according to the classification of the customers and related products.
As a further scheme of the invention: the step S500 includes:
counting the repeated purchasing parameters in the target customer group within a preset time;
calculating the commodity dependence score of the target user according to the re-purchasing parameter;
the re-purchasing parameters comprise the re-purchasing frequency and single consumption amount of the target commodity purchased by the target customers in the target customer group and the re-purchasing time interval;
the higher the commodity dependence score, the better the marketing effect of the marketing model.
Through the technical scheme, the repeated purchasing frequency reflects the viscosity between the user and the target commodity, and the word consumption amount and the repeated purchasing time interval can reflect the demand of the user.
As a further scheme of the invention: the commodity classification label comprises basic attributes, interactive behaviors, adaptation scenes, supply chain attributes and commodity values;
the basic attributes comprise the shape and color characteristics of the commodity, and the interactive behaviors comprise click quantity, browsing quantity and commodity quantity of the corresponding commodity.
As a further scheme of the invention: the client label system comprises key attributes, interest labels, social characteristic labels and expense labels;
the key attributes comprise gender, age, education level, year and month of birth, industry engagement, constellation;
the interest tags comprise interest, browsing/collecting goods, interactive contents, brand preferences and product preferences;
the social characteristic labels comprise marital conditions and family environments;
the spending label includes income status, purchasing power level.
As a further scheme of the invention: the step S100 includes:
acquiring a commodity graph group of the target commodity; the commodity picture group comprises commodity pictures;
inputting the commodity pictures in the commodity picture group into a classification model;
determining the commodity data according to the classification result output by the classification model;
and the classification model is a trained neural network model.
By the technical scheme, the commodities can be automatically classified through the neural network model, the labeling efficiency of target commodities can be greatly improved, the workload of manual labeling is reduced, and the accuracy is improved; in addition, a plurality of neural network models can be adopted for classification, as target commodities can relate to a plurality of labels, such as adaptive scenes, office use and medical use, the target commodities can be identified to be domestic or office use through the trained neural network model I, and medical use or non-medical use is identified through the trained neural network model II; in addition, when the target commodity is considered to have more than two labels, the neural network model III can be called to continue classification, and a third commodity classification label is obtained.
As a further scheme of the invention: the commodity picture group comprises a plurality of commodity pictures shot at different angles;
and inputting the commodity pictures in the commodity picture group into a classification model one by one, and taking a classification result with the highest output ratio probability of the classification model as a final basis for determining the commodity data.
Through the technical scheme, the output classification result with the largest probability ratio can be taken as the final basis by identifying a plurality of commodity pictures of the same target commodity at different angles, the commodity classification accuracy can be improved, whether the target commodity possibly has various classification labels or not can be judged according to the diversity degree of the classification result, and the types of the commodity classification labels are more and more when the diversity of the classification result is higher.
As a further scheme of the invention: a data analysis system based on accurate marketing of big data commodities comprises:
the acquisition module is used for acquiring commodity data of the target commodity;
the commodity information base is used for automatically determining a target user group according to the commodity data;
a marketing model library for automatically determining a marketing model according to the commodity data and the target user group;
the marketing effect evaluation module is used for acquiring sales data and determining the marketing effect of the marketing model according to the sales data;
the step S500 includes:
counting the repeated purchasing parameters in the target customer group within a preset time;
calculating the commodity dependence score of the target user according to the re-purchasing parameter;
the re-purchasing parameters comprise the re-purchasing frequency and single consumption amount of the target commodity purchased by the target customers in the target customer group and the re-purchasing time interval;
the higher the commodity dependence score, the better the marketing effect of the marketing model.
As a further scheme of the invention: the method comprises the following steps:
the crawling module is used for collecting and acquiring business data;
the label generating module is used for establishing a commodity label library corresponding to a commodity label system and establishing a customer label library corresponding to a customer label system;
the marketing model generation module is used for establishing a marketing model library;
wherein the business data comprises the commodity data, customer data, order data; the commodity label system is a set of commodity classification labels corresponding to different commodities; the client label system is a set of client classification labels corresponding to different clients.
The invention has the beneficial effects that:
(1) the commodity classification labels can be determined according to commodity characteristics embodied by commodity data, and as the shopping demands of users can be analyzed in advance to obtain the corresponding user classification labels, a target user group can be found according to the corresponding relation between the commodity classification labels and the user classification labels, a corresponding marketing model is selected, marketing output is carried out, the sales data of the target commodity is obtained, the effect is monitored and tracked, and duplication and optimization are carried out after activities are carried out;
(2) collecting commodity data, customer data and order data for analysis and diagnosis, analyzing the positioning of the commodity data to find corresponding customer groups and potential customer groups, classifying and labeling users through the order data of the customer groups and the potential customer groups, and performing overall analysis to perform accurate and effective marketing activities according to the classification of the customers and related products;
(3) the repeated purchasing frequency reflects the viscosity between the user and the target commodity, and the word consumption amount and the repeated purchasing time interval can reflect the demand of the user;
(4) the commodities can be automatically classified through the neural network model, the labeling efficiency of target commodities can be greatly improved, the workload of manual labeling is reduced, and the accuracy is improved; in addition, a plurality of neural network models can be adopted for classification, as target commodities can relate to a plurality of labels, such as adaptive scenes, office use and medical use, the target commodities can be identified to be domestic or office use through the trained neural network model I, and medical use or non-medical use is identified through the trained neural network model II; in addition, when the target commodity is considered to have more than two labels, a third neural network model can be called to continue classification to obtain a third commodity classification label;
(5) the classification method has the advantages that the output classification result with the largest probability ratio can be taken as the final basis by identifying a plurality of commodity pictures of the same target commodity at different angles, the commodity classification accuracy can be improved, whether the target commodity possibly has various classification labels or not can be judged according to the diversity degree of the classification result, and the types of the commodity classification labels are more and more when the diversity of the classification result is higher.
Drawings
The invention will be further described with reference to the accompanying drawings.
FIG. 1 is a basic principle flow diagram of a data analysis method in the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention is a data analysis method based on accurate marketing of big data commodities, including the following steps:
s100, acquiring commodity data of a target commodity;
s200, automatically determining a target user group according to the commodity data;
s300, automatically determining a marketing model according to the commodity data and the target user group;
s400, obtaining sales data;
s500, determining the marketing effect of the marketing model according to the sales data;
s600, adjusting the marketing model according to the marketing effect.
According to the technical scheme, the commodity classification labels can be determined according to the commodity characteristics embodied by the commodity data, the shopping demands of the users can be analyzed in advance to obtain the corresponding user classification labels, the target user groups can be found according to the corresponding relation between the commodity classification labels and the user classification labels, the corresponding marketing models are selected, after marketing output is carried out, the sales data of the target commodities are obtained, effects are monitored and tracked, and after activities, retaking and optimization are carried out.
As a further scheme of the invention: before the step S100, the method further includes:
s001, collecting and acquiring commercial data;
s002, establishing a commodity label library corresponding to the commodity label system;
s003, establishing a customer label library corresponding to the customer label system;
s004, establishing a marketing model base;
wherein the business data comprises the commodity data, customer data, order data; the commodity label system is a set of commodity classification labels corresponding to different commodities; the client label system is a set of client classification labels corresponding to different clients.
According to the technical scheme, the commodity data, the customer data and the order data are collected for analysis and diagnosis, the positioning of the commodity data is analyzed, the corresponding customer groups and the corresponding potential customer groups are found, the customers are classified and labeled through the order data of the customer groups and the potential customer groups, and the overall analysis is carried out to carry out accurate and effective marketing activities according to the classification of the customers and related products.
As a further scheme of the invention: the commodity classification label comprises basic attributes, interactive behaviors, adaptation scenes, supply chain attributes and commodity values;
the basic attributes comprise the shape and color characteristics of the commodity, and the interactive behaviors comprise click quantity, browsing quantity and commodity quantity of the corresponding commodity.
The label of the adaptation scene can have various classifications for the same commodity, and the label of the adaptation scene can simultaneously record all the possible classifications because the label of the adaptation scene possibly influences the determination of a target customer group, and if the label of the adaptation scene needs higher dividing accuracy, the marketing scheme can be comprehensively and smoothly carried out. The same is true for supply chain attributes.
As a further scheme of the invention: the client label system comprises key attributes, interest labels, social characteristic labels and expense labels;
the key attributes comprise gender, age, education level, year and month of birth, industry engagement, constellation;
the interest tags comprise interest, browsing/collecting goods, interactive contents, brand preferences and product preferences;
the social characteristic labels comprise marital conditions and family environments;
the spending label includes income status, purchasing power level.
As a further scheme of the invention: the step S500 includes:
counting the repeated purchasing parameters in the target customer group within a preset time;
calculating the commodity dependence score of the target user according to the repurchase parameters;
the re-purchasing parameters comprise the re-purchasing frequency and single consumption amount of the target commodity purchased by the target customers in the target customer group and the re-purchasing time interval;
the higher the commodity dependence score, the better the marketing effect of the marketing model.
Through the technical scheme, the repeated purchasing frequency reflects the viscosity between the user and the target commodity, and the word consumption amount and the repeated purchasing time interval can reflect the demand of the user.
As a further scheme of the invention: the step S100 includes:
acquiring a commodity graph group of the target commodity; the commodity picture group comprises commodity pictures;
inputting the commodity pictures in the commodity picture group into a classification model;
determining the commodity data according to the classification result output by the classification model;
and the classification model is a trained neural network model.
Through the technical scheme, the neural network model adopted in the invention can adopt a Convolutional Neural Network (CNN), the convolutional neural network is the most popular neural network model for the image classification problem, and the training sample in retraining is the same as the acquisition mode of the commodity picture; more, compared with the commodity picture, the training sample has one more manual labeling step.
The commodities can be automatically classified through the neural network model, the labeling efficiency of target commodities can be greatly improved, the workload of manual labeling is reduced, and the accuracy is improved; in addition, a plurality of neural network models can be adopted for classification, as target commodities can relate to a plurality of labels, such as adaptive scenes, office use and medical use, the target commodities can be identified to be domestic or office use through the trained neural network model I, and medical use or non-medical use is identified through the trained neural network model II; in addition, when the target commodity is considered to have more than two labels, the neural network model III can be called to continue classification, and a third commodity classification label is obtained.
For example, the vise can be used in a factory, or at home, or in the medical field, in the present invention, the neural network model i, the neural network model ii, and the neural network model iii have different classification results according to different training samples adopted during their own training, for example, the neural network model distinguishes whether a target commodity belongs to factory use or daily use, the neural network model distinguishes whether a target commodity belongs to home use or commercial use, and the neural network model iii distinguishes whether a target commodity belongs to medical field utility or toy field use.
In the invention, if the probability of the first classification output by the first neural network model is higher than the probability of the second classification by 80 percent, the second neural network model does not need to be continuously adopted for classification, otherwise, the second neural network model is adopted for continuous classification, and the upper cycle limit can be set to be 5.
The design is that most of the convolutional neural networks are binary classification, the requirement of the multivariate classification on the structural complexity is extremely high, and the convolutional neural networks can be flexibly adjusted by the number of neural network models and are convenient to use.
As a further scheme of the invention: the commodity picture group comprises a plurality of commodity pictures shot at different angles;
and inputting the commodity pictures in the commodity picture group into a classification model one by one, and taking a classification result with the highest output ratio probability of the classification model as a final basis for determining the commodity data.
Through the technical scheme, the output classification result with the largest probability ratio can be taken as the final basis by identifying a plurality of commodity pictures of the same target commodity at different angles, the commodity classification accuracy can be improved, whether the target commodity possibly has various classification labels or not can be judged according to the diversity degree of the classification result, and the types of the commodity classification labels are more and more when the diversity of the classification result is higher.
As a further scheme of the invention: a data analysis system based on accurate marketing of big data commodities comprises:
the acquisition module is used for acquiring commodity data of the target commodity;
the commodity information base is used for automatically determining a target user group according to the commodity data;
a marketing model library for automatically determining a marketing model according to the commodity data and the target user group;
and the marketing effect evaluation module is used for acquiring sales data and determining the marketing effect of the marketing model according to the sales data.
As a further scheme of the invention: the method comprises the following steps:
the crawling module is used for collecting and acquiring business data;
the label generating module is used for establishing a commodity label library corresponding to a commodity label system and establishing a customer label library corresponding to a customer label system;
the marketing model generation module is used for establishing a marketing model library;
wherein the business data comprises the commodity data, customer data, order data; the commodity label system is a set of commodity classification labels corresponding to different commodities; the client label system is a set of client classification labels corresponding to different clients.
The invention has the following summarizing effects:
the commodity classification labels can be determined according to commodity characteristics embodied by commodity data, and as the shopping demands of users can be analyzed in advance to obtain the corresponding user classification labels, a target user group can be found according to the corresponding relation between the commodity classification labels and the user classification labels, a corresponding marketing model is selected, marketing output is carried out, the sales data of the target commodity is obtained, the effect is monitored and tracked, and duplication and optimization are carried out after activities are carried out; the method comprises the steps of collecting commodity data, customer data and order data for analysis and diagnosis, analyzing the positioning of the commodity data to find corresponding customer groups and potential customer groups, classifying and labeling users through the order data of the customer groups and the potential customer groups, and performing overall analysis to perform accurate and effective marketing activities according to the classification of the customers and related products.
The commodities can be automatically classified through the neural network model, the labeling efficiency of target commodities can be greatly improved, the workload of manual labeling is reduced, and the accuracy is improved; in addition, a plurality of neural network models can be adopted for classification, as target commodities can relate to a plurality of labels, such as adaptive scenes, office use and medical use, the target commodities can be identified to be domestic or office use through the trained neural network model I, and medical use or non-medical use is identified through the trained neural network model II; in addition, when the target commodity is considered to have more than two labels, the neural network model III can be called to continue classification, and a third commodity classification label is obtained.
The classification accuracy of commodities can be improved by identifying a plurality of commodity pictures of the same target commodity at different angles and taking the output classification result with the largest probability ratio as the final basis, and whether the target commodity possibly has various classification labels or not can be judged according to the diversity degree of the classification result, so that the types of the commodity classification labels are more, and the classification accuracy of the commodity classification labels of the target commodity and the target commodity can be comprehensively improved.
While one embodiment of the present invention has been described in detail, the description is only a preferred embodiment of the present invention and should not be taken as limiting the scope of the invention. All equivalent changes and modifications made within the scope of the present invention shall fall within the scope of the present invention.
Claims (8)
1. A data analysis method based on big data commodity accurate marketing is characterized by comprising the following steps:
s100, acquiring commodity data of a target commodity;
s200, automatically determining a target user group according to the commodity data;
s300, automatically determining a marketing model according to the commodity data and the target user group;
s400, obtaining sales data;
s500, determining the marketing effect of the marketing model according to the sales data;
s600, adjusting the marketing model according to the marketing effect;
the step S500 includes:
counting the repeated purchasing parameters in the target customer group within a preset time;
calculating the commodity dependence score of the target user according to the re-purchasing parameter;
the repurchase parameters are the repurchase frequency and the single consumption amount of the target commodities purchased by the target customers in the target customer group and the repurchase time interval;
the higher the commodity dependence score, the better the marketing effect of the marketing model.
2. The data analysis method based on accurate marketing of big data commodities, according to claim 1, further comprising, before said step S100:
s001, collecting and acquiring commercial data;
s002, establishing a commodity label library corresponding to the commodity label system;
s003, establishing a customer label library corresponding to the customer label system;
s004, establishing a marketing model library;
wherein the business data comprises the commodity data, customer data, order data; the commodity label system is a set of commodity classification labels corresponding to different commodities; the client label system is a set of client classification labels corresponding to different clients.
3. The big-data commodity precision marketing-based data analysis method according to claim 2, wherein the commodity classification labels comprise basic attributes, interactive behaviors, adaptation scenes, supply chain attributes and commodity values;
the basic attributes comprise the shape and color characteristics of the commodity, and the interactive behaviors comprise click quantity, browsing quantity and commodity quantity of the corresponding commodity.
4. The data analysis method based on big data commodity precision marketing according to claim 2, characterized in that the customer label system comprises key attributes, interest labels, social characteristic labels and expense labels;
the key attributes comprise gender, age, education level, year and month of birth, industry engagement, constellation;
the interest tags comprise interest, browsing/collecting goods, interactive contents, brand preferences and product preferences;
the social characteristic labels comprise marital conditions and family environments;
the spending label includes income status, purchasing power level.
5. The data analysis method based on big data commodity precision marketing according to claim 1, wherein the step S100 comprises:
acquiring a commodity graph group of the target commodity; the commodity picture group comprises commodity pictures;
inputting the commodity pictures in the commodity picture group into a classification model;
determining the commodity data according to the classification result output by the classification model;
and the classification model is a trained neural network model.
6. The data analysis method based on big data commodity precision marketing according to claim 5, wherein the commodity map group comprises commodity pictures taken at a plurality of different angles;
and inputting the commodity pictures in the commodity picture group into a classification model one by one, and taking a classification result with the highest output ratio probability of the classification model as a final basis for determining the commodity data.
7. A data analysis system based on accurate marketing of big data commodities, characterized by comprising:
the acquisition module is used for acquiring commodity data of the target commodity;
the commodity information base is used for automatically determining a target user group according to the commodity data;
a marketing model library for automatically determining a marketing model according to the commodity data and the target user group;
the marketing effect evaluation module is used for acquiring sales data and determining the marketing effect of the marketing model according to the sales data;
the method for determining the marketing effect of the marketing model according to the sales data comprises the following steps:
within a preset time, counting the re-purchasing parameters in the target customer group;
calculating the commodity dependence score of the target user according to the re-purchasing parameter;
the re-purchasing parameters comprise the re-purchasing frequency and single consumption amount of the target commodity purchased by the target customers in the target customer group and the re-purchasing time interval;
the higher the commodity dependence score, the better the marketing effect of the marketing model.
8. The big-data commodity precision marketing-based data analysis system according to claim 7, comprising:
the crawling module is used for collecting and acquiring business data;
the label generating module is used for establishing a commodity label library corresponding to a commodity label system and establishing a customer label library corresponding to a customer label system;
the marketing model generation module is used for establishing a marketing model library;
wherein the business data comprises the commodity data, customer data, order data; the commodity label system is a set of commodity classification labels corresponding to different commodities; the client label system is a set of client classification labels corresponding to different clients.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210826883.6A CN114971747A (en) | 2022-07-14 | 2022-07-14 | Data analysis method and system based on big data commodity accurate marketing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210826883.6A CN114971747A (en) | 2022-07-14 | 2022-07-14 | Data analysis method and system based on big data commodity accurate marketing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114971747A true CN114971747A (en) | 2022-08-30 |
Family
ID=82970321
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210826883.6A Pending CN114971747A (en) | 2022-07-14 | 2022-07-14 | Data analysis method and system based on big data commodity accurate marketing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114971747A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115510328A (en) * | 2022-10-11 | 2022-12-23 | 江苏云机汇软件科技有限公司 | Commodity brand marketing data analysis method based on big data |
| CN117078360A (en) * | 2023-10-16 | 2023-11-17 | 深圳市卖点科技股份有限公司 | Intelligent commodity display method, system and device based on off-line popularization |
| CN117094752A (en) * | 2023-10-13 | 2023-11-21 | 广州市零脉信息科技有限公司 | Product sales intention group analysis system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107437203A (en) * | 2017-08-07 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Information-pushing method, device, electronic installation and computer-readable medium |
| CN107886369A (en) * | 2017-11-29 | 2018-04-06 | 口碑(上海)信息技术有限公司 | A kind of method, apparatus and electronic equipment for marketing activity effect prediction |
| CN111222952A (en) * | 2020-01-09 | 2020-06-02 | 苏宁云计算有限公司 | Marketing customer group recommendation method and device |
| CN111586169A (en) * | 2020-05-07 | 2020-08-25 | 苏宁云计算有限公司 | Commodity marketing information pushing method and system |
| CN113254781A (en) * | 2021-06-10 | 2021-08-13 | 北京明略昭辉科技有限公司 | Model determination method and device in recommendation system, electronic equipment and storage medium |
-
2022
- 2022-07-14 CN CN202210826883.6A patent/CN114971747A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107437203A (en) * | 2017-08-07 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Information-pushing method, device, electronic installation and computer-readable medium |
| CN107886369A (en) * | 2017-11-29 | 2018-04-06 | 口碑(上海)信息技术有限公司 | A kind of method, apparatus and electronic equipment for marketing activity effect prediction |
| CN111222952A (en) * | 2020-01-09 | 2020-06-02 | 苏宁云计算有限公司 | Marketing customer group recommendation method and device |
| CN111586169A (en) * | 2020-05-07 | 2020-08-25 | 苏宁云计算有限公司 | Commodity marketing information pushing method and system |
| CN113254781A (en) * | 2021-06-10 | 2021-08-13 | 北京明略昭辉科技有限公司 | Model determination method and device in recommendation system, electronic equipment and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115510328A (en) * | 2022-10-11 | 2022-12-23 | 江苏云机汇软件科技有限公司 | Commodity brand marketing data analysis method based on big data |
| CN117094752A (en) * | 2023-10-13 | 2023-11-21 | 广州市零脉信息科技有限公司 | Product sales intention group analysis system |
| CN117078360A (en) * | 2023-10-16 | 2023-11-17 | 深圳市卖点科技股份有限公司 | Intelligent commodity display method, system and device based on off-line popularization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114971747A (en) | Data analysis method and system based on big data commodity accurate marketing | |
| US8738436B2 (en) | Click through rate prediction system and method | |
| CN110942337A (en) | Accurate tourism marketing method based on internet big data | |
| CN111062757A (en) | Information recommendation method and system based on multi-path optimization matching | |
| CN101454771A (en) | System and method of segmenting and tagging entities based on profile matching using a multi-media survey | |
| Dzyabura et al. | Leveraging the power of images in managing product return rates | |
| Xue et al. | Pricing personalized bundles: A new approach and an empirical study | |
| Huang | Excess loyalty in online retailing | |
| US20230139824A1 (en) | Media content enhancement based on user feedback of multiple variations | |
| CN115099878B (en) | Marketing method based on big data analysis | |
| CN114331543A (en) | Advertisement propagation method for large-scale crowd orientation and dynamic scene matching | |
| CN112287238A (en) | User characteristic determination method and device, storage medium and electronic equipment | |
| Wang | A survey of online advertising click-through rate prediction models | |
| CN113052653A (en) | Financial product content recommendation method and system and computer readable storage medium | |
| CN113988945B (en) | Management system for multidimensional data trend accurate marketing | |
| CN116957691B (en) | Cross-platform intelligent advertisement putting method and system for commodities of e-commerce merchants | |
| CN113688306A (en) | Recommendation strategy generation method and device based on reinforcement learning | |
| CN110555719B (en) | Commodity click rate prediction method based on deep learning | |
| CN114936911B (en) | Intelligent marketing popularization system | |
| CN116911926A (en) | Advertisement marketing recommendation method based on data analysis | |
| CN116320626A (en) | Method and system for calculating live broadcast heat of electronic commerce | |
| CN114723491A (en) | Accurate marketing method and system based on user portrait and data mining | |
| CN113254775A (en) | Credit card product recommendation method based on client browsing behavior sequence | |
| CN111178934A (en) | Method and device for acquiring target object | |
| CN111427919A (en) | Brand feature extraction method and device based on e-commerce recommendation model |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220830 |