CN117114744A - Product marketing method, device, equipment and storage medium - Google Patents
Product marketing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117114744A CN117114744A CN202310979798.8A CN202310979798A CN117114744A CN 117114744 A CN117114744 A CN 117114744A CN 202310979798 A CN202310979798 A CN 202310979798A CN 117114744 A CN117114744 A CN 117114744A
- Authority
- CN
- China
- Prior art keywords
- marketing
- product
- target
- strategy
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000000694 effects Effects 0.000 claims abstract description 66
- 238000004458 analytical method Methods 0.000 claims description 46
- 238000011156 evaluation Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 10
- 230000004931 aggregating effect Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000007619 statistical method Methods 0.000 claims description 4
- 238000013480 data collection Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 12
- 238000012795 verification Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 description 1
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000012216 screening Methods 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
- 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
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0211—Determining the effectiveness of discounts or incentives
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of marketing management, and discloses a product marketing method, a device, equipment and a storage medium. According to the invention, a plurality of product marketing strategies are constructed according to the collected product marketing data; predicting the marketing effect of the product marketing strategy, and determining a target marketing strategy corresponding to the target group; and marketing products to the target group according to the target marketing strategy. Because various product marketing strategies can be constructed in advance, then the optimal product marketing strategy is selected for the groups divided from various prediction dimensions such as areas, consumption limits and the like through marketing effect prediction to serve as target marketing strategies, and then the target groups are subjected to product marketing according to the target marketing strategies, the fact that a proper strategy can be selected for marketing aiming at the user groups is ensured, and therefore the marketing effect of product marketing is improved.
Description
Technical Field
The present invention relates to the field of marketing management technologies, and in particular, to a product marketing method, device, apparatus, and storage medium.
Background
With the continuous development of business, the marketing management idea of internet big data is more and more different, but how to obtain better marketing effect (for example, how to reasonably screen consumers, how to accurately calculate member classes, how to keep members truly active, and how to improve after-sales service) is important at present.
The foregoing is provided merely for the purpose of facilitating understanding of the technical solutions of the present invention and is not intended to represent an admission that the foregoing is prior art.
Disclosure of Invention
The invention mainly aims to provide a product marketing method, a device, equipment and a storage medium, and aims to solve the technical problem of poor marketing effect in the prior art.
To achieve the above object, the present invention provides a product marketing method comprising the steps of:
constructing various product marketing strategies according to the collected product marketing data;
predicting the marketing effect of the product marketing strategy, and determining a target marketing strategy corresponding to a target group, wherein the target group is a user group divided according to at least one preset dimension;
and marketing products to the target group according to the target marketing strategy.
Optionally, the step of predicting the marketing effect of the product marketing strategy and determining the target marketing strategy corresponding to the target group includes:
carrying out marketing effect prediction on the product marketing strategies through a preset marketing analysis model, and determining a marketing effect prediction value of each product marketing strategy for a target group;
and selecting a target marketing strategy corresponding to the target group from the multiple product marketing strategies according to the marketing effect predicted value.
Optionally, before the step of predicting the marketing effect of the product marketing strategies by the preset marketing analysis model and determining the marketing effect predicted value of each product marketing strategy for the target group, the method further includes:
sampling the marketing data of the historical product based on a preset sampling principle to obtain a data acquisition sample;
evaluating the data acquisition sample;
selecting part of samples from the data acquisition samples according to the evaluation result to construct a model sample set;
training the initial marketing analysis model according to the model sample set to obtain a preset marketing analysis model.
Optionally, the step of selecting a part of samples from the data collection samples according to the evaluation result to construct a model sample set includes:
selecting a target sample from the data acquisition samples according to the evaluation result;
setting corresponding group labels for the target samples according to preset dimensions to obtain model samples;
and aggregating the model samples to obtain a model sample set.
Optionally, the step of marketing the product to the target group according to the target marketing strategy includes:
extracting a product combination strategy from the target marketing strategy;
Generating a product combination scheme according to the product combination strategy;
and marketing the products of the target group according to the product combination scheme.
Optionally, the step of marketing the target group according to the product combination scheme includes:
extracting discount coupon strategies from the target marketing strategies;
determining a discount scheme corresponding to each product combination scheme according to the discount strategy;
and marketing the products of the target group according to the product combination scheme and the preferential scheme.
Optionally, the step of constructing a plurality of product marketing strategies according to the collected product marketing data includes:
carrying out statistical analysis on the product marketing data to determine monthly sales data and regional demand of each product;
generating product collocation combinations according to collocation relations among the products;
generating a plurality of product combination schemes according to the monthly sales data and the product collocation combination;
setting a plurality of preferential schemes for each product combination scheme according to the regional demand and the product sales time period of each product;
and generating various product marketing strategies according to the various product combination schemes and various preferential schemes corresponding to the product combination schemes.
In addition, in order to achieve the above object, the present invention also provides a product marketing device, which includes the following modules:
the construction module is used for constructing various product marketing strategies according to the collected product marketing data;
the prediction module is used for predicting the marketing effect of the product marketing strategy and determining a target marketing strategy corresponding to a target group, wherein the target group is a user group divided according to at least one preset dimension;
and the marketing module is used for marketing the products of the target group according to the target marketing strategy.
In addition, in order to achieve the above object, the present invention also proposes a product marketing apparatus comprising: a processor, a memory, and a product marketing program stored on the memory and executable on the processor, which when executed, implements the steps of the product marketing method as described above.
In addition, in order to achieve the above object, the present invention also proposes a computer-readable storage medium having stored thereon a product marketing program which, when executed, implements the steps of the product marketing method as described above.
According to the invention, a plurality of product marketing strategies are constructed according to the collected product marketing data; predicting the marketing effect of the product marketing strategy, and determining a target marketing strategy corresponding to the target group; and marketing products to the target group according to the target marketing strategy. Because various product marketing strategies can be constructed in advance, then the optimal product marketing strategy is selected for the groups divided from various prediction dimensions such as areas, consumption limits and the like through marketing effect prediction to serve as target marketing strategies, and then the target groups are subjected to product marketing according to the target marketing strategies, the fact that a proper strategy can be selected for marketing aiming at the user groups is ensured, and therefore the marketing effect of product marketing is improved.
Drawings
FIG. 1 is a schematic diagram of a product marketing device of a hardware operating environment in accordance with an embodiment of the present invention;
FIG. 2 is a flow chart of a first embodiment of a product marketing method according to the present invention;
FIG. 3 is a flow chart of a second embodiment of a product marketing method according to the present invention;
FIG. 4 is a schematic diagram of a product marketing system according to an embodiment of the present invention;
fig. 5 is a block diagram of a first embodiment of a product marketing device of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a product marketing device of a hardware running environment according to an embodiment of the present invention.
As shown in fig. 1, the product marketing device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
Those skilled in the art will appreciate that the structure shown in FIG. 1 is not limiting of the product marketing device and may include more or fewer components than shown, or may combine certain components, or may be arranged in different components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a product marketing program may be included in the memory 1005 as one type of storage medium.
In the product marketing device shown in FIG. 1, the network interface 1004 is primarily used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the product marketing device of the present invention may be provided in the product marketing device, and the product marketing device invokes the product marketing program stored in the memory 1005 through the processor 1001 and executes the product marketing method provided by the embodiment of the present invention.
An embodiment of the invention provides a product marketing method, referring to fig. 2, fig. 2 is a flow chart of a first embodiment of the product marketing method of the invention.
In this embodiment, the product marketing method includes the following steps:
step S10: and constructing various product marketing strategies according to the collected product marketing data.
It should be noted that, the execution body of the embodiment may be the product marketing device, and the product marketing device may be an electronic device such as a personal computer, a server, or other devices capable of implementing the same or similar functions.
It should be noted that, the product marketing data may include marketing promotion information, product sales data, product sales volume data, and the like, where the marketing promotion information may include related data for daily promotion and product collocation of the product, the product sales data may include data such as total sales volume of the product, sales volume of each region, sales volume of each operator, and the product sales volume data may include data such as monthly and quarterly product demand volume and sales volume of each product region. The product marketing strategy may include information such as product portfolio strategy, product offer strategy, marketing duration, etc.
In a specific implementation, the step of constructing a plurality of product marketing strategies according to the collected product marketing data may include:
carrying out statistical analysis on the product marketing data to determine monthly sales data and regional demand of each product;
Generating product collocation combinations according to collocation relations among the products;
generating a plurality of product combination schemes according to the monthly sales data and the product collocation combination;
setting a plurality of preferential schemes for each product combination scheme according to the regional demand and the product sales time period of each product;
and generating various product marketing strategies according to the various product combination schemes and various preferential schemes corresponding to the product combination schemes.
The monthly sales data may be sales data of products in a dimension of month, and the regional demand may be a demand of each product region for products. The collocation relation between the products can be preset by a manager of the product marketing device, for example: the A product and the B product can be combined for use, so that the A and the B have a collocation relationship.
In actual use, the multiple product combination schemes can be generated according to the monthly sales data and the product collocation combination by determining the high sales volume product and the low sales volume product according to the monthly sales data, then taking the product collocation combination simultaneously containing the high sales volume product and the low sales volume product as the target combination, and then generating the product combination scheme according to the target combination.
In a specific implementation, setting multiple discount schemes for each product combination scheme according to the regional demand and the product sales time period of each product may be to determine sales difficulty of each product combination scheme in each region and time period according to the regional demand and the product sales time period of each product, and then setting multiple discount schemes for each product combination scheme according to the sales difficulty, where discount in the discount schemes is in direct proportion to the sales difficulty, i.e. the higher the sales difficulty, the higher the discount proportion, for example: the sales difficulty can be divided into A, B, C three stages, wherein A is more than B and more than C, and the corresponding discount can be A-7, B-8 and C-9.
In practical use, the generating of the multiple product marketing strategies according to the multiple product combination schemes and the multiple preferential schemes corresponding to the multiple product combination schemes may be to arrange and combine the multiple product combination schemes and the multiple preferential schemes corresponding to the product combination schemes, so as to generate the multiple product marketing strategies, for example: assuming that there are A, B product combination schemes, wherein there are two types of preferential schemes corresponding to A, R and S, and one type of preferential scheme corresponding to B, K, then a product marketing strategy can be generated according to AR, AS and BK respectively.
Step S20: and predicting the marketing effect of the product marketing strategy, and determining a target marketing strategy corresponding to the target group.
It should be noted that the target group may be a user group divided according to at least one preset dimension, where the preset dimension may include a plurality of limits such as regions, urban prosperity where the target group is located, consumption limits, and the like, and of course, may further include other dimensions, for example: the customer base of the carrier market can be divided into: various target groups such as large and medium city clients, medium and small town clients, village and town clients and the like; customer groups of the carrier market can be divided into by consumption line: a plurality of target groups such as a high-end client, a medium-end client, a low-end client and the like; if the urban luxury and the consumption limit are combined for division, the customer groups of the operator market can be divided into a plurality of target groups such as A (large and medium urban high-end customers), B (large and medium urban high-end customers), C (medium and small urban high-end customers), D (medium and small urban medium-end customers), E (other customers) and the like.
When the product marketing strategy is predicted and the target marketing strategy corresponding to the target group is determined, the marketing effect when the product marketing strategy is used for marketing the target group is predicted, and then the target marketing strategy which is most suitable for the target group is selected from multiple product marketing strategies according to the marketing effect. The target groups can be multiple, and then the marketing effect prediction can be performed once for each target group, so that the target marketing strategy corresponding to each target group is obtained.
Step S30: and marketing products to the target group according to the target marketing strategy.
It can be understood that the target marketing strategy is the optimal marketing strategy determined when the target marketing strategy is predicted and used for marketing products to the target group, so that after the target marketing strategy corresponding to the target group is determined, the target marketing strategy can be used for marketing products to the target group, thereby ensuring that a better marketing effect can be obtained.
In actual use, the actual product promotion is generally performed by the operators, and then the product marketing to the target groups according to the target marketing strategies can be performed by sending the target marketing strategies to the operators corresponding to the target groups, so that the operators hold the product promotion activities according to the target marketing strategies, and product marketing is performed to the users.
In order to ensure normal product marketing, the product marketing device can also acquire the product inventory of each operator and calculate the inventory required by marketing according to a target marketing strategy, when the product inventory of the operator is insufficient to support a product popularization activity, the operator is informed to carry out replenishment, and a platform, a user group and a merchant are linked to ensure normal product marketing activity, meanwhile, the sufficiency of marketing products is ensured, and the consumption experience of the user group is improved, for example: and notifying the operator to carry out replenishment when the product inventory of the operator is less than half of the inventory required for marketing.
In a specific implementation, in order to ensure that product marketing is reasonably performed, step S30 in this embodiment may include:
extracting a product combination strategy from the target marketing strategy;
generating a product combination scheme according to the product combination strategy;
and marketing the products of the target group according to the product combination scheme.
When marketing and promotion of products are carried out, products with lower part sales volume and products with higher part sales volume can be combined and marketed, so that the overall sales volume is ensured to be higher, then the product combination strategy can be extracted from the target marketing strategy, then the products to be sold at present are combined according to the product combination strategy, so that at least one product combination scheme is obtained, and then the target group is subjected to product marketing based on the product combination scheme.
Further, since the low sales volume product and the high sales volume product are combined and marketed when the product combination marketing is performed, in order to increase the interest of the user in the combined product, the product marketing step for the target group according to the product combination scheme in this embodiment may include:
extracting discount coupon strategies from the target marketing strategies;
Determining a discount scheme corresponding to each product combination scheme according to the discount strategy;
and marketing the products of the target group according to the product combination scheme and the preferential scheme.
It should be noted that, the discount coupon strategy may include coupon schemes corresponding to different combination schemes (such as coupon discounts under different inventory amounts), and determining the coupon scheme corresponding to each product combination scheme according to the discount coupon strategy may be searching the coupon scheme corresponding to the product combination in each product combination scheme in the discount coupon strategy, so as to obtain the coupon scheme corresponding to each product combination scheme.
It can be understood that when product marketing is performed on the target group according to the product combination schemes and the preferential schemes corresponding to the product combination schemes, the interest of the user on the combined product can be still improved through the preferential schemes when the combination marketing of the products with lower sales and the products with higher partial sales is ensured, so that the good overall sales can be ensured when the product marketing is performed.
The embodiment constructs various product marketing strategies according to the collected product marketing data; predicting the marketing effect of the product marketing strategy, and determining a target marketing strategy corresponding to the target group; and marketing products to the target group according to the target marketing strategy. Because various product marketing strategies can be constructed in advance, then the optimal product marketing strategy is selected for the groups divided from various prediction dimensions such as areas, consumption limits and the like through marketing effect prediction to serve as target marketing strategies, and then the target groups are subjected to product marketing according to the target marketing strategies, the fact that a proper strategy can be selected for marketing aiming at the user groups is ensured, and therefore the marketing effect of product marketing is improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a product marketing method according to a second embodiment of the present invention.
Based on the above-mentioned first embodiment, the step S20 of the product marketing method of the present embodiment includes:
step S201: and predicting the marketing effect of the product marketing strategies through a preset marketing analysis model, and determining the marketing effect prediction value of each product marketing strategy for the target group.
It should be noted that the preset marketing analysis model may be a model obtained by training in advance, and the preset marketing analysis model may be a BP (back propagation) neural network model, or may be a model with other similar functions, which is not limited in this embodiment. The predicted value of the marketing effect may be a quantized score representing the marketing effect, and the larger the predicted value of the marketing effect is, the higher the marketing effect is.
In actual use, the marketing effect prediction is performed on the product marketing strategies through the preset marketing analysis model, and the determination of the marketing effect prediction value of each product marketing strategy for the target group can be that the product marketing strategy and the target group are input into the preset marketing analysis model, and the marketing effect prediction is performed through the preset marketing analysis model, so that the marketing effect prediction value of each product marketing strategy for the target group is obtained.
Further, in order to ensure that the prediction accuracy of the preset marketing analysis model is high, before step S201 in the embodiment, the method may further include:
sampling the marketing data of the historical product based on a preset sampling principle to obtain a data acquisition sample;
evaluating the data acquisition sample;
selecting part of samples from the data acquisition samples according to the evaluation result to construct a model sample set;
training the initial marketing analysis model according to the model sample set to obtain a preset marketing analysis model.
It should be noted that the historical product marketing data may be recorded product marketing data that previously marketing the product, and the preset sampling principle may be preset by a manager of the product marketing device.
For example: the preset sampling principle is set as follows: 1. variables that greatly affect the outcome output and are easily detected or extracted are used as input quantities; 2. as much correlation or uncorrelation as possible does not exist between the input and output; 3. the method has the advantages that the characteristic extraction technology in the original data is required to be used for extracting parameters capable of reflecting network characteristics as normalization processing input, so that all data and information can be prevented from being selected blindly in the process of establishing a preset marketing analysis model, and the model training efficiency and the model accuracy are improved by screening sample data.
It should be noted that, when designing the model sample set, the sample set has a large number of network features for the marketing customer population sample, the training result can well embody its internal rule, and a representative organization or sample is selected to balance the category, and different types of samples are input in a crossing manner, so that the sample set has good generalization capability, furthermore, the collected sample set can be divided into two parts, one part is used for training, and the other part is used for verification (the specific division ratio can be preset by the manager of the product marketing equipment according to the actual requirement). When constructing the initial weights, since the neuron action function has symmetry with respect to the origin, the net input and output of each node near the zero point is at the midpoint of the action function, and the change in position is most sensitive and far from saturation, the learning of the network can be accelerated by selecting a smaller initial weight and equating the initial weights +1 and-1. Thus, a model sample set may be constructed by selecting a portion of the samples from the data acquisition samples according to the evaluation results in such a manner that a portion of the samples from the data acquisition samples are selected according to the evaluation results, and then the selected samples are aggregated, thereby obtaining the model sample set.
In a specific implementation, training the initial marketing analysis model according to the model sample set to obtain the preset marketing analysis model may be splitting the model sample set into a model training set and a model verification set, verifying the initial marketing analysis model trained to be converged by the model training set, and when verification passes, taking the initial marketing analysis model trained to be converged as the preset marketing analysis model.
The verification of the initial marketing analysis model trained to be converged through the model verification set may be to input data in the model verification set into the initial marketing analysis model trained to be converged to predict, obtain a prediction result output by the model, and then compare the prediction result with a real result in the model verification set, and if an error (which may be a variance or a similar algorithm calculation error) between the two is smaller than a preset value, determine that the verification is passed.
Further, in order to ensure that the trained model can analyze for different target groups, the step of selecting a part of samples from the data collection samples according to the evaluation result to construct a model sample set according to the embodiment may include:
Selecting a target sample from the data acquisition samples according to the evaluation result;
setting corresponding group labels for the target samples according to preset dimensions to obtain model samples;
and aggregating the model samples to obtain a model sample set.
It should be noted that the preset dimensions may include various amounts such as regions, urban bloom, consumption amounts, and the like, and of course, may further include other dimensions, for example: the urban luxury and the consumption limit are combined for division, the client groups of the operator market can be divided into a plurality of target groups such as A (large and medium city high-end client), B (large and medium city client), C (medium and small town high-end client), D (medium and small town client), E (other clients) and the like, and at the moment, if the user group to which the corresponding user belongs in the target sample is C, the group label to which the corresponding user belongs can be set as TagA.
It will be appreciated that the focus of different user groups on a product is different, for example: in the above examples, class a customers are important few high-quality customers, 20% of the two-eight customers are in the two-eight principle, after telephone communication and interview, the chances of successfully promoting packages or customizing new services are relatively high, meanwhile, the customers are insensitive to gift feedback marketing, and more tend to one-to-one more professional services, and a corresponding marketing scheme needs to be formulated in a key way; B. class C is very similar, is an important potential customer, focuses more on the needs and product value of the class C, and does not need to further mine customer requirements unlike class A customers for high requirements on service quality; class D customers are of the mass type, more prone to preferential, flow gifting or vip qualification experience, while improving quality of service, increasing customer loyalty; other customers pay more attention to the price, customer loyalty is relatively low, and the marketing means can be further refined according to the characteristics. Therefore, when the model is trained, corresponding group labels are set for all the samples, and then the model is trained, so that the model can consider the relevant dimension of the user group when the model is predicted subsequently, and the predicted result is ensured to be closer to the actual situation.
Step S202: and selecting a target marketing strategy corresponding to the target group from the multiple product marketing strategies according to the marketing effect predicted value.
It should be noted that, selecting the target marketing strategy corresponding to the target group from the multiple product marketing strategies according to the marketing effect prediction value may be taking the product marketing strategy with the largest marketing effect prediction value among the multiple product marketing strategies as the target marketing strategy corresponding to the target group.
In practical use, in order to quickly determine a target marketing strategy corresponding to a target group, multiple product marketing strategies can be ranked from large to small according to a corresponding marketing effect predicted value, and then the first product marketing strategy ranked in the ranking result is used as the target marketing strategy corresponding to the target group.
For easy understanding, the present embodiment will be described with reference to fig. 4, but not limited thereto, and fig. 4 is a schematic structural diagram of the product marketing system of the present embodiment;
because the product marketing method provided by the invention involves a large number of operations such as data processing and data analysis, the performance of a single device may not be enough to support the completion of such a large number of calculations, so that a product marketing scheme can be attempted to be executed cooperatively by using a plurality of devices, and then a product marketing system can be constructed according to a combination of the plurality of devices, and the structure of the product marketing system can be as shown in fig. 4, and the product marketing system comprises a marketing module, a data acquisition module, a sales volume data module, an analysis module, a storage module, a marketing strategy matching module, a data integration module, a pushing module, an inventory query module, a notification module, an order statistics module and an order tracking module, wherein one module can correspond to one device, a plurality of devices can be combined into one module, and a plurality of modules can be deployed in one device.
The marketing module can be used for carrying out daily promotion on products, matching the products and collecting marketing popularization information;
the data acquisition module is used for acquiring, classifying and processing the product sales data; the sales volume data module is used for acquiring the monthly and quarterly demand volume and sales volume data of the regional products so as to obtain product sales volume data, the data acquisition module can comprise a data receiving unit, a data processing unit and a data classification unit, the data receiving unit is used for receiving product sales data, product browsing data and matched product data, the data processing unit is used for removing useless data for subsequent data analysis in the data received by the data receiving unit, and the data classification unit is used for carrying out data classification processing on the data set processed by the data processing unit according to different products, regions and matched products;
the analysis module is used for carrying out subsequent marketing strategies and analysis processing of product collocation in combination with the browsing amount of the product, the demand amount of the area and the monthly sales amount, and can comprise a monthly browsing amount analysis unit, a monthly sales amount analysis unit and an area demand amount analysis unit when the analysis module is applied specifically, wherein the monthly browsing amount analysis unit is used for acquiring the monthly browsing amount data of different products and analyzing a data set, the monthly sales amount analysis unit is used for not acquiring the monthly sales amount data of the product and analyzing a sales data set, and the area demand amount analysis unit is used for acquiring the demand amount data of different areas of the marketing product and analyzing the sales amount data set of the area;
The storage module is used for storing a plurality of data sets of the monthly browsing amount, the monthly sales amount and the regional demand amount of the products in the analysis module;
the marketing strategy matching module can comprise a product matching unit, a sales scheme generating unit and a preferential discount unit, wherein the product matching unit is used for producing different product matching marketing schemes for selectively marketing products and matched products, the sales scheme generating unit is used for generating different sales combination schemes according to different product sales amounts and product matching, the preferential discount unit is used for setting corresponding preferential discount for the sales combination schemes according to different time periods and different regional requirements, so that various product marketing strategies are formed, and then marketing effect prediction can be carried out on the product marketing strategies through a preset marketing analysis model, so that target marketing strategies corresponding to each target group are determined;
the data integration module is used for merging and sorting the generated marketing strategy data, the product data, the collocation data and the sales volume data;
the pushing module is used for pushing corresponding product data to the user group by combining the integrated data;
the order statistics module is used for counting order data of successful order placing of the push data and order numbers;
The order tracking module is used for tracking the subsequent logistics condition, the goods returning condition and the satisfaction degree of the user on the product of the product order by combining the order data of the successful order and the order number;
the inventory inquiry module is used for inquiring the product inventory quantity of the merchant in combination with the pushing user group data and the monthly sales;
the notification module is used for notifying a merchant or a supplier to timely replenishment operation on the product when the inventory quantity of the product is lower than half of the push data and the monthly sales quantity.
The whole system collects and acquires different marketing data through big data of operators, then carries out deep analysis on marketing products, marketing data, marketing strategies and user groups through a programmed flow of collecting data, analyzing the data, matching marketing strategies, integrating the data and pushing the data, carries out corresponding analysis processing on different user groups, different areas and different product collocations through the result of data analysis, and finally carries out corresponding marketing activities on the user groups in different areas through integrating the analysis data and collocating different marketing strategies, thereby reducing the limiting conditions suffered in the marketing activities and facilitating the development of the marketing activities. The inventory inquiry module is used for inquiring the inventory quantity of products of the merchant in combination with the pushing user group data and the monthly sales, and the notification module is used for notifying the merchant or the supplier of timely replenishment operation on the products when the inventory quantity of the products is lower than half of the pushing data and the monthly sales. And then, sending a replenishment notice to the merchant or the supplier through a notification module when the product inventory data is lower than a set threshold value by matching with the inquiry of the inventory quantity of the merchant or the supplier, so as to ensure the normal running of the subsequent marketing, prevent the dislocation of supply and demand relations during the day of a large-scale activity and ensure the normal running of the subsequent marketing. The threshold value of the stock can be set according to multiple limiting conditions such as the value, the demand degree and the prior sales amount of the marketing products, the threshold value can be set to be 50% when the product value is low, the threshold value can be set to be 10% -30% unequal when the product value is high, the setting of the threshold value can be set by a merchant, and meanwhile, the conditions such as product stock backlog caused by more product stock can be prevented. The order statistics module is used for counting order data and order numbers of successful order placing of the push data, and the order tracking module is used for tracking and processing subsequent logistics conditions, return goods conditions and satisfaction degree of a user on the product by combining the order data and the order numbers of successful order placing. After successful ordering in the user group pushing data, order numbers and corresponding logistics information of the successful ordering can be acquired through Internet big data, then different orders are tracked, return goods information of marketing products is synchronously tracked, product collocation data of the marketing products are corrected through various different information, and normal operation of subsequent marketing is guaranteed.
According to the method, the marketing effect prediction is carried out on the product marketing strategies through a preset marketing analysis model, and the marketing effect prediction value of each product marketing strategy for a target group is determined; and selecting a target marketing strategy corresponding to the target group from the multiple product marketing strategies according to the marketing effect predicted value. Because the marketing effect prediction is carried out through the pre-trained preset marketing analysis model, and the data set used when the preset marketing analysis model is trained is sampled through the preset sampling principle, and the sample set constructed after evaluation can ensure that the model prediction accuracy obtained through training is higher, thereby ensuring that the selected target marketing strategy meets the actual demands of target groups, and ensuring the marketing effect of product marketing.
In addition, the embodiment of the invention also provides a storage medium, wherein the storage medium is stored with a product marketing program, and the product marketing program realizes the steps of the product marketing method when being executed by a processor.
Referring to fig. 5, fig. 5 is a block diagram showing a first embodiment of the product marketing device of the present invention.
As shown in fig. 5, a product marketing device according to an embodiment of the present invention includes:
A construction module 10 for constructing a plurality of product marketing strategies according to the collected product marketing data;
the prediction module 20 is configured to predict a marketing effect of the product marketing strategy, and determine a target marketing strategy corresponding to a target group, where the target group is a user group divided according to at least one preset dimension;
marketing module 30 for marketing products to the target group according to the target marketing strategy.
The embodiment constructs various product marketing strategies according to the collected product marketing data; predicting the marketing effect of the product marketing strategy, and determining a target marketing strategy corresponding to the target group; and marketing products to the target group according to the target marketing strategy. Because various product marketing strategies can be constructed in advance, then the optimal product marketing strategy is selected for the groups divided from various prediction dimensions such as areas, consumption limits and the like through marketing effect prediction to serve as target marketing strategies, and then the target groups are subjected to product marketing according to the target marketing strategies, the fact that a proper strategy can be selected for marketing aiming at the user groups is ensured, and therefore the marketing effect of product marketing is improved.
Further, the prediction module 20 is further configured to predict the marketing effect of the product marketing strategies by using a preset marketing analysis model, and determine a predicted value of the marketing effect of each product marketing strategy for the target group; and selecting a target marketing strategy corresponding to the target group from the multiple product marketing strategies according to the marketing effect predicted value.
Further, the prediction module 20 is further configured to sample the historical product marketing data based on a preset sampling principle, so as to obtain a data acquisition sample; evaluating the data acquisition sample; selecting part of samples from the data acquisition samples according to the evaluation result to construct a model sample set; training the initial marketing analysis model according to the model sample set to obtain a preset marketing analysis model.
Further, the prediction module 20 is further configured to select a target sample from the data acquisition samples according to the evaluation result; setting corresponding group labels for the target samples according to preset dimensions to obtain model samples; and aggregating the model samples to obtain a model sample set.
Further, the marketing module 30 is further configured to extract a product combination policy from the target marketing policy; generating a product combination scheme according to the product combination strategy; and marketing the products of the target group according to the product combination scheme.
Further, the marketing module 30 is further configured to extract a discount offer policy from the target marketing policy; determining a discount scheme corresponding to each product combination scheme according to the discount strategy; and marketing the products of the target group according to the product combination scheme and the preferential scheme.
Further, the construction module 10 is further configured to perform statistical analysis on the product marketing data to determine monthly sales data and regional demand of each product; generating product collocation combinations according to collocation relations among the products; generating a plurality of product combination schemes according to the monthly sales data and the product collocation combination; setting a plurality of preferential schemes for each product combination scheme according to the regional demand and the product sales time period of each product; and generating various product marketing strategies according to the various product combination schemes and various preferential schemes corresponding to the product combination schemes.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the invention as desired, and the invention is not limited thereto.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present invention, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
In addition, technical details not described in detail in this embodiment may refer to the product marketing method provided in any embodiment of the present invention, and are not described herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. A method of product marketing, the method comprising the steps of:
constructing various product marketing strategies according to the collected product marketing data;
predicting the marketing effect of the product marketing strategy, and determining a target marketing strategy corresponding to a target group, wherein the target group is a user group divided according to at least one preset dimension;
and marketing products to the target group according to the target marketing strategy.
2. The product marketing method of claim 1, wherein the step of predicting a marketing effect of the product marketing strategy and determining a target marketing strategy corresponding to a target group comprises:
carrying out marketing effect prediction on the product marketing strategies through a preset marketing analysis model, and determining a marketing effect prediction value of each product marketing strategy for a target group;
And selecting a target marketing strategy corresponding to the target group from the multiple product marketing strategies according to the marketing effect predicted value.
3. The product marketing method of claim 2, wherein the step of predicting the marketing effect of the product marketing strategies by a preset marketing analysis model, prior to the step of determining the predicted value of the marketing effect of each product marketing strategy for the target group, further comprises:
sampling the marketing data of the historical product based on a preset sampling principle to obtain a data acquisition sample;
evaluating the data acquisition sample;
selecting part of samples from the data acquisition samples according to the evaluation result to construct a model sample set;
training the initial marketing analysis model according to the model sample set to obtain a preset marketing analysis model.
4. The product marketing method of claim 3, wherein the step of selecting a portion of the samples from the data collection samples to construct a model sample set based on the evaluation results comprises:
selecting a target sample from the data acquisition samples according to the evaluation result;
setting corresponding group labels for the target samples according to preset dimensions to obtain model samples;
And aggregating the model samples to obtain a model sample set.
5. The product marketing method of claim 1, wherein the step of marketing products to the target group in accordance with the target marketing strategy comprises:
extracting a product combination strategy from the target marketing strategy;
generating a product combination scheme according to the product combination strategy;
and marketing the products of the target group according to the product combination scheme.
6. The product marketing method of claim 5 wherein the step of product marketing the target group according to the product portfolio comprises:
extracting discount coupon strategies from the target marketing strategies;
determining a discount scheme corresponding to each product combination scheme according to the discount strategy;
and marketing the products of the target group according to the product combination scheme and the preferential scheme.
7. The product marketing method of any of claims 1-6 wherein the step of constructing a plurality of product marketing strategies based on the collected product marketing data comprises:
carrying out statistical analysis on the product marketing data to determine monthly sales data and regional demand of each product;
Generating product collocation combinations according to collocation relations among the products;
generating a plurality of product combination schemes according to the monthly sales data and the product collocation combination;
setting a plurality of preferential schemes for each product combination scheme according to the regional demand and the product sales time period of each product;
and generating various product marketing strategies according to the various product combination schemes and various preferential schemes corresponding to the product combination schemes.
8. A product marketing device, the product marketing device comprising the following modules:
the construction module is used for constructing various product marketing strategies according to the collected product marketing data;
the prediction module is used for predicting the marketing effect of the product marketing strategy and determining a target marketing strategy corresponding to a target group, wherein the target group is a user group divided according to at least one preset dimension;
and the marketing module is used for marketing the products of the target group according to the target marketing strategy.
9. A product marketing device, the product marketing device comprising: a processor, a memory and a product marketing program stored on the memory and executable on the processor, the product marketing program when executed implementing the steps of the product marketing method of any of claims 1-7.
10. A computer readable storage medium, characterized in that it has stored thereon a product marketing program, which when executed implements the steps of the product marketing method according to any of the claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310979798.8A CN117114744A (en) | 2023-08-04 | 2023-08-04 | Product marketing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310979798.8A CN117114744A (en) | 2023-08-04 | 2023-08-04 | Product marketing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117114744A true CN117114744A (en) | 2023-11-24 |
Family
ID=88810244
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310979798.8A Pending CN117114744A (en) | 2023-08-04 | 2023-08-04 | Product marketing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117114744A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118172112A (en) * | 2024-05-11 | 2024-06-11 | 江西旅游商贸职业学院 | Marketing strategy intelligent analysis system and method based on big data |
| CN118297640A (en) * | 2024-06-06 | 2024-07-05 | 南京信息工程大学 | Product marketing management system and method based on big data |
-
2023
- 2023-08-04 CN CN202310979798.8A patent/CN117114744A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118172112A (en) * | 2024-05-11 | 2024-06-11 | 江西旅游商贸职业学院 | Marketing strategy intelligent analysis system and method based on big data |
| CN118297640A (en) * | 2024-06-06 | 2024-07-05 | 南京信息工程大学 | Product marketing management system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11574139B2 (en) | Information pushing method, storage medium and server | |
| CN108154401B (en) | User portrait depicting method, device, medium and computing equipment | |
| Seo et al. | Two-level model of customer retention in the US mobile telecommunications service market | |
| Lemmens et al. | Bagging and boosting classification trees to predict churn | |
| Coussement et al. | Integrating the voice of customers through call center emails into a decision support system for churn prediction | |
| Kamakura et al. | Cross-selling through database marketing: A mixed data factor analyzer for data augmentation and prediction | |
| CN109741146A (en) | Products Show method, apparatus, equipment and storage medium based on user behavior | |
| CN105490823B (en) | data processing method and device | |
| CN106156809A (en) | For updating the method and device of disaggregated model | |
| CN103150696A (en) | Method and device for selecting potential customer of target value-added service | |
| CN101385018A (en) | Using estimated ad qualities for ad filtering, ranking and promotion | |
| CN101390118A (en) | Predicting ad quality | |
| CN108885624A (en) | Information recommendation system and method | |
| Etzion et al. | e-CLV: a modelling approach for customer lifetime evaluation in e-commerce domains, with an application and case study for online auctions | |
| CN112215448A (en) | Method and device for distributing customer service | |
| CN110033120A (en) | For providing the method and device that risk profile energizes service for trade company | |
| CN117114744A (en) | Product marketing method, device, equipment and storage medium | |
| CN112767177A (en) | Insurance customer information management system for customer grading based on random forest | |
| TWM624658U (en) | Prediction devices for predicting whether users belong to valuable user groups based on short-term user characteristics | |
| Negoiță et al. | Research on online promoting methods used in a technological society | |
| Cui et al. | Targeting high value customers while under resource constraint: partial order constrained optimization with genetic algorithm | |
| Gubela et al. | Multiple treatment modeling for Target Marketing campaigns: A large-scale Benchmark Study | |
| US20230368226A1 (en) | Systems and methods for improved user experience participant selection | |
| CN116934372A (en) | Store operation customer data management method and system | |
| CN115719183A (en) | Power customer self-feedback service evaluation method and system based on weight dynamic grading |
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 |