CN112396498A - Commodity sales promotion method, device, equipment and storage medium - Google Patents
Commodity sales promotion method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN112396498A CN112396498A CN202011395091.5A CN202011395091A CN112396498A CN 112396498 A CN112396498 A CN 112396498A CN 202011395091 A CN202011395091 A CN 202011395091A CN 112396498 A CN112396498 A CN 112396498A
- Authority
- CN
- China
- Prior art keywords
- sales promotion
- commodity
- commodities
- index
- channel
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0623—Item investigation
- G06Q30/0625—Directed, with specific intent or strategy
- G06Q30/0629—Directed, with specific intent or strategy for generating comparisons
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a commodity sales promotion method, a device, equipment and a storage medium, wherein the method comprises the following steps: acquiring a commodity set containing all commodities promoted in a specified time period of a specified area; obtaining the value of each preset index characteristic corresponding to each commodity in the commodity set under each sales promotion channel; the preset index features are features for showing the sales promotion effect of the commodities in different sales promotion channels; and determining an optimal sales promotion channel when the commodities are sold based on the values of the preset index characteristics corresponding to the commodities in the sales promotion channels, and realizing sales promotion of the corresponding commodities by using the optimal sales promotion channel. Therefore, the method and the device can analyze the best effect when different commodities are promoted through which promotion channels based on historical commodity promotion data, and further utilize the best promotion channels to promote corresponding commodities, so that commodity promotion can be efficiently realized.
Description
Technical Field
The invention relates to the technical field of internet data processing, in particular to a commodity sales promotion method, a commodity sales promotion device, commodity sales promotion equipment and a storage medium.
Background
When the marketing activity is carried out by the sales platform, a certain brand of activity or a certain category of activity is usually played, but the time for the sales to reach the user is limited because the activities are usually limited; therefore, how to efficiently implement merchandising is a problem to be solved by those skilled in the art.
Disclosure of Invention
The invention aims to provide a commodity sales promotion method, a commodity sales promotion device, commodity sales promotion equipment and a storage medium, which can realize commodity sales promotion efficiently.
In order to achieve the above purpose, the invention provides the following technical scheme:
a merchandising method comprising:
acquiring a commodity set containing all commodities promoted in a specified time period of a specified area;
obtaining the value of each preset index characteristic corresponding to each commodity in the commodity set under each sales promotion channel; the preset index features are features for showing the sales promotion effect of the commodities in different sales promotion channels;
and determining an optimal sales promotion channel when the commodities are sold based on the values of the preset index characteristics corresponding to the commodities in the sales promotion channels, and realizing sales promotion of the corresponding commodities by using the optimal sales promotion channel.
Preferably, the determining an optimal sales promotion channel for sales promotion of each commodity based on the value of each preset index feature corresponding to each commodity in each sales promotion channel includes:
and calculating the comprehensive scores of the commodities corresponding to the sales promotion channels based on the values of the preset index characteristics, and determining the sales promotion channel corresponding to the highest comprehensive score in the comprehensive scores of the commodities corresponding to the sales promotion channels, wherein the sales promotion channel is the optimal sales promotion channel when the corresponding commodities are sold.
Preferably, the calculating of the comprehensive score of each commodity corresponding to each sales promotion channel based on the value of each preset index feature includes:
dividing all index features into a plurality of layers, and acquiring the weight of each index feature; the preset index features are index features positioned on the last layer, and any index feature in any layer except the last layer corresponds to a plurality of index features in the layer below the last layer;
and determining the last layer as a current layer, performing weighted calculation by using the scores and weights to which the values of all the index features corresponding to the same index feature of the previous layer in the current layer belong to obtain the scores to which the values of all the index features in the previous layer of the current layer belong, determining the previous layer of the current layer as the current layer, performing weighted calculation by using the scores and weights to which the values of all the index features in the current layer belong to obtain the comprehensive score if the current layer is the first layer, and otherwise, returning to execute the step of performing weighted calculation by using the scores and weights to which the values of all the index features corresponding to the same index feature of the previous layer belong in the current layer.
Preferably, after obtaining the weight of each index feature, the method further includes:
and normalizing the weights of the index features to enable the sum of the weights of all index features contained in each layer to be 1.
Preferably, the preset index features include labor cost, time cost and promotion success rate, the index features on the upper layer of the preset index features include comprehensive cost and promotion efficiency, the labor cost and the time cost both correspond to the comprehensive cost, and the promotion success rate corresponds to the promotion efficiency.
Preferably, the determining an optimal sales promotion channel for sales promotion of each commodity based on the value of each preset index feature corresponding to each commodity in each sales promotion channel includes:
taking the commodity identification information of each commodity and the value corresponding to each preset index characteristic as samples, and taking a sales promotion channel used when each commodity is sold as a label value of the corresponding sample;
processing the classification model by using each sample and each label value to obtain a corresponding promotion classification model;
and inputting the commodity identification information of each commodity into the sales promotion classification model, and determining a sales promotion channel output by the sales promotion classification model as an optimal sales promotion channel when the corresponding commodity is sold.
Preferably, the classification model is specifically a K-nearest neighbor algorithm.
A merchandising apparatus comprising:
a first obtaining module to: acquiring a commodity set containing all commodities promoted in a specified time period of a specified area;
a second obtaining module to: obtaining the value of each preset index characteristic corresponding to each commodity in the commodity set under each sales promotion channel; the preset index features are features for showing the sales promotion effect of the commodities in different sales promotion channels;
a promotion module to: and determining an optimal sales promotion channel when the commodities are sold based on the values of the preset index characteristics corresponding to the commodities in the sales promotion channels, and realizing sales promotion of the corresponding commodities by using the optimal sales promotion channel.
A merchandising apparatus comprising:
a memory for storing a computer program;
a processor for implementing the steps of the merchandising method according to any one of the preceding claims when said computer program is executed.
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the merchandising method according to any one of the preceding claims.
The invention provides a commodity sales promotion method, a commodity sales promotion device, commodity sales promotion equipment and a storage medium, wherein the method comprises the following steps: acquiring a commodity set containing all commodities promoted in a specified time period of a specified area; obtaining the value of each preset index characteristic corresponding to each commodity in the commodity set under each sales promotion channel; the preset index features are features for showing the sales promotion effect of the commodities in different sales promotion channels; and determining an optimal sales promotion channel when the commodities are sold based on the values of the preset index characteristics corresponding to the commodities in the sales promotion channels, and realizing sales promotion of the corresponding commodities by using the optimal sales promotion channel. According to the method and the system, after the commodities promoted in the appointed area within the appointed time period and the values of the preset index characteristics of the commodities under different promotion channels are obtained, the promotion channels which enable the promotion effect of the commodities to be the best can be determined based on the values, and then promotion of the corresponding commodities is achieved through the determined promotion channels. Therefore, the method and the device can analyze the best effect when different commodities are promoted through which promotion channels based on historical commodity promotion data, and further utilize the best promotion channels to promote corresponding commodities, so that commodity promotion can be efficiently realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a method for merchandising according to an embodiment of the present invention;
fig. 2 is a first flowchart of a marketing channel for determining the best goods in a marketing method according to an embodiment of the present invention;
fig. 3 is a second flowchart of a marketing channel for determining the best goods in a marketing method according to an embodiment of the present invention;
fig. 4 is a logic flow diagram of classification implemented by using a K-nearest neighbor algorithm in a merchandising method according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a merchandising apparatus according to an embodiment of 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, a flowchart of a method for promoting merchandise according to an embodiment of the present invention is shown, where the method may include:
s11: a set of products is obtained that contains all of the products promoted in the designated area for the designated period of time.
It should be noted that, the execution subject of the merchandising method provided by the embodiment of the present invention may be a corresponding merchandising device. The designated area and the designated time period may be set according to actual needs, for example, the designated area may be a certain city (e.g., a hound city), the designated time period may be a latest period of time (e.g., within the latest 90 days), and all the products promoted in the designated area within the designated time period may be all the products promoted in the designated area within the designated time period. In addition, when the commodity set is obtained, commodity identification information of each commodity can be obtained, as shown in table 1, the commodity identification information may include commodity names, commodity categories, commodity brands and the like, and the commodity categories may include background first-level categories to background fourth-level categories and the like.
TABLE 1
S12: acquiring the value of each preset index characteristic corresponding to each commodity in the commodity set under each sales promotion channel; the preset index features are features for showing the sales promotion effect of the commodities in different sales promotion channels.
According to the actual business scene, the promotion channel can comprise ground push (ground promotion) and electric push (telephone promotion); the preset index features can include labor cost, time cost and sales promotion success rate, and other features capable of showing sales promotion effect of commodities in different sales promotion channels can be set according to actual needs; wherein, the labor cost and the time cost can be obtained from a company database for promotion, and the promotion success rate can be calculated according to the following formula:
γ＝m/n
wherein n is the number of actual sales promotion users, m is the number of transaction users, and the transaction users can be defined as users who place orders within 24 hours after sales promotion.
S13: and determining an optimal sales promotion channel when the commodities are sold based on the values of the preset index characteristics corresponding to the commodities in the sales promotion channels, and realizing sales promotion of the corresponding commodities by using the optimal sales promotion channel.
After the values of the preset index characteristics corresponding to any commodity in different promotion channels are obtained, the promotion effects of the any commodity in different promotion channels can be determined based on the values, the promotion channel with the best promotion effect is determined to be the promotion channel which promotes the any commodity to be the best, and promotion of the any commodity is achieved by means of the promotion channel.
According to the method and the system, after the commodities promoted in the appointed area within the appointed time period and the values of the preset index characteristics of the commodities under different promotion channels are obtained, the promotion channels which enable the promotion effect of the commodities to be the best can be determined based on the values, and then promotion of the corresponding commodities is achieved through the determined promotion channels. Therefore, the method and the device can analyze the best effect when different commodities are promoted through which promotion channels based on historical commodity promotion data, and further utilize the best promotion channels to promote corresponding commodities, so that commodity promotion can be efficiently realized.
In a specific implementation manner, as shown in fig. 2, step S13 in the merchandising method according to the embodiment of the present invention may include:
s131: calculating the comprehensive scores of the commodities corresponding to the sales promotion channels based on the values of the preset index characteristics, and determining the sales promotion channel corresponding to the highest comprehensive score in the comprehensive scores of the commodities corresponding to the sales promotion channels as the optimal sales promotion channel when the corresponding commodities are sold;
s132: and realizing the sales promotion of corresponding commodities by utilizing an optimal sales promotion channel.
When an optimal promotion channel of any commodity is determined, calculating a comprehensive score of the any commodity when the any commodity is promoted in the any promotion channel based on values of the preset index features corresponding to the promotion channel of the any commodity, so as to obtain the comprehensive score of each promotion channel corresponding to each commodity; based on this, the comprehensive scores of any commodity corresponding to different promotion channels can be compared, if only one highest comprehensive score exists, the highest comprehensive score corresponding to the promotion channel is used as a promotion channel for promoting the any commodity later, and if a plurality of highest comprehensive scores exist, the electric promotion is preferentially selected as the promotion channel for promoting the any commodity. Therefore, the method and the device can compare the corresponding promotion effects of different promotion channels, select the promotion channel with the best promotion effect as the optimal promotion channel for realizing the promotion of the corresponding commodities, and ensure that the best promotion effect is achieved when promotion is realized.
The method for promoting commodities provided by the embodiment of the invention calculates the comprehensive scores of each commodity corresponding to each promotion channel based on the values of each preset index characteristic, and comprises the following steps:
dividing all index features into a plurality of layers, and acquiring the weight of each index feature; the preset index features are index features positioned on the last layer, and any index feature in any layer except the last layer corresponds to a plurality of index features in a layer below the preset index features;
and determining the last layer as a current layer, performing weighted calculation by using the scores and weights to which the values of all the index features corresponding to the same index feature of the previous layer in the current layer belong to obtain the scores to which the values of all the index features in the previous layer of the current layer belong, determining the previous layer of the current layer as the current layer, performing weighted calculation by using the scores and weights to which the values of all the index features in the current layer belong to obtain a comprehensive score if the current layer is the first layer, and otherwise, returning to execute the step of performing weighted calculation by using the scores and weights to which the values of all the index features corresponding to the same index feature of the previous layer belong in the current layer.
According to the method, all index features can be divided into a plurality of layers, each preset index feature is used as the index feature of the last layer, each index feature in the layer above the last layer corresponds to at least one index feature in the last layer, and each index feature in any layer except the last layer also corresponds to at least one index feature in the next layer; when the comprehensive score is calculated, the score and the weight of the value of at least one index feature corresponding to the same index feature are subjected to weighted summation calculation on the index features in any layer except the first layer to obtain the corresponding score as the score of the same index feature corresponding to the at least one index feature, and the score and the weight of the value of each feature index in the first layer are subjected to weighted summation calculation until the first layer is reached to obtain the final comprehensive score; wherein, AHP (analytic hierarchy process) and expert group decision method can be adopted to determine the weight of each index feature; according to the method, the comprehensive score obtained by final calculation can correspond to the index characteristics of each layer in a layer-by-layer calculation mode, and the method is more accurate and more effective.
The commodity sales method provided by the embodiment of the present invention, after obtaining the weight of each index feature, may further include:
the weights of the index features are normalized so that the sum of the weights of all the index features included in each layer is 1.
In the embodiment of the application, after all the index features are obtained, normalization processing can be performed on the index features, so that the sum of the weights of all the index features contained in any layer is 1, arrangement of data corresponding to the index features is achieved, and the data are more standard.
In a specific application scenario, the preset index features may include labor cost, time cost and promotion success rate, the index features on the upper layer of the preset index features may include comprehensive cost and promotion efficiency, the labor cost and the time cost both correspond to the comprehensive cost, and the promotion success rate corresponds to the promotion efficiency. Specifically, according to the embodiment of the application, the sales promotion success rate, the labor cost and the time cost are used as main characteristic factors influencing a sales promotion channel when the sales promotion effect evaluation is realized, the corresponding index characteristics of the upper layer can include the sales promotion efficiency and the comprehensive cost, the commodity profit can be increased under other application scenes, and the specific characteristic can be shown in table 2.
TABLE 2
For the index features in table 2, AHP (analytic hierarchy process) and expert group decision pair methods can be adopted to determine the weights of the index features on the same layer, normalization processing is performed, after normalization processing, the sum of the weights of the index features on the same layer is equal to 1, and the exemplary results are shown in table 3.
TABLE 3
Setting a grading standard of a promotion channel, and calculating the comprehensive score of different promotion channels of each commodity according to the weight of each index characteristic; the results of scoring criteria are shown in table 4.
TABLE 4
When the score of the value of the index feature in any layer except the last layer is calculated, the calculation can be realized according to the following formula:
wherein S is(i)A score indicating a value of any index feature of the i-th layer among the index features,
indicates the score to which the value of the index feature j of the (i + 1) th layer belongs,
indicating the weight of the i +1 th index feature j, the i +1 th index feature j corresponding to the i-th arbitrary index feature, and n indicating the i +1 th index featureThe number of index features corresponding to any index feature of the ith layer.
In summary, the method and the system determine the sales promotion channel of the commodity, calculate the labor cost, the time cost and the sales promotion success rate of the commodity, obtain the evaluation scores of different sales promotion channels of the commodity according to the weight of each index characteristic, and finally determine the sales promotion channel which enables the sales promotion success effect to be the best based on historical sales promotion data, so that the human effect is maximized, and meanwhile, the order quantity is increased.
In another specific implementation manner, as shown in fig. 3, step S13 in the merchandising method according to the embodiment of the present invention may include:
s133: and taking the commodity identification information of each commodity and the value corresponding to each preset index characteristic as samples, and taking a sales promotion channel used when each commodity is sold as a label value of the corresponding sample.
When the optimal promotion channel is determined, the commodity identification information of each commodity can be obtained firstly, the commodity identification information of any commodity and the value corresponding to each preset index characteristic when any promotion channel is used for promotion of the any commodity are used as samples, the any promotion channel used by the any commodity is used as a corresponding label value, and the corresponding samples of all commodities and the corresponding label value are obtained as sample data; some of the samples and the label values are selected as a training data set, and the remaining samples and the label values are selected as a testing data set, wherein if the sample data includes 90 days of data, the training data set may include 70 days of sample data, and the testing data set may include 20 days of sample data.
S134: and processing the classification model by using each sample and each label value to obtain a corresponding promotion classification model.
The classification model may be specifically a K-nearest neighbor algorithm. After the training data set and the test data set are obtained, a corresponding K nearest neighbor algorithm (KNN algorithm) module can be called from a scimit-learn library (a machine learning tool library) to serve as a classification model, the training data set is used for training the classification model, and the test data set is used for testing the classification model; in addition, in the process of training and testing the classification model, in order to further improve the accuracy on the sample data, the embodiment of the application can adjust the classification model, for example, the hyper-parameter K in the K-nearest neighbor algorithm is adjusted in an experimental search mode to achieve higher accuracy.
S135: and inputting the commodity identification information of each commodity into the sales promotion classification model, and determining a sales promotion channel output by the sales promotion classification model as an optimal sales promotion channel when the corresponding commodity is sold.
For the commodities of which the optimal promotion channel is to be determined, the commodity identification information of the commodities can be input into the promotion classification model, so that the label value output by the promotion classification model is obtained, namely the optimal promotion channel of the commodities corresponding to the input commodity identification information is obtained. In a specific implementation manner, the logic for implementing classification by using the K-nearest neighbor algorithm may be as shown in fig. 4, where the new sample is a sample that does not include a label value, and the training data is sample data included in the training data set.
S136: and realizing the sales promotion of corresponding commodities by utilizing an optimal sales promotion channel.
After obtaining each commodity promoted in a specified time period of a specified area, commodity identification information of each commodity, a promotion channel used by each commodity and values of each preset index characteristic corresponding to each commodity under different promotion channels, the method can utilize the commodity identification information of each commodity, the values corresponding to each preset index and the promotion channel used to train a classification model to obtain a corresponding promotion classification model, further utilize the promotion classification model to determine an optimal promotion channel of the commodity based on the commodity identification information of the commodity so as to realize promotion of the corresponding commodity based on the promotion channel; therefore, after the model training is realized based on the commodity relevant information, the prediction of the sales promotion channel can be realized based on the model, so that the sales promotion channel is determined when the commodities are sold based on historical commodity sales promotion data quickly and effectively.
An embodiment of the present invention further provides a merchandising apparatus, as shown in fig. 5, which may include:
a first obtaining module 11, configured to: acquiring a commodity set containing all commodities promoted in a specified time period of a specified area;
a second obtaining module 12, configured to: acquiring the value of each preset index characteristic corresponding to each commodity in the commodity set under each sales promotion channel; the preset index features are features for showing the sales promotion effect of the commodities in different sales promotion channels;
a promotion module 13 for: and determining an optimal sales promotion channel when the commodities are sold based on the values of the preset index characteristics corresponding to the commodities in the sales promotion channels, and realizing sales promotion of the corresponding commodities by using the optimal sales promotion channel.
In an embodiment of the invention, a merchandising module includes:
a first determination unit configured to: and calculating the comprehensive scores of the commodities corresponding to the sales promotion channels based on the values of the preset index characteristics, and determining the sales promotion channel corresponding to the highest comprehensive score in the comprehensive scores of the commodities corresponding to the sales promotion channels, wherein the sales promotion channel is the optimal sales promotion channel when the corresponding commodities are sold.
In an embodiment of the present invention, a merchandising apparatus includes:
a calculation subunit to: dividing all index features into a plurality of layers, and acquiring the weight of each index feature; determining the last layer as the current layer, performing weighted calculation by using the scores and weights to which the values of all the index features corresponding to the same index feature of the previous layer in the current layer belong to obtain the scores to which the values of all the index features in the previous layer of the current layer belong, determining the previous layer of the current layer as the current layer, performing weighted calculation by using the scores and weights to which the values of all the index features in the current layer belong to obtain a comprehensive score if the current layer is the first layer, and otherwise, returning to perform the step of performing weighted calculation by using the scores and weights to which the values of all the index features corresponding to the same index feature of the previous layer belong in the current layer; the preset index features are index features located in the last layer, and any index feature in any layer except the last layer corresponds to a plurality of index features in a layer below the last layer.
The merchandising device provided by the embodiment of the present invention may further include:
a normalization processing module configured to: after the weights of the index features are obtained, normalization processing is performed on the weights of the index features, so that the sum of the weights of all the index features contained in each layer is 1.
According to the commodity sales promotion device provided by the embodiment of the invention, the preset index characteristics can comprise labor cost, time cost and sales promotion success rate, the index characteristics on the upper layer of the preset index characteristics can comprise comprehensive cost and sales promotion efficiency, the labor cost and the time cost correspond to the comprehensive cost, and the sales promotion success rate corresponds to the sales promotion efficiency.
In an embodiment of the invention, a merchandising module includes:
a second determination unit configured to: taking the commodity identification information of each commodity and the value corresponding to each preset index characteristic as samples, and taking a sales promotion channel used when each commodity is sold as a label value of the corresponding sample; processing the classification model by using each sample and each label value to obtain a corresponding promotion classification model; and inputting the commodity identification information of each commodity into the sales promotion classification model, and determining a sales promotion channel output by the sales promotion classification model as an optimal sales promotion channel when the corresponding commodity is sold.
According to the commodity sales promotion device provided by the embodiment of the invention, the classification model can be a K nearest neighbor algorithm.
The embodiment of the invention also provides a commodity sales promotion device, which can comprise:
a memory for storing a computer program;
a processor for implementing the steps of the merchandising method according to any one of the above when executing the computer program.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, can implement the steps of any of the merchandising methods as described above.
It should be noted that, for the description of the relevant parts in the merchandising apparatus, the device and the storage medium provided by the embodiment of the present invention, reference is made to the detailed description of the corresponding parts in the merchandising method provided by the embodiment of the present invention, and no further description is given here. In addition, parts of the technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail, so as to avoid redundant description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method of merchandising, comprising:
acquiring a commodity set containing all commodities promoted in a specified time period of a specified area;
obtaining the value of each preset index characteristic corresponding to each commodity in the commodity set under each sales promotion channel; the preset index features are features for showing the sales promotion effect of the commodities in different sales promotion channels;
and determining an optimal sales promotion channel when the commodities are sold based on the values of the preset index characteristics corresponding to the commodities in the sales promotion channels, and realizing sales promotion of the corresponding commodities by using the optimal sales promotion channel.
2. The method of claim 1, wherein determining an optimal marketing channel for each commodity to market based on the value of each preset index feature corresponding to each commodity in each marketing channel comprises:
and calculating the comprehensive scores of the commodities corresponding to the sales promotion channels based on the values of the preset index characteristics, and determining the sales promotion channel corresponding to the highest comprehensive score in the comprehensive scores of the commodities corresponding to the sales promotion channels, wherein the sales promotion channel is the optimal sales promotion channel when the corresponding commodities are sold.
3. The method of claim 2, wherein calculating a composite score for each sales channel corresponding to each commodity based on the value of each preset index feature comprises:
dividing all index features into a plurality of layers, and acquiring the weight of each index feature; the preset index features are index features positioned on the last layer, and any index feature in any layer except the last layer corresponds to a plurality of index features in the layer below the last layer;
and determining the last layer as a current layer, performing weighted calculation by using the scores and weights to which the values of all the index features corresponding to the same index feature of the previous layer in the current layer belong to obtain the scores to which the values of all the index features in the previous layer of the current layer belong, determining the previous layer of the current layer as the current layer, performing weighted calculation by using the scores and weights to which the values of all the index features in the current layer belong to obtain the comprehensive score if the current layer is the first layer, and otherwise, returning to execute the step of performing weighted calculation by using the scores and weights to which the values of all the index features corresponding to the same index feature of the previous layer belong in the current layer.
4. The method of claim 3, wherein after obtaining the weight of each index feature, further comprising:
and normalizing the weights of the index features to enable the sum of the weights of all index features contained in each layer to be 1.
5. The method according to claim 4, wherein the predetermined index features comprise labor cost, time cost and sales promotion success rate, the index features of the layer above the predetermined index features comprise comprehensive cost and sales promotion efficiency, the labor cost and the time cost both correspond to the comprehensive cost, and the sales promotion success rate corresponds to the sales promotion efficiency.
6. The method of claim 1, wherein determining an optimal marketing channel for each commodity to market based on the value of each preset index feature corresponding to each commodity in each marketing channel comprises:
taking the commodity identification information of each commodity and the value corresponding to each preset index characteristic as samples, and taking a sales promotion channel used when each commodity is sold as a label value of the corresponding sample;
processing the classification model by using each sample and each label value to obtain a corresponding promotion classification model;
and inputting the commodity identification information of each commodity into the sales promotion classification model, and determining a sales promotion channel output by the sales promotion classification model as an optimal sales promotion channel when the corresponding commodity is sold.
7. The method according to claim 6, characterized in that the classification model is in particular a K-nearest neighbor algorithm.
8. A merchandising apparatus, comprising:
a first obtaining module to: acquiring a commodity set containing all commodities promoted in a specified time period of a specified area;
a second obtaining module to: obtaining the value of each preset index characteristic corresponding to each commodity in the commodity set under each sales promotion channel; the preset index features are features for showing the sales promotion effect of the commodities in different sales promotion channels;
a promotion module to: and determining an optimal sales promotion channel when the commodities are sold based on the values of the preset index characteristics corresponding to the commodities in the sales promotion channels, and realizing sales promotion of the corresponding commodities by using the optimal sales promotion channel.
9. A merchandising apparatus, comprising:
a memory for storing a computer program;
processor for implementing the steps of the merchandising method according to any one of claims 1 to 8 when executing said computer program.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the merchandising method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011395091.5A CN112396498A (en) | 2020-12-03 | 2020-12-03 | Commodity sales promotion method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011395091.5A CN112396498A (en) | 2020-12-03 | 2020-12-03 | Commodity sales promotion method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112396498A true CN112396498A (en) | 2021-02-23 |
Family
ID=74605023
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011395091.5A Pending CN112396498A (en) | 2020-12-03 | 2020-12-03 | Commodity sales promotion method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112396498A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113220463A (en) * | 2021-05-31 | 2021-08-06 | 中科曙光国际信息产业有限公司 | Binding strategy inference method and device, electronic equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886168A (en) * | 2012-12-19 | 2014-06-25 | 腾讯科技（深圳）有限公司 | Multi-channel analysis method and device based on analytic hierarchy process |
-
2020
- 2020-12-03 CN CN202011395091.5A patent/CN112396498A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886168A (en) * | 2012-12-19 | 2014-06-25 | 腾讯科技（深圳）有限公司 | Multi-channel analysis method and device based on analytic hierarchy process |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113220463A (en) * | 2021-05-31 | 2021-08-06 | 中科曙光国际信息产业有限公司 | Binding strategy inference method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106485562B (en) | Commodity information recommendation method and system based on user historical behaviors | |
| CN106372249B (en) | A kind of clicking rate predictor method, device and electronic equipment | |
| CN110163647A (en) | A kind of data processing method and device | |
| JP2002092305A (en) | Score calculating method, and score providing method | |
| CN104750674B (en) | A kind of man-machine conversation's satisfaction degree estimation method and system | |
| CN107730131A (en) | The ability prediction of mass-rent software developer a kind of and recommendation method, apparatus | |
| CN111444380B (en) | Music search ordering method, device, equipment and storage medium | |
| CN113191838B (en) | Shopping recommendation method and system based on heterogeneous graph neural network | |
| CN109299245A (en) | The method and apparatus that knowledge point is recalled | |
| CN108304426A (en) | The acquisition methods and device of mark | |
| CN109615504A (en) | Products Show method, apparatus, electronic equipment and computer readable storage medium | |
| CN112132618A (en) | Commodity price determining method, device and equipment and readable storage medium | |
| CN113407854A (en) | Application recommendation method, device and equipment and computer readable storage medium | |
| CN111861679A (en) | Commodity recommendation method based on artificial intelligence | |
| CN112396498A (en) | Commodity sales promotion method, device, equipment and storage medium | |
| CN108074122A (en) | Product beta test recommends method, apparatus and server | |
| CN108228950A (en) | A kind of information processing method and device | |
| US20200302541A1 (en) | Resource processing method, storage medium, and computer device | |
| CN108074071A (en) | A kind of project data processing method and processing device | |
| CN111368131A (en) | User relationship identification method and device, electronic equipment and storage medium | |
| CN112365302B (en) | Product recommendation network training method, device, equipment and medium | |
| CN115439180A (en) | Target object determination method and device, electronic equipment and storage medium | |
| CN107291722B (en) | Descriptor classification method and device | |
| CN114020957A (en) | Search algorithm evaluation method and device, computing equipment and medium | |
| KR101886418B1 (en) | A System of Stock Price Simulation Based on GPU |
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 |