CN113554457B - Intelligent poster generation method and device suitable for e-commerce platform and storage medium - Google Patents
Intelligent poster generation method and device suitable for e-commerce platform and storage medium Download PDFInfo
- Publication number
- CN113554457B CN113554457B CN202110762736.2A CN202110762736A CN113554457B CN 113554457 B CN113554457 B CN 113554457B CN 202110762736 A CN202110762736 A CN 202110762736A CN 113554457 B CN113554457 B CN 113554457B
- Authority
- CN
- China
- Prior art keywords
- commodity
- data
- poster
- order
- promotion
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 239000011159 matrix material Substances 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 10
- 239000002994 raw material Substances 0.000 description 13
- 230000001737 promoting effect Effects 0.000 description 11
- 238000004458 analytical method Methods 0.000 description 10
- 238000013145 classification model Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 239000000463 material Substances 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 5
- 239000003086 colorant Substances 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000003379 elimination reaction Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 235000013361 beverage Nutrition 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000003064 k means clustering Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000969 carrier Substances 0.000 description 1
- 239000012459 cleaning agent Substances 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 235000011194 food seasoning agent Nutrition 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 235000008446 instant noodles Nutrition 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 235000011888 snacks Nutrition 0.000 description 1
- 238000012795 verification 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an intelligent poster generation method, device and storage medium suitable for an e-commerce platform, wherein the method comprises the following steps: acquiring a shop range selected by a user; generating a promoted commodity list according to historical order data of shops in the shop range; acquiring corresponding commodity pictures and commodity promotion price data according to the promotion commodity list; acquiring a poster template selected by a user; and filling the commodity pictures and commodity promotion price data to the appointed position of the poster template according to the ordering of the promotion commodity list. The intelligent poster generation method, the intelligent poster generation device and the storage medium are suitable for the electronic commerce platform, and the intelligent poster generation method, the intelligent poster generation device and the storage medium are used for automatically selecting sales promotion commodities in the posters and generating the posters according to the shop range selected by a user.
Description
Technical Field
The application relates to the field of data management of electronic commerce platforms, in particular to an intelligent poster generation method, device and storage medium suitable for electronic commerce platforms.
Background
The electronic commerce platform provides commodity purchasing and other services for buyers through the Internet, and the transaction scale and the transaction frequency of the electronic commerce platform are greatly increased due to the development of the mobile Internet technology. Unlike traditional off-line sales, on-line e-commerce platform sales often require on-line acquisition and drainage. For example, staff on the e-commerce platform needs to issue promotion information on the social platform in a manner of poster, etc. so as to promote shopping will of the buyer on the e-commerce platform.
The prior art poster of the e-commerce platform sales promotion comprises two types, namely a fixed sales promotion date, such as 618, double eleven and legal holidays, which are uniformly manufactured by the artists of the e-commerce platform and then sent to the salespersons of the e-commerce platforms, and then the salespersons launch the sales promotion on the social platform, and the prior art poster is manufactured by the artists of the e-commerce platform or the salespersons according to the market condition, but the art poster manufacturing time is overlong, the price data is lagged and the drawing of the art poster is slower no matter the art designer or the salesperson manufactures the art poster.
Disclosure of Invention
In order to solve the defects of the prior art, the application provides an intelligent poster generation method suitable for an e-commerce platform, which comprises the following steps: acquiring a shop range selected by a user; generating a promoted commodity list according to historical order data of shops in the shop range; acquiring corresponding commodity pictures and commodity promotion price data according to the promotion commodity list; acquiring a poster template selected by a user; and filling the commodity pictures and commodity promotion price data to the appointed position of the poster template according to the ordering of the promotion commodity list.
Further, the step of acquiring the shop range selected by the user comprises the following steps: and automatically selecting the shop range according to the corresponding relation between the account of the user and the shop.
Further, the step of obtaining the corresponding commodity picture and commodity promotion price data according to the promotion commodity list further comprises the following steps: acquiring historical order data of stores in the store range; analyzing order feature data from the historical order data; inputting the order feature data into a purchase intent prediction model to cause the purchase intent prediction model to output purchase intent prediction data; generating a sales promotion commodity sub-table of the store according to the purchase intention prediction data; and summarizing sales promotion commodity sub-tables of all shops in the shop range to form the sales promotion commodity list.
Further, the parsing the order feature data from the historical order data includes the following steps: setting an observation period of the historical order data; collecting the historical order data of the store in the observation period according to the total order number, the total sum, the order frequency value and the frequency value of each commodity; the total number of orders, the summarized amount, the order frequency value and the frequency value of each collected commodity are correspondingly numbered to the commodity, and then a data matrix is constructed as order characteristic data; wherein the commodity number is the SKU value of the commodity; the total number of orders is total order data related to the commodity in the observation period; the total amount is the sum of the order amounts of the commodity in the observation period; the order frequency value is the average value of the total number of orders relative to the observation period, and the frequency value is the ratio of the sum to the order frequency value.
Further, the purchase intention prediction data is a matrix identical to the data matrix of the order feature data.
Further, the generating a sales promotion sub-table of the store according to the purchase intention prediction data comprises the following steps: and sequentially filling the data in the matrix into form data according to the frequency value of the data in the matrix of the purchase intention prediction data serving as a row sequencing basis, wherein the form data is a sales promotion commodity sub-table.
Further, the step of summarizing the sales promotion commodity sub-tables of all shops in the shop range to form the sales promotion commodity list comprises the following steps: summing the total number of orders and the sum of the amounts in each sales promotion commodity sub-table according to the SKU value of the commodity, and then calculating the order frequency value and the frequency value after corresponding sum data; the order of the rows in the promotional item list is arranged according to the magnitude of the frequency value as a basis for the ordering of the rows.
Further, the step of filling the commodity pictures and the commodity promotion price data to the formulated positions of the poster templates according to the ordering of the promotion commodity list comprises the following steps: setting a plurality of commodity filling positions for each poster template; setting a filling sequence number for each commodity filling position; filling and matching the goods with the front order of the sales promotion goods list with filling positions with larger filling serial numbers in the poster template; and according to the matching relation between the commodity and the filling position, invoking commodity pictures and commodity promotion price data of the commodity to fill the commodity pictures and commodity promotion price data into the filling position of the poster template.
As another aspect of the present application, the present application also provides an intelligent poster generating apparatus adapted for an e-commerce platform, including: a memory for storing a computer program; and the processor is used for realizing the intelligent poster generation method suitable for the e-commerce platform and suitable for the e-commerce platform when executing the computer program.
As another aspect of the present application, there is also provided a computer client storage medium having stored therein a computer program which, when executed by a processor, implements the intelligent poster generation method suitable for an e-commerce platform as described above.
The application has the advantages that: provided are an intelligent poster generation method, device and storage medium suitable for an electronic commerce platform, wherein the intelligent poster generation method, device and storage medium are used for automatically selecting sales promotion commodities in a poster and generating the poster according to a shop range selected by a user.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, are incorporated in and constitute a part of this specification. The drawings and their description are illustrative of the application and are not to be construed as unduly limiting the application. In the drawings:
FIG. 1 is a schematic diagram of steps of a smart poster generation method suitable for an e-commerce platform according to one embodiment of the application;
FIG. 2 is a schematic diagram of a purchase intent prediction model in accordance with one embodiment of the application;
FIG. 3 is a schematic matrix diagram of order characteristic data in accordance with one embodiment of the application;
FIG. 4 is a schematic illustration of a user-selected poster template in the method of FIG. 1;
FIG. 5 is a schematic illustration of a poster generated according to the method shown in FIG. 1;
FIG. 6 is a schematic diagram of steps of a machine learning based intelligent poster generation method according to one embodiment of the present application;
FIG. 7 is a schematic diagram of a picture classification model according to an embodiment of the application;
FIG. 8 is a schematic diagram of a poster analysis model according to one embodiment of the application;
FIG. 9 is a schematic illustration of a history poster of the method of FIG. 6;
FIG. 10 is a raw material picture of the illustration type in the method shown in FIG. 6;
FIG. 11 is a raw material image of a tagline type in the method shown in FIG. 6;
FIG. 12 is a schematic illustration of a poster generated according to the method shown in FIG. 6;
fig. 13 is a schematic diagram showing the composition of device modules for performing the method according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
In order to facilitate the introduction of the technical scheme of the application, the following describes an e-commerce platform and an application scene to which the method of the application is applicable.
The electronic commerce platform is mainly used for shops such as 24-hour convenience stores and mini supermarkets, after the shops purchase goods from the electronic commerce platform, the electronic commerce platform combines the orders purchased by the shops through the electronic commerce platform and then matches the combined orders to corresponding suppliers and logistics carriers, so that the shops are purchased at a more preferential price and in a faster distribution mode. Compared with the electronic commerce platform facing the individual buyer, the electronic commerce platform facing the store has the characteristics of low purchasing frequency and large purchasing quantity, and the electronic commerce platform reduces single purchasing quantity through the internet technology, so that purchasing is more flexible. However, due to the inherent characteristics of store purchasing, the store is sensitive to commodity sales promotion due to the large single purchasing quantity, and sales personnel of the electronic commerce platform can send sales promotion information such as sales promotion poster to the store according to actual conditions so as to increase sales quantity or eliminate inventory. The application scene of the intelligent poster generation method is to help sales personnel of an e-commerce platform to obtain required propaganda posters from a system through simple operation.
Referring to fig. 1, the intelligent poster generation method applicable to the e-commerce platform of the present application comprises the following steps:
s101: the user selected store range is obtained.
S102: a promotional item list is generated based on historical order data for stores within the store range.
S103: and acquiring corresponding commodity pictures and commodity promotion price data according to the promotion commodity list.
S103: and acquiring the poster template selected by the user.
S104: and filling the commodity pictures and commodity promotion price data to the appointed position of the poster template according to the ordering of the promotion commodity list.
As a specific scheme, the intelligent poster generation method suitable for the e-commerce platform is mainly aimed at the fact that the user is sales personnel of the e-commerce platform. Namely, the users refer to sales personnel of the e-commerce platform.
In general, the salesperson of the e-commerce platform is responsible for a fixed customer group, and the system records the corresponding relationship between the corresponding customer and the salesperson, namely the corresponding relationship between the store and the user. Therefore, the user-selected shop range can be acquired and automatically selected by the system according to the corresponding relation between the shop and the user. Specifically, after the user logs in the e-commerce platform system, the user can display a detail list of stores managed by the user on the customer group management interface, and the user can select all the users managed by the user through the function of store full selection, or can manually select a plurality of stores which the user wants to target.
As a further preferred embodiment, the system classifies stores maintained by the user according to historical purchase orders of the stores to form different store attribute sets, and the user can select a certain range of stores by selecting a store attribute set. Specifically, the method for classifying the store attribute set includes the steps of: acquiring historical purchase order data of a store; generating three-dimensional attribute coordinates of the store according to historical purchase order data of the store; K-Means clustering operation is carried out by coordinate values of three-dimensional attribute coordinates of shops; and dividing the K-Means clustering operation result into a plurality of store attribute sets. More specifically, the dimension attribute coordinate construction includes the steps of: setting a commodity classification table to divide commodities into quick-elimination classes, living classes and stationery classes; classifying commodities in the historical purchase order data of a store into classifications of commodity classification tables according to the commodity classification tables; calculating the total classified price of the commodities in the classification of each commodity classification table of the store; three classifications of the commodity classification table are respectively used as coordinate axes to establish a coordinate system of three-dimensional attribute coordinates, and the total price of the classifications of the shops is used as a coordinate value.
Preferably, the system can set the length of the time period for collecting the historical purchase orders, such as quarterly or annually, as needed for analysis. Preferably, if the acquisition time period length is set to be annual in order to obtain a more stable order prediction model and store attribute set.
When the time period length is annual, the above method is specifically: the annual purchase orders of a store are summarized, the commodities in the summary are classified into three classifications according to the three classifications in the commodity classification table, the classification total prices of all the commodities in the three classifications are respectively counted, the classification total price of the store under the three classifications is the coordinate value of the store in the three-dimensional attribute coordinates, and the counting unit of the classification total price is hundred yuan in view of the time period length, so that the coordinate value is not excessively large, and the coordinate points of a representative circuit are excessively scattered due to the calculating unit in clustering operation.
By the three-dimensional attribute coordinate establishment and clustering operation, stores can be divided into different store attribute sets. According to ideal state, designing conception per se according to quick-elimination type, living type and stationery type is to divide shops into corresponding business district type, district type and school type, wherein the quick-elimination type in the business district type shop purchase order is main commodity purchase type; the living type in the shop purchase order of the district is the main purchase commodity type; stationery in the store purchase order of the school type is the main purchase commodity type. Alternatively, the quick-vanishing class may include: beverages, snack foods, instant noodles, and the like; the living classes may include: seasoning, cleaning agent and articles for daily use; stationery may include: stationery, toys, etc.
And when the actual data are sorted and analyzed, the attributes of a plurality of shops are found to be complex, if the shops are only classified into business district types, community types and school types, the classified highest total price of classification can be adopted to belong to the classification, namely the classification, but the model training is more difficult due to the fact that the simple classification is found through later model construction and verification. For example, even if a store is located as a school, the quick-release purchasing amount is larger than the stationery purchasing amount. Simple classification does not bring practical value to later analysis and model construction.
By adopting the scheme, stores can be divided into store attribute sets according to actual conditions through dimension division and three-dimensional clustering, and the store attribute sets reflect actual attributes instead of manually dividing into classification attributes.
Through classification of the store attribute set, a user can select a store in a certain range more specifically under the assistance of the system to push the targeted poster, and meanwhile, as the selection of the store range has influence on the generation of the subsequent poster, the more accurate selection of the targeted range is also beneficial to the effect of the generation of the later poster.
As a specific scheme, step S102 specifically includes the following steps:
S1021: historical order data for stores in a store range is obtained.
S1022: order characteristic data is parsed from the historical order data.
As a specific scheme, the specific method of step S1022 includes: setting an observation period of historical order data; collecting historical order data of stores in an observation period according to the commodity collection, and collecting the total number of orders, the total amount, the order frequency value and the frequency value of each commodity; the total number of orders, the sum of the orders, the order frequency value and the frequency value of each collected commodity are corresponding to the serial numbers of the commodities, and then a data matrix shown in figure 3 is constructed as order characteristic data. The number and amount of the commodity related to the order in the observation period of the store can be represented by the data matrix.
Wherein the commodity number is the SKU value of the commodity; the total number of orders is total order data related to the commodity in an observation period; the total amount is the sum of the order amount of the commodity in the observation period; the order frequency value is the average value of the total number of orders relative to the observation period, and the frequency value is the ratio of the sum to the order frequency value. In the data matrix shown in fig. 3, one week (monday to sunday) is taken as one observation period. The effect of the order frequency value reflects the frequency of the purchased goods, which can directly reflect the purchase intention of the store on the goods, but because of some quick-release goods with cheaper price, such as various beverages in summer, only paying attention to the purchase frequency can lead to neglecting the goods which are possibly out of stock or are possibly out of stock in the store, and especially the electronic commerce platform applied by the application has the promotion effect of improving the transaction frequency. Therefore, on the basis, the frequency value is added to the data matrix of the order characteristic data (also the data matrix of the purchase intention prediction data), and according to the algorithm of the frequency value, the frequency value reflects the price related to the average order, namely the average order amount of an order of a commodity in an observation period. The higher this value, the higher the amount paid per purchase by the user. Therefore, the comprehensive order frequency value and the frequency value can comprehensively analyze the purchase intention of the user for a certain commodity.
The purpose of the historical order data here is to predict purchase intention, not to determine the attribute type of the store, and thus the historical order data here is the historical order data within a certain observation period. And, the store range is determined according to the user selection, not all stores.
S1023: the order characteristic data is input to a purchase intent prediction model such that the purchase intent prediction model outputs purchase intent prediction data. Specifically, the purchase intention prediction data is a matrix identical to the data matrix of the order characteristic data. The purchase intention prediction model is a neural network model for predicting according to historical data, and as a preferred scheme, the purchase intention prediction model is a BP neural network model. The historical order data may be used to construct a data matrix as shown in fig. 3, and then the BP neural network model is trained by training the data matrix corresponding to the historical order data of one store until convergence is achieved as a purchase intention prediction model. Each store has a corresponding purchase intention prediction model, and training and prediction are performed in each store.
As a preferable scheme, considering that the sales promotion commodity books are not too much, the number of lines of the data matrix of the purchase intention prediction data and the order feature data can be set values, and the value range of the set values is 5 to 50; as a preferred option, the set value is 20 in order to obtain enough alternatives.
In the specific method, when historical data in an observation period is acquired, a matrix shown in fig. 3 is generated according to the method, then each row is ordered according to the frequency value, rows exceeding a set value are discarded, only the first 20 rows are reserved as a data matrix, and when the number of commodity rows is less than 20, the insufficient rows are set to be 0 values in a corresponding format. In other words, only the commodity with the frequency value of the first 20 in the observation period is analyzed and selected by the set value.
S1024: and generating a sales promotion commodity sub-table of the store according to the purchase intention prediction data. Specifically, this step S1024 includes the steps of: and (3) predicting data in the matrix of the data according to the purchase will, and sequentially filling the data in the matrix into table data which is a sales promotion commodity sub-table according to the frequency value as a row ordering basis.
S1025: and summarizing sales promotion commodity sub-tables of all shops in the range of the shops to form a sales promotion commodity list.
Specifically, summing the total number of orders and the sum of the amounts in each sales promotion commodity sub-table according to the SKU value of the commodity, and then calculating the order frequency value and the frequency value after corresponding sum data; the order of the rows in the promotional item list is arranged according to the magnitude of the frequency value as a basis for the ordering of the rows. More specifically, the total amount and total amount of orders for different products are accumulated according to the product SKU, so that the total amount and total amount of orders belonging to the product in the selected store range are obtained. It should be noted that the order frequency value and the frequency value may be directly accumulated, but since the order frequency value and the frequency value are rounded when the sub-table of each store is generated, the recalculated data according to the total number of the collected orders and the total amount is more accurate.
After obtaining the promotional commodity list, the user can directly use the promotional commodity list to generate a poster, and can manually select certain commodities in the promotional commodity list. As a preferred approach, the promotional item list may be embodied in a tabular interface in the management software of the e-commerce platform system. The user can realize the selection operation through a form interface of the operation management software. The generation of the promotional item list is automatically performed by the system in the background, and the user only needs to select the store range.
After acquiring the promotional item list or the promotional items selected based on the promotional item list, the user selects the corresponding items to be added to the poster. Specifically, the system prompts the user to select a poster template, which the user can select based on the number and type of merchandise promoted and the time of the promotion. The poster form is shown in fig. 4, with the basic background and fill locations. The filling positions are represented as rectangular frames in fig. 4, then filling serial numbers are set for each filling position according to the significance degree or the propaganda effect of the filling positions, larger filling serial numbers are set for filling positions with high significance degree or better propaganda effect, and then pictures of commodities selected by a user are filled into the filling positions according to the filling serial numbers. The earlier items in the list of promoted items are filled into filling locations with a greater filling number.
In addition, as a preferable scheme, filling positions of non-commodity pictures or propaganda characters can be further arranged in the poster template, and a user can fill the filling positions through manual selection or input, so that the poster shown in fig. 5 is formed.
As a further preferable scheme, each commodity has a plurality of pictures, and when the pictures are stored in the system and the commodity pictures are filled in filling positions by recording commodity SKU values in the picture file names, the current price data (including promotion prices) of the commodity, commodity names, commodity specifications and other data can be called from the system database, and meanwhile, the poster template records the data of prices, rules, coordinate positions of commodity names, fonts, colors and the like corresponding to the filling positions in addition to the coordinates (rectangular frames determined by four coordinate points) of the filling positions. Thus, after the corresponding commodity pictures are filled, the corresponding commodity name, price and specification text data are automatically generated. Namely, as a preferable scheme, the intelligent poster generating method of the application further comprises the following steps: and acquiring the commodity name, commodity price and commodity specification of the commodity according to the SKU value of the commodity picture, and generating character data for setting fonts and colors at the relative preset position of the filling position according to the filling relation between the commodity picture and the filling position. The text data may or may not overlap with the commodity picture in the poster.
By adopting the intelligent poster generation method suitable for the e-commerce platform, a user can be helped to select a group of shops from the system as audiences, and targeted promotion posters can be rapidly generated according to the purchase will of the shops.
In the above scheme, the user still needs to select the poster template by himself, and can only process on the basis of the original poster template, thus limiting the diversity of the generated posters.
As another aspect of the present application, the present application also provides a machine learning-based intelligent poster generation method, which is mainly used for solving the problem of generating a poster based on raw material pictures, and specifically, the machine learning-based intelligent poster generation method includes the following steps:
S201: and acquiring the raw material picture selected by the user.
S202: the raw material picture is input into a picture classification model so that the picture classification model outputs the picture type of the raw material picture.
S203: and inputting the raw material pictures and the picture types thereof into a poster analysis model so that the poster analysis model outputs a preset poster template.
S204: and acquiring an operation instruction of a user so as to correspond the raw material picture to a preset position of a preset poster template.
S205: and matching the promotion data or the price data to the peripheral position of the raw material picture in the preset poster template.
Specifically, in step S201, acquiring the picture selected by the user may include: commodity pictures, background pictures, picture-inserting pictures and slogan pictures. The commodity picture can be obtained from commodities in the promotion commodity list in the method. That is, the user can select the commodity drawing through the above scheme. And the background pictures, the artwork pictures and the tagline pictures can be obtained by the user from a gallery or the internet.
In step S202, the types of the selected pictures may be acquired through a picture classification model, specifically, a CNN neural network model.
As a more specific approach, the picture classification model may be trained by: acquiring the picture data of commodities, backgrounds, illustrations and slogans in the historical poster according to the material data of the historical poster; taking picture data of commodities, backgrounds, inserts and slogans as input data, and taking picture types as output data to train a picture classification model; and training a poster analysis model by taking the picture data and the picture types of commodities, backgrounds, inserted pictures and slogans as input data and taking the historical posters as output data.
The system files the poster and the original materials in the historical data by the artists of the electronic commerce platform, then divides the pictures in the original materials into commodities, backgrounds, pictures and slogans in a manual labeling mode, and then trains a picture classification model. Of course, an externally trained neural network model may also be utilized as the picture classification model.
After classifying the pictures, inputting the raw materials and the picture types thereof into a poster analysis model, and outputting a preset poster template through the poster analysis model.
Specifically, referring to fig. 8, the system archives a poster and an original material made by an artist of an e-commerce platform in history data, then divides pictures in the original material into commodities, backgrounds, illustrations and slogans by means of manual labeling, takes the pictures and picture types as input data, and trains a convolutional neural network as a poster analysis model by taking the corresponding poster as output data. As a more specific scheme, the new poster generated by the method of the application can be used as a training set to train the convolutional neural network, namely, after the poster template is obtained by the poster prediction model, the input raw material picture and the final poster generated by the user operation are respectively used as input data and output data in the further training set of the poster prediction model, and meanwhile, the generated final poster forms a new poster template (also can be regarded as the preset poster template) in a mode of inheriting the template attribute of the preset poster template. Specifically, the template attributes of the poster template include the picture coordinates of various kinds of pictures, and data such as set fonts and colors for automatically generating text data as described above.
As a specific scheme, the setting of the preset poster template further includes the following steps: acquiring picture coordinates of commodities, backgrounds, inserting pictures and slogan pictures in the historical poster according to the material data of the historical poster; and generating a rectangular picture frame for marking the filling position of the picture according to the picture coordinates of the picture in the historical poster.
More specifically, if the picture is rectangular, the picture coordinates are coordinate values of four vertices, and corresponding picture types are set for the set of coordinates in the system, such as a set value 001 representing a commodity picture and 002 representing a background picture; then, the layer sequence of the picture is set for the set of coordinates, for example, 001 represents the uppermost layer, and in this way, the overlapping relationship between the position and display of the picture can be determined. As a further scheme, the picture coordinates of the commodity picture with the picture type are also added with corresponding commodity names, commodity specifications, commodity prices and other text data positions and font parameters. The function of generating a rectangular frame is to provide a user to drag a picture into a poster template reference position. As a further preference, the poster template still displays the original picture when displayed to the user, and the system prompts the user whether to replace the picture in the template or not by dragging the raw material picture to the corresponding position, so that the user can select to keep the picture in the original poster template.
Fig. 9 shows a poster template, fig. 10 is a user-selected pictorial picture, fig. 11 is a user-selected banner picture, and assuming that the user-selected merchandise picture is not shown in fig. 9, the system generates the poster shown in fig. 12 according to the above method by dragging the pictures shown in fig. 10 and 11 to the poster template shown in fig. 9 according to the poster template shown in fig. 9 and the user. The poster template as shown in fig. 9 can be obtained by inputting these commodity pictures and picture types in fig. 12 and the pictures and picture types shown in fig. 10, 11 to the poster analysis model.
By the method, a user can automatically obtain the required poster template by dragging the raw material picture, so that the efficiency of generating the poster is improved, and commodities and related announced data related to the poster are automatically generated by the method through selecting an audience store.
As another aspect of the present application, as shown in fig. 13, the present application also provides a server 300, i.e., a device executing a program, which includes a memory 301 and a processor 302. Wherein the memory 301 is for storing a computer program and the processor 302 is for implementing the steps of the method as provided above when the computer program is executed.
The application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method as provided above.
The application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method as provided above.
The above is only a preferred embodiment of the present application, and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (3)
1. An intelligent poster generation method suitable for an e-commerce platform is characterized in that:
the intelligent poster generation method suitable for the e-commerce platform comprises the following steps:
Acquiring a shop range selected by a user;
generating a promoted commodity list according to historical order data of shops in the shop range;
Acquiring corresponding commodity pictures and commodity promotion price data according to the promotion commodity list;
Acquiring a poster template selected by a user;
Filling the commodity pictures and commodity promotion price data to the appointed position of the poster template according to the ordering of the promotion commodity list;
the step of obtaining the shop range selected by the user comprises the following steps:
automatically selecting the shop range according to the corresponding relation between the account of the user and the shop;
the step of obtaining the corresponding commodity picture and commodity promotion price data according to the promotion commodity list further comprises the following steps:
Acquiring historical order data of stores in the store range;
analyzing order feature data from the historical order data;
Inputting the order feature data into a purchase intent prediction model to cause the purchase intent prediction model to output purchase intent prediction data;
generating a sales promotion commodity sub-table of the store according to the purchase intention prediction data;
summarizing sales promotion commodity sub-tables of all shops in the shop range to form a sales promotion commodity list;
The step of analyzing the order characteristic data from the historical order data comprises the following steps:
Setting an observation period of the historical order data;
collecting the historical order data of the store in the observation period according to the total order number, the total sum, the order frequency value and the frequency value of each commodity;
the total number of orders, the summarized amount, the order frequency value and the frequency value of each collected commodity are correspondingly numbered to the commodity, and then a data matrix is constructed as order characteristic data;
Wherein the commodity number is the SKU value of the commodity; the total number of orders is total order data related to the commodity in the observation period; the total amount is the sum of the order amounts of the commodity in the observation period; the order frequency value is an average value of the total number of orders relative to the observation period, and the frequency value is a ratio of the total amount to the order frequency value;
the purchase intention prediction data is a matrix which is the same as the data matrix of the order feature data;
The generation of the sales promotion commodity sub-table of the store according to the purchase intention prediction data comprises the following steps:
The data in the matrix of the purchase intention prediction data are used as the basis of row ordering according to the frequency value, so that the data in the matrix are sequentially filled into form data, and the form data are sales promotion commodity sub-tables;
the step of summarizing the sales promotion commodity sub-tables of all shops in the shop range to form the sales promotion commodity list comprises the following steps:
Summing the total number of orders and the sum of the amounts in each sales promotion commodity sub-table according to the SKU value of the commodity, and then calculating the order frequency value and the frequency value after corresponding sum data;
According to the frequency value, the order of the rows in the sales promotion commodity list is arranged according to the row ordering;
The step of filling the commodity pictures and commodity promotion price data to the formulated positions of the poster templates according to the ordering of the promotion commodity list comprises the following steps:
setting a plurality of commodity filling positions for each poster template;
Setting a filling sequence number for each commodity filling position;
Filling and matching the goods with the front order of the sales promotion goods list with filling positions with larger filling serial numbers in the poster template;
And according to the matching relation between the commodity and the filling position, invoking commodity pictures and commodity promotion price data of the commodity to fill the commodity pictures and commodity promotion price data into the filling position of the poster template.
2. An intelligent poster generation device suitable for electronic commerce platform, its characterized in that:
The intelligent poster generating device suitable for the e-commerce platform comprises: a memory for storing a computer program; a processor for implementing the intelligent poster generation method applicable to an e-commerce platform as claimed in claim 1 when executing said computer program.
3. A computer client storage medium, characterized by:
The computer readable storage medium stores a computer program which, when executed by a processor, implements the intelligent poster generation method applicable to an e-commerce platform as claimed in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110762736.2A CN113554457B (en) | 2021-07-04 | 2021-07-04 | Intelligent poster generation method and device suitable for e-commerce platform and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110762736.2A CN113554457B (en) | 2021-07-04 | 2021-07-04 | Intelligent poster generation method and device suitable for e-commerce platform and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113554457A CN113554457A (en) | 2021-10-26 |
| CN113554457B true CN113554457B (en) | 2024-09-24 |
Family
ID=78131353
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110762736.2A Active CN113554457B (en) | 2021-07-04 | 2021-07-04 | Intelligent poster generation method and device suitable for e-commerce platform and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113554457B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114298781A (en) * | 2021-11-25 | 2022-04-08 | 珠海格力电器股份有限公司 | Method, device, electronic device and storage medium for generating posters for online shopping malls |
| CN117473972A (en) * | 2023-12-12 | 2024-01-30 | 深圳市移卡科技有限公司 | Method and device for generating poster |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840730A (en) * | 2017-11-29 | 2019-06-04 | 北京京东尚科信息技术有限公司 | Method and device for data prediction |
| CN110706311A (en) * | 2019-09-18 | 2020-01-17 | 可爱可亲(广州)高新科技有限公司 | Intelligent poster generation method and system based on chain store |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5982310B2 (en) * | 2013-03-21 | 2016-08-31 | 株式会社エヌ・ティ・ティ・データ | Sales promotion system, server device, sales promotion method, and program |
| CN108279886A (en) * | 2017-01-05 | 2018-07-13 | 长沙海商网络技术有限公司 | A kind of logical+WAP mall systems in fast shop |
| CN107545460B (en) * | 2017-07-25 | 2020-12-18 | 广州智选网络科技有限公司 | Digital color page promotion management and analysis method, storage device and mobile terminal |
| CN109034950A (en) * | 2018-06-29 | 2018-12-18 | 深圳春沐源控股有限公司 | Poster generation method and poster generate system |
| CN109801102A (en) * | 2019-01-10 | 2019-05-24 | 哈步数据科技(上海)有限公司 | A kind of method and system promoting selection |
| KR102261343B1 (en) * | 2020-11-11 | 2021-06-04 | 이성구 | Method for Shopping Advertisement Printed Matter Using Integrated Services Platform |
-
2021
- 2021-07-04 CN CN202110762736.2A patent/CN113554457B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840730A (en) * | 2017-11-29 | 2019-06-04 | 北京京东尚科信息技术有限公司 | Method and device for data prediction |
| CN110706311A (en) * | 2019-09-18 | 2020-01-17 | 可爱可亲(广州)高新科技有限公司 | Intelligent poster generation method and system based on chain store |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113554457A (en) | 2021-10-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108694210A (en) | Template generation method and device | |
| US9881407B1 (en) | Systems, methods, and devices for integrated product and electronic image fulfillment | |
| US11205245B2 (en) | Method of improving visual recognition of an item and item display system | |
| CN113554457B (en) | Intelligent poster generation method and device suitable for e-commerce platform and storage medium | |
| JP2018538636A (en) | Method, system and apparatus for providing product information | |
| Irion et al. | A hierarchical decomposition approach to retail shelf space management and assortment decisions | |
| JP2008165505A (en) | Merchandise purchase system | |
| CN113643075B (en) | Intelligent poster generation method, device and storage medium based on machine learning | |
| JP2013025386A (en) | Merchandise information provision device, merchandise information provision method and program | |
| US20130262263A1 (en) | Coordination list-providing system and related method | |
| CN111352624A (en) | Interface display method, information processing method and device | |
| JP2000200260A (en) | Product sales forecast system | |
| CN110851568A (en) | Commodity information processing method, terminal device and computer-readable storage medium | |
| CN117196758A (en) | Screening method, equipment and medium for commodity before being put on shelf | |
| KR102371090B1 (en) | Method for providing advertisement using distance relationship graph based on simple receipt service | |
| CN115937341A (en) | AI technology-based e-commerce report generation system and generation method thereof | |
| Ishak et al. | Do convenience, time-saving and trust determine consumers online shopping behaviour? | |
| KR20160110814A (en) | System, method and computer program for management of food delivery | |
| CN112308671A (en) | Commodity package generation method, system and storage medium | |
| CN112685441A (en) | Metadata-based content asset management method and system | |
| CN111915405A (en) | Order management method and system | |
| KR101002584B1 (en) | How to make stickers for product containers | |
| WO2023276051A1 (en) | Sales information processing device, sales information processing method, and program | |
| KR20190016405A (en) | Customer-Recognized-Image-based Order Commerce Method and Apparatus thereof | |
| US20140122290A1 (en) | Methods & apparatus to select optimum promotional giveaway or gift |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |