CN111738786A - Method, system, apparatus and readable storage medium for building a combination of commodities - Google Patents
Method, system, apparatus and readable storage medium for building a combination of commodities Download PDFInfo
- Publication number
- CN111738786A CN111738786A CN201910335099.3A CN201910335099A CN111738786A CN 111738786 A CN111738786 A CN 111738786A CN 201910335099 A CN201910335099 A CN 201910335099A CN 111738786 A CN111738786 A CN 111738786A
- Authority
- CN
- China
- Prior art keywords
- commodity
- candidate
- strength
- album
- commodities
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 230000006870 function Effects 0.000 claims description 23
- 238000005457 optimization Methods 0.000 claims description 21
- 238000005065 mining Methods 0.000 claims description 16
- 230000002349 favourable effect Effects 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000001737 promoting effect Effects 0.000 abstract description 5
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000007405 data analysis Methods 0.000 abstract 2
- 238000013507 mapping Methods 0.000 description 11
- 230000008901 benefit Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000006399 behavior Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 239000008267 milk Substances 0.000 description 3
- 210000004080 milk Anatomy 0.000 description 3
- 235000013336 milk Nutrition 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 239000002304 perfume Substances 0.000 description 2
- 239000000344 soap Substances 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000003471 anti-radiation Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 235000013312 flour Nutrition 0.000 description 1
- 235000015219 food category Nutrition 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
- 238000005201 scrubbing Methods 0.000 description 1
- 238000002922 simulated annealing Methods 0.000 description 1
- 235000011888 snacks Nutrition 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
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]
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method, a system, a device and a readable storage medium for constructing a commodity combination. The method for constructing the commodity combination comprises the following steps: according to order data, acquiring a plurality of item sets, wherein each item set comprises a plurality of commodity items, each commodity item is an N-level commodity item, commodities contained in at least two commodity items appear in the same order, and N is an integer greater than or equal to 1; for each category set, acquiring candidate commodities from a plurality of commodities contained in the category set, and forming a candidate commodity set, wherein the candidate commodities meet the current discount and/or promotion requirements; and acquiring a commodity combination with the preference strength greater than or equal to a preset preference strength as a combined preference album aiming at each candidate commodity set. According to the invention, big data analysis is applied to order data analysis, so that a combined preferential album conforming to preset preferential strength is obtained and provided for a consumer, thereby being beneficial to improving user experience and promoting the purchasing behavior of the consumer.
Description
Technical Field
The invention relates to the technical field of internet, in particular to a method, a system, a device and a readable storage medium for constructing a commodity combination.
Background
The combination preferential sale refers to that associated commodities are combined together, and the commodities are sold in an album form. For example, in a mother-and-infant-oriented consumption scene, associated commodities such as milk powder, milk bottles, infant tableware, mother-and-infant antiradiation clothes, early education toys and the like can be displayed together, and additional multi-purchase preferential discount is given. The combination offers benefit both consumers and merchants with the advantages of the following table:
table 1
Referring to fig. 1, fig. 1 illustrates preferential discounts in an example of a combination sale. Wherein, the block 100-300 represents that there are three commodities A, B and C, each selling price is 100 yuan, and facing to a consumption scene; block 400 is a total promotion (full reduction) with a use condition of at least 300 dollars in purchase amount; block 500 is a shop first coupon, using the conditions of the shop first's goods (A and B) and having a monetary value of at least 200 Yuan; block 600 is a category II coupon, used if category II items (B and C) are available and the dollar value is at least 105 dollars.
If the consumer purchases three items A, B and C separately (three orders, 100 dollars per order), the consumer pays a total of 300 dollars because all of the above promotions and coupon usage conditions are not met; if a combination purchase is used, i.e., correct use of the total promotion, the store A coupon and the Category II coupon, the calculation in block 600 is obtained and the consumer pays only 90 dollars (210 dollars savings) to buy the three items.
In the existing purchasing scene, consumers need to find the most suitable for the consumption scene and construct the most favorable commodity combination by themselves. However, manually setting the sales pattern of the combination of merchandise offer album has the following major disadvantages:
1) and shopping consumption scenes are difficult to identify: shopping consumption scenes per se, commodities, consumers and markets related to the scenes dynamically and greatly change every day;
2) and preferential commodities facing to scenes are difficult to select: the commodity preferential activities of the e-commerce platform dynamically change every day, and the mass of commodities cause that commodities which are oriented to shopping consumption scenes and have preferential strength are difficult to select;
3) and the commodities in the combined offer album are difficult to calculate: the number of the preferential activities covering the commodities is large, the preferential activities are mutually overlapped, and the price of the preferential commodities is difficult to calculate.
Disclosure of Invention
In view of the above, embodiments of the present invention provide a method, system, apparatus, and computer-readable storage medium for constructing a combination of goods according to current offers and/or promotions, so as to solve the problems in the prior art.
In a first aspect, an embodiment of the present invention provides a method for constructing a commodity combination, including:
according to order data, acquiring a plurality of item sets, wherein each item set comprises a plurality of commodity items, each commodity item is an N-level commodity item, commodities contained in at least two commodity items appear in the same order, and N is an integer greater than or equal to 1;
for each category set, acquiring candidate commodities from a plurality of commodities contained in the category set, and forming a candidate commodity set, wherein the candidate commodities meet the current discount and/or promotion requirements; and acquiring a commodity combination with the preference strength greater than or equal to a preset preference strength as a combined preference album aiming at each candidate commodity set.
In some embodiments, further comprising: and releasing the combined preferential album.
In some embodiments, the combined offer album is released as a hash combination and/or recommendation combination.
In some embodiments, the obtaining a plurality of sets of categories according to the order data includes:
acquiring N-level commodity classes to which each commodity belongs, wherein each order comprises the N-level commodity classes;
constructing a undirected weight graph according to the N-level commodity class to which each commodity belongs, wherein each order comprises the commodities;
obtaining a plurality of first subgraphs from the undirected weight graph, wherein the first subgraphs are subgraphs with communication rate and/or weight larger than or equal to a set threshold; and
and obtaining the plurality of item sets according to the plurality of first subgraphs.
In some embodiments, the first sub-graph is a full graph.
In some embodiments, further comprising: and optimizing the candidate commodity set, and acquiring a commodity combination reaching preset discount strength as a combined discount album for each candidate commodity set:
and acquiring a commodity combination with the preference strength greater than or equal to the preset preference strength as a combined preference album aiming at each optimized candidate commodity set.
In some embodiments, the candidate combination of items is optimized based on an indicator of at least one of a degree of offer, a degree of goodness, a degree of purchase, and a degree of novelty.
In some embodiments, said optimizing said candidate combination of items according to an indicator of at least one of offer strength, goodness, purchase strength, and novelty strength further comprises:
setting respective weights of the preferential strength, the favorable evaluation strength, the purchasing strength and the new product strength;
calculating the value degree of each commodity in the candidate commodity combination according to the discount degree, the favorable evaluation degree, the purchasing degree, the new product degree and respective weights; and
and eliminating the commodities with the value degree equal to or larger than a second set threshold value in the candidate commodity combination.
In some embodiments, the obtaining a combination of commodities with a preset offer strength or greater as a combined offer album includes:
establishing a target function taking the preset preferential strength as a target and taking the current preferential and/or promotion requirement and budget limitation as constraint conditions; and
and solving the objective function to obtain the combined preferential album.
In a second aspect, an embodiment of the present invention provides a system for constructing a commodity combination, including:
the system comprises a scene mining module, a data processing module and a data processing module, wherein the scene mining module is used for acquiring a plurality of commodity class sets according to order data, each commodity class set comprises a plurality of commodity classes, each commodity class belongs to N-level commodity classes, commodities contained in at least two commodity classes appear in the same order, and N is greater than or equal to 1;
the commodity selection module is used for acquiring candidate commodities from a plurality of commodities contained in each commodity class set and forming a candidate commodity set, wherein the candidate commodities meet the current discount and/or promotion requirements; and
and the album optimization module is used for acquiring a commodity combination with the preference strength greater than or equal to the preset preference strength as a combined preference album for each candidate commodity set.
In some embodiments, the scene mining module comprises:
the drawing expression unit is used for acquiring the N-level commodity class to which each commodity belongs and contained in each order, and constructing a undirected weight drawing according to the N-level commodity class to which each commodity belongs and contained in each order;
the subgraph acquisition unit is used for obtaining a plurality of first subgraphs from the undirected weight graph, wherein the first subgraph is the subgraph of which the communication rate and/or the weight are greater than or equal to a set threshold; and
and the data output unit is used for obtaining the plurality of item sets according to the plurality of first subgraphs.
In some embodiments, the first sub-graph is a full graph.
In some embodiments, the merchandise selection module comprises:
the information extraction unit is used for obtaining a plurality of candidate commodity sets according to the plurality of category sets;
a commodity optimization unit for optimizing the candidate commodity set;
and the data generating unit is used for establishing a data unit according to the optimized candidate commodity set.
In some embodiments, the album optimization module comprises:
the model establishing unit is used for establishing a target function which takes the preset preferential strength as a target and takes the current preferential, the promotion requirement and the budget limit as constraint conditions;
and the model solving unit is used for solving the objective function to obtain the combined preferential album.
In a third aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions, which when executed implement any one of the methods described above.
In a fourth aspect, an embodiment of the present invention provides an apparatus, including:
a memory for storing computer instructions;
a processor coupled to the memory, the processor configured to perform a method implementing any of the above based on computer instructions stored by the memory.
The embodiment of the invention has the following advantages or beneficial effects: and a combined preferential album conforming to the preset preferential strength is constructed according to the big data statistical analysis of the order data and provided for the consumer, so that the user experience is improved, and the purchasing behavior of the consumer is promoted.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing embodiments of the present invention with reference to the following drawings, in which:
FIG. 1 illustrates discount offers in a combination sales example;
FIG. 2 illustrates a flow chart of a method of constructing a portfolio of goods of an embodiment of the present invention;
FIG. 3 illustrates a block diagram of a two-level commodity class;
fig. 4 shows a detailed flowchart of step S201 in fig. 2;
FIG. 5 illustrates a undirected weight graph derived from order data;
FIG. 6 is a block diagram illustrating a system for building a portfolio of goods in accordance with an embodiment of the present invention;
fig. 7 is a block diagram showing an apparatus for constructing a commodity combination according to an embodiment of the present invention.
Detailed Description
The present invention will be described below based on examples, but the present invention is not limited to only these examples. In the following detailed description of the present invention, certain specific details are set forth. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details. Well-known methods, procedures, and procedures have not been described in detail so as not to obscure the present invention. The figures are not necessarily drawn to scale.
[ term interpretation ]
Complete graph: a full graph means that any two vertices in the graph have an edge connected.
Maximum complete graph: it means that for a given graph, the subgraph composed of a part of the vertices and their neighbors between the vertices in the graph is the complete graph and contains the maximum number of weights.
FIG. 2 shows a flow chart of a method of constructing a portfolio of goods of an embodiment of the present invention. The method specifically comprises the following steps.
In step S201, a plurality of item sets are acquired based on order data.
Order data is data that records consumer purchases. For example, when the first consumer purchases soap and perfume at one time, the corresponding order data records the user identifier of the first consumer, the commodity identifier of the soap, the price, the quantity, the commodity identifier of the perfume, the price, the quantity, the purchase time and other information.
The categories of goods determine what goods make up the groups and categories. The classification of the categories of merchandise may be based on the consumer's perception of the product, may be based on the attributes of the merchandise itself, or both. An understanding of the categories of merchandise can be seen in the tree structure of fig. 3. For simplicity, FIG. 3 shows only two levels of merchandise items, with 1 representing a first level merchandise item, 2-4 representing a second level merchandise item belonging to the first level merchandise item, 5-6 representing an item identifier (e.g., SKU) belonging to merchandise item 2, and 7 representing an item identifier belonging to merchandise item 4. Meanwhile, since the child node of the tree structure only has one parent node, one commodity only has one N-level commodity category, and N is an integer greater than or equal to 1.
In this step, according to the commodity identification of the order data, the corresponding N-level commodity category can be determined, and the N-level commodity category of the commodity appearing in the same order is subjected to big data statistical analysis to determine one or more category sets. Wherein, a plurality of commodity classes contained in each class set are N-grade commodity classes, and commodities contained in at least two commodity classes appear in the same order.
In step S202, for each category set, candidate commodities are obtained from the commodities included in the category set, and a candidate commodity set is formed, where the candidate commodities meet the current offer and/or promotion requirement.
In this step, according to each item set, a plurality of item identifiers contained in the item set are obtained, and item identifiers meeting the current discount and/or promotion requirements are obtained from the plurality of item identifiers to form a candidate item set. It should be noted that the commodity identification included in one commodity category refers to not only the commodity identification directly included in the commodity category, but also the commodity identification indirectly included in the commodity category, that is, the commodity identification included in the commodity category from the next level to the next K level, where K is a positive integer.
In step S203, for each candidate commodity set, a commodity combination greater than or equal to a preset offer strength is acquired as a combined offer album.
In this embodiment, at least one candidate commodity set can be obtained for each commodity category, and in this step, the commodities in the candidate commodity set are continuously screened according to the preset offer strength to obtain a combined offer album. The combined preferential album is a commodity album which is determined according to the purchasing behavior of the consumer and accords with the preset preferential strength, and the combined preferential album is provided for the consumer, so that the user experience is improved, and the purchasing behavior of the consumer is promoted.
Fig. 4 shows a detailed flowchart of step S201 in fig. 2. The method specifically comprises the following steps.
In step S2011, the N-level commodity class to which each commodity included in each order belongs is acquired
In step S2012, a undirected weight graph is constructed from the N-class commodity categories to which each commodity belongs, which are included in each order.
In step S2013, a plurality of first subgraphs are obtained according to the undirected weight graph, where the first subgraph is a subgraph in which the communication rate and/or the weight is greater than or equal to the set threshold.
In step S2014, a plurality of item sets are obtained according to the plurality of first subgraphs.
The present embodiment is explained below with reference to fig. 5. FIG. 5 is a undirected weight graph of a class of tertiary commodities constructed from order data. Wherein, C1-C12 all belong to the three-level commodity class obtained according to the order data. The connecting line between the two commodity categories indicates that the commodities belonging to the two commodity categories respectively appear in the same order, and the number on the connecting line indicates the weight, namely the number of times that the two commodity categories correspondingly appear in the same order. For the undirected weight graph, multiple subgraphs can be obtained according to set conditions. For example, based on fig. 5, each weight in the subgraph is required to be greater than or equal to 7, thereby obtaining a subgraph 50, where the subgraph 50 includes commodity classes C1-C5, or a connecting line is required between each commodity class in the subgraph, thereby obtaining a subgraph 60, where the subgraph 60 includes commodity classes C6-C9. Subgraph 60 is a fully connected subgraph, also called a full graph. For another example, if each weight in the subgraph is required to be greater than or equal to 5 and there is a connecting line between each commodity class, then the subgraph 60 including the commodity classes C6-C9 is obtained. Optionally, for the above undirected weight graph, the weight is the ratio of the number of times two categories of goods appear in the same order and the total amount of order data, so that the weight is more representative of the relative probability of the categories of goods appearing in the same order.
In the embodiment, the sub-images are obtained according to the graphs after the order data are expressed through the images, so that the class set meeting the preset conditions is obtained.
In some embodiments, the method of constructing a combination of commodities further comprises optimizing the set of candidate commodities. As described above, if the candidate product set is a product that meets the current benefit and/or promotion requirement, the candidate product set may be several tens of thousands to several hundreds of thousands, and the number of the candidate product set is too large, so that some of the candidate products can be screened in advance according to some set indexes. And then, acquiring commodity combinations with the preference strength greater than or equal to the preset preference strength as combined preference albums for each optimized candidate commodity set.
FIG. 6 is a block diagram of a system 600 for constructing a portfolio of goods in accordance with an embodiment of the present invention. As shown in the figure, the system 600 interacts with the combined album application 700, the combined album application 700 sends a task request, and after receiving the task request, the system 600 sequentially calls the scene mining module 601, the commodity selection module 602, and the album optimization module 603 to obtain a combined special offer album and returns the combined special offer album to the combined album application 700. In addition, the scene mining module 601, the commodity selection module 602, and the album optimization module 603 communicate with the storage system 800 to acquire required data from the storage system 800.
The scene mining module 601 is configured to obtain a plurality of category sets according to order data, where the category sets include a plurality of commodity categories, the commodity categories all belong to N-level commodity categories, and commodities included in at least two commodity categories appear in the same order, and N is greater than or equal to 1.
The item selection module 602 and the album optimization module 603 are invoked in a loop for each item class of merchandise. The item selection module 602 is configured to, for each item set, obtain candidate items from a plurality of items included in the item set, and form a candidate item set, where the candidate items meet current offer and/or promotion requirements, thereby establishing an item-promotion mapping. The album optimizing module 603 is configured to apply an intelligent technology to each candidate commodity set, and acquire a commodity combination with a preference strength greater than or equal to a preset preference strength as a combined preference album.
In the system for constructing commodity combinations of this embodiment, a commodity combination is constructed through a scene mining model, and then a commodity selection module 602 and an album optimization module 603 are circularly called to realize that, for each commodity set, a candidate commodity combination is obtained first and then the candidate commodity combination is optimized to obtain a combination preferential album. The combined preferential album is a commodity album which is determined according to the purchasing behavior of the consumer and accords with the preset preferential strength, and the combined preferential album is provided for the consumer, so that the user experience is improved, and the purchasing behavior of the consumer is promoted.
In the present system, the portfolio application 700 first needs to define a category range: from which large categories of merchandise (commodity secondary category, or commodity primary category, or how many thousands of commodity tertiary categories, or all categories of merchandise) a composite offer album for the scene is generated, for example:
selecting washing liquid types, scrubbing tool types, kitchen tool types, cleaning toilets and other secondary types to generate kitchen and toilet cleaning combination preferential albums;
and selecting secondary categories such as snack categories, rice and flour food categories, oil categories, egg and milk categories and the like to generate the family weekend improvement life combination preferential albums.
Secondly, it is also necessary to define the constraints of the portfolio album, such as:
maximum number of pieces of the same item in a portfolio album;
or how many secondary categories (or other categories) of merchandise may be included in a portfolio album at most.
After the tasks are completed, the defined commodity classes and the constraint conditions are sent to a system for constructing commodity combinations.
The scene mining module 601 inputs the commodity category and the constraint condition input by the album composition application 700, and outputs a set of the commodity categories. The goal of the scene mining module 601 is to mine the consumption scenes in the commodity categories specified by the combo album utility 700. Since a specific consumption scenario (e.g., autumn mountain climbing equipment, etc.) is often associated with several specific commodity tertiary categories (or quaternary categories), and since a commodity secondary category usually includes thousands of commodity tertiary categories, the specific task of the scenario mining module 601 is to find all associated commodity category sets in the set commodity categories.
In some embodiments, intelligent mining module 601 includes a graph expression unit 6011, a subgraph acquisition unit 6012, and a data output unit 6013
And acquiring N-level commodity classes to which each commodity belongs, wherein each order comprises the N-level commodity classes, and constructing a undirected weight graph according to the N-level commodity classes to which each commodity belongs, wherein each order comprises the N-level commodity classes. I.e. expressing the order data using undirected weight graph. The map expression unit 6011 comprises the following steps:
inquiring an existing historical order commodity user information table in the E-commerce platform storage system;
extracting all orders related to the defined categories of goods;
the undirected weight graph represents the orders of a plurality of commodity classes according to all the order information obtained by query, and the vertex represents the set commodity class (such as a third-level commodity class or a fourth-level commodity class). If there is a consumer who has purchased a tertiary item class of merchandise associated with two vertices in a single day's order, then there is an edge between the two vertices. The weight of an edge is the number of orders that the two vertices are consumed to purchase in common.
And obtaining a plurality of first subgraphs from the undirected weight graph, wherein the first subgraphs are subgraphs of which the communication rate and/or the weight are larger than or equal to a set threshold value. The first sub-graph obtained in this way has a higher probability that the commodities included in the commodity category are purchased together, so that a first sub-graph is taken as a consumption scene. This unit iteratively performs the following tasks:
1. using an artificial intelligence algorithm to find a first sub-graph meeting a set condition, and moving the found first sub-graph out of an original undirected weight graph (see fig. 5 and corresponding description in particular);
2. and storing the item set consisting of the commodity items in the first sub-graph into a data table.
3. Loop 1-2 (stop condition is step 1 returns to empty set).
And outputting a plurality of item sets according to the plurality of first subgraphs. Namely, a group of associated commodity classes corresponding to each consumption scene is recorded, as shown in the following table (in the table, C1-C14 refer to the commodity three-class with numbers of C1-C14 respectively):
table 2
| Scene No.1 | C1,C2,C3,C4,C5 |
| Scene No.2 | C6,C7,C8,C9 |
| Scene No.3 | C10,C11,C12 |
| Scene No.4 | C13,C14 |
The input of the goods selection module 602 is a set of categories output by the data output unit 6013. The item class set characterizes a consumption scene of the associated commodity under the corresponding commodity class, for example (C1, C2, C3, C4, C5). Since a given commodity class (e.g., tertiary or quaternary) typically includes more than tens of thousands of commodities, the module is tasked with selecting the most valuable set of candidate commodities from the commodities to which the given commodity class belongs.
In some embodiments, the commodity selection module 602 includes an information extraction unit 6021, a commodity optimization unit 6022, and a data generation unit 6023.
Inquiring information of each commodity in the associated item set from the e-commerce platform storage system, specifically comprising the following steps:
extracting from the promotion campaign table and coupon campaign batch table, the valid promotions and coupons to which the item relates;
extracting the number and rate of good comments related to the commodities from the commodity comment form;
extracting the transaction amount of the commodity from the order form;
information on whether or not the product belongs to a new product is extracted from the other table.
The unit optimizes all the commodities in the candidate commodity set according to the set index.
First, the value degree calculation of each commodity is performed according to formula (1) and sorted in descending order according to the value degree of each commodity:
weight ofOffersPreferential strength + weightGood commentGoodness + weightPurchasingPurchase strength + weightNew productNew force formula (1)
Wherein:
benefit degree: to retrieve the item with the promotion (which may be calculated as the item's discount amount, from the largest promotion or coupon, divided by the item's bid);
good scoring power: for extracting the goods with good comments (which can be calculated as the total number of good comments of the goods divided by the average number of comments in the three classes of goods);
purchase strength: used for extracting commodities with hot sales (the commodity purchase quantity can be calculated);
new product strength: for extracting new goods (whether new goods are available or not or the date of sale can be calculated);
weight ofOffersWeight ofGood commentWeight ofPurchasingAnd weightNew productIs a weight value set correspondingly;
other dimensions of information about the item may also be included by equation (1), such as the store popularity to which the item belongs. The candidate commodity set for the scene can be entered after sorting (set threshold value) before the certain position in front.
The unit stores the goods, tertiary categories, promotions, coupons, and their correspondences within the candidate set as model data:
a) a set of three-level categories of merchandise within the scene (noted as C, e.g., C1, C2, C3, C4, C5), the number of different three-level categories of merchandise within all the scene is noted as | C |;
b) a candidate commodity set (noted as G), namely a set of all candidate commodities contained in a commodity three-level class set (namely C) in the scene;
c) a set of promotional ways (noted as P), i.e., a set of promotional ways that a product (i.e., G) within the scene can use;
d) a coupon set (noted as Q), i.e., a set of coupons that can be used by a good (i.e., G) within the scene;
e) due to different shop coupons, the category coupon and the platform coupon can be used in a superposition mode (at most three coupons are superposed), and the one-to-one mapping relation (noted as Map) of each commodity ID and the commodity tertiary category to which the commodity ID belongsG→C)；
f) One-to-many mapping (annotated Map) for each item ID and its candidate available promotional way IDsG→P)；
g) One-to-many mapping for available promotional offers to the goods to which they can be applied (annotated MapP→G)；
h) One-to-many mapping for each coupon ID and its superimposable use of coupon IDs(annotated MapQ→Q)；
i) One-to-many mapping (annotated as Mop) that can use coupons for each item and its candidatesG→Q)。
For example, for a scene-related set of three-level merchandise categories (C1, C2, C3, C4, C5), the unit stores information as follows:
table 3
The task of the album optimization module 603 is to select a number of items from the set of candidate items for a given scene, with constraints satisfied, to produce the best album of scene items.
The inputs to the module include the following:
output by the scene mining module 601: a set of items (for a given consumption scenario);
the set of candidate items and the model data output by the item selection module 602.
In some embodiments, the module includes a model building unit 6031 and a model solving unit 6032.
The problem of how to generate the preferential commodity album facing the scene is defined as a problem of multi-target mathematical combination solution. It comprises the following two steps.
maximization: weight ofOffersOffer target value + weightSceneScene target value + weightBudget targetsBudget target value
Constraint conditions are as follows: the number of the commodities in the album is less than or equal to that of the commodities in the albumMaximum commodity quantity limit
The number of the commodities in the album is more than or equal to that of the commodities in the albumMinimum commodity quantity limit valueFormula (2)
Wherein:
preferential target values: through the calculation of the total price promotion mode and the superposition discount of the discount coupons, the larger the ratio of the settlement amount of each commodity in the album after discount to the original price of the commodity is, the better the ratio is (namely, the higher the discount strength is, the better the ratio is);
scene target value: because each commodity in the album has the commodity class which is subordinate to the commodity, the ratio of the number of different commodity classes in the album to the number of different commodity classes in the commodity class set of the specified scene is better;
budget target value: each album has a budget spending amount, denoted B, such as 200 or 500 dollars (this amount typically slightly exceeds the full reduction amount for a total promotion) that is preset by the marketing department. The smaller the difference between the settlement amount after all the commodities in the album and the amount is, the better (or the larger the reciprocal of the value is, the better);
weight ofOffersWeight ofSceneAnd weight ofBudget targetsAre weight values corresponding to the three target values;
album merchandiseMaximum commodity quantity limitIs a limit value of the maximum number of different commodities permitted in the set album (for example, at the mobile terminal of the mobile phone, the commodity album can contain four commodities at most);
album merchandiseMinimum commodity quantity limit valueIs a limit for the minimum number of different items permitted in the album (e.g., at the mobile end of the phone, the album of items may include at least two items).
The solution to the problem (noted as S) is an album containing several different items. Albums may contain different items (even different pieces). The total number of different albums (i.e., solutions) that theoretically exist over the search space of the different albums can be calculated by the following formula:
in the formula (3), | G | represents the total number of commodities included in the commodity set. As can be seen from equation (3), when there are hundreds or thousands of candidate commodities, the search space for the solution is large (the problem computation complexity is NP-complete).
1. calculating the offer target value (i.e. the offer amount of the album) for a given solution:
for any given album (i.e., comments such as S), calculating the preferential amount of the items within the album involves the following:
a) for the commodity G on solutioni∈ S, according to the MapG→PThe merchandise GiThere may be multiple total reduction promotion modes that may be used as candidates, so selecting different total reduction promotion modes for the items in the album results in different preferential amounts;
b) coupons are divided into three categories: stores, limitations, and full platforms may be overlaid. The e-commerce settlement policy allows only one category of coupon and one merchandise can be enjoyed only once. According to the MapG→QThere may be many coupons available for each item, so selecting different levels of coupons for items in the album also results in different coupon amounts;
c) calculating the benefit of the item therefore involves the problem of choosing a sales promotion and coupon for each item on the solution, thereby ensuring that the consumer receives the maximum benefit amount. This maximum offer amount is the offer amount for the album.
Thus, the preferential amount of the items on the album is a mathematical portfolio optimization problem. Since there are only four items in an album at most, each item generally involves four different total sales promotion methods at most, and the coupons at three levels are divided into three categories. The commodity technology calculates the maximum preferential strength by using an enumeration method. For any given album, the preferential target value is calculated by the following formula (enumerate the total number):
2. calculating a scene target value of the solution:
for any given album, the scene target value is calculated by the following formula:
3. calculating the budget target value of the album:
for any given album, the budget target value is calculated by the following formula:
for any given album, after the preferential target value, the scene target value and the budget target value are calculated (formulas 4 to 6), the objective function value of the whole album is calculated by formula (2).
The technology uses an intelligent technology which is designed for customizing innovation for the commodity optimization problem of the intelligent album, and the album with the optimal objective function value is searched in a search space. The unit comprises the following three steps:
1. constructing an initial solution:
construct an album that starts empty (i.e., the initial solution S)0) I.e., no merchandise is included within the album. A random initial solution is then constructed cyclically from the following steps:
a) randomly selecting a promotion mode Pi∈ P according to the mapping MapP→GRandomly selecting one available promotion mode PiAnd adding the item to the original album S0The above step (1);
b) check album S after adding the item0All goods in the upper partIf the sum of the original price amount exceeds the album budget target B and the hard constraint condition, taking the current commodity in the album as an initial random solution, otherwise, continuously adding a usable promotion mode PiIs on album S0The above step (1);
c) and (c) checking whether the sum of the original price amounts of all commodities in the album exceeds an album budget target B and a hard constraint condition, if so, taking the commodities in the album as an initial random solution, and otherwise, repeating the step a).
After the loop is stopped, the generated commodity in the album is the initial solution.
2. Search for the best solution (i.e., best combination offer album):
the initial solution is a point randomly chosen from the solution space. The optimization process is to take the initial solution as an intermediate solution, and iterate and traverse a part of solution space from the intermediate solution according to a certain rule in each iteration to try to find a better solution:
1) and transforming the intermediate solution, and changing the element values on the partial intermediate solution according to the following three ways:
a) and (4) replacing commodities: randomly selecting and deleting a commodity on the current solution; according to the mapping relationship (Map) between the commodity ID and the candidate sales promotion mode IDG→P) Randomly selecting a promotion mode; according to the mapping relationship (Map) between randomly selected promotion mode and available commodityP→G) Randomly selecting a new commodity and adding the new commodity on the current solution;
b) and (4) deleting the commodity: deleting one commodity randomly as long as more than two commodities exist in the current solution;
c) adding commodities: randomly selecting one commodity on the current solution as long as the current solution has more than three commodities; according to the mapping relationship (Map) between the commodity ID and the candidate sales promotion mode IDG→P) Randomly selecting a promotion mode; mapping (Map) of randomly selected promotion modes to available goodsP→G) Randomly selecting a new commodity and adding the new commodity on the current solution;
the above three transformations change the current solution into a new solution, called the interim solution.
2) The objective function value of the temporary intermediate solution is calculated using equation (2).
3) If the objective function value of the temporary intermediate solution is better than the objective function value of the current solution, the temporary intermediate solution will be accepted. If the objective function value of the temporary intermediate solution is worse than the objective function value of the original current solution, the acceptance probability of this worse solution is calculated by the simulated annealing formula.
4) Step 1 to step 3 are performed iteratively. The best solution found throughout the search is recorded. The exit conditions are set as: after a certain number of iterations (controllable parameters), the best solution is not improved, indicating that the solution has converged.
3. Output solution (i.e. best combination special offer album)
Because the search space is huge, the optimal solution of the combined optimization problem cannot be unique, and the difference of the objective function values between the sub-optimal solutions is small. Therefore, aiming at one scene, different random seeds are given, and the task flow (constructing an initial solution, searching an optimal solution and outputting the solution) of the artificial intelligence optimization unit can be operated repeatedly for many times, so that dozens of best solutions can be found. All the combination offer albums can be saved and returned to the caller in the form of a list together with the corresponding scenes, for example for the scenes (set of associated merchandise categories: C1, C2, C3, C4, C5), see the following table:
table 4
To sum up, the system for constructing a commodity combination first calls the commodity selection module 602 and then calls the album optimization module 603 for each scene output by the scene mining module, and finally generates a combined preferential album as shown in the above figure for each scene.
In practice, the combined album application side stores the mined consumption scenario, binds the corresponding combined offer album, and deploys and presents at the e-commerce platform front end, the contents of the following table:
table 5
Therefore, the invention can be applied to various marketing channel display pages of all the industry e-commerce platforms, activity aggregation display pages of e-commerce promotion activities, suit of commodity detail display pages, recommendation, order collection and other services.
The invention converts the problem of generating scene-oriented combination excellent purchase with great technical difficulty into a series of search problems, and gradually reduces the search range from commodities in a large range and even all commodity categories until a combined preferential album (a plurality of commodities) is generated finally. Firstly, in large commodity categories (such as primary or secondary commodity categories), even total-station commodity categories, specific consumption scenes are mined and a category set associated with the consumption scenes is locked through a big data statistical analysis method, so that the complexity of problems is reduced; secondly, after a class set corresponding to the locked consumption scene is obtained, continuously locking and optimizing a most valuable candidate commodity set; and finally, generating a combined favorable commodity album which best meets the consumption scene, has favorable strength and best meets the application requirements of the e-commerce platform combined favorable album according to a configurable optimization target in the candidate commodity set.
Accordingly, due to the big data statistical analysis of the order data, it is ensured that the refined set of categories characterizes the purchasing behavior of the consumer. For a given consumption scene, the optimal combination of the candidate commodities in the candidate commodity set is carried out, so that a batch of commodities which are more likely to generate the most valuable combined commodities and are bought in a good-and-good mode are ensured to be locked. And in the optimized commodity combination range, the finally formed combination preferential albums can realize the set target through searching and sorting of the mathematical model.
Fig. 7 is a block diagram of an apparatus for constructing a commodity combination according to an exemplary embodiment of the present invention. The apparatus shown in fig. 7 is only an example and should not limit the functionality and scope of use of embodiments of the present invention in any way.
Referring to fig. 7, the apparatus includes a processor 701, a memory 702, and an input-output device 703 connected by a bus. The memory 702 includes a Read Only Memory (ROM) and a Random Access Memory (RAM), and various computer instructions and data required to perform system functions are stored in the memory 702, and the processor 701 reads the various computer instructions from the memory 702 to perform various appropriate actions and processes. An input/output device including an input portion of a keyboard, a mouse, and the like; an output section including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section including a hard disk and the like; and a communication section including a network interface card such as a LAN card, a modem, or the like. The memory 702 also stores computer instructions to perform the operations specified by the apparatus of an embodiment of the present invention. The computer instructions include: according to order data, acquiring a plurality of item sets, wherein each item set comprises a plurality of commodity categories, each commodity category belongs to N-level commodity categories, commodities contained in at least two commodity categories appear in the same order, and N is greater than or equal to 1; for each category set, acquiring candidate commodities from a plurality of commodities contained in the category set, and forming a candidate commodity set, wherein the candidate commodities meet the current discount and/or promotion requirements; and acquiring a commodity combination with the preference strength greater than or equal to a preset preference strength as a combined preference album aiming at each candidate commodity set.
Accordingly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions that, when executed, implement the operations specified by the above-described method.
The flowcharts and block diagrams in the figures and block diagrams illustrate the possible architectures, functions, and operations of the systems, methods, and apparatuses according to the embodiments of the present invention, and may represent a module, a program segment, or merely a code segment, which is an executable instruction for implementing a specified logical function. It should also be noted that executable instructions that implement specified logical functions may be recombined to create new modules and program segments. The blocks of the drawings, and the order of the blocks, are thus provided to better illustrate the processes and steps of the embodiments and should not be taken as limiting the invention itself.
The various modules or units of the system may be implemented in hardware, firmware or software. The software includes, for example, a code program formed using various programming languages such as JAVA, C/C + +/C #, SQL, and the like. Although the steps and sequence of steps of the embodiments of the present invention are presented in method and method illustrations, the executable instructions of the steps implementing the specified logical functions may be re-combined to create new steps. The sequence of steps should not be limited to the order of steps in the methods and method illustrations, but can be modified as required by the function. Such as performing some of the steps in parallel or in reverse order.
Systems and methods according to the present invention may be deployed on a single server or on multiple servers. For example, different modules may be deployed on different servers, respectively, to form a dedicated server. Alternatively, the same functional unit, module or system may be deployed in a distributed fashion across multiple servers to relieve load stress. Servers include, but are not limited to, multiple PCs, PC servers, blades, supercomputers, etc. on the same local area network and connected via the Internet.
The above is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made to the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (16)
1. A method of constructing a portfolio of commodities, comprising:
according to order data, acquiring a plurality of item sets, wherein each item set comprises a plurality of commodity items, each commodity item is an N-level commodity item, commodities contained in at least two commodity items appear in the same order, and N is an integer greater than or equal to 1;
for each category set, acquiring candidate commodities from a plurality of commodities contained in the category set, and forming a candidate commodity set, wherein the candidate commodities meet the current discount and/or promotion requirements; and
and acquiring a commodity combination with the preference strength greater than or equal to the preset preference strength as a combined preference album aiming at each candidate commodity set.
2. The method of claim 1, further comprising: and releasing the combined preferential album.
3. The method of claim 2, wherein the combination offer album is distributed as a hash group and/or recommendation group.
4. The method of claim 1, wherein obtaining a plurality of sets of categories from the order data comprises:
acquiring N-level commodity classes to which each commodity belongs, wherein each order comprises the N-level commodity classes;
constructing a undirected weight graph according to the N-level commodity class to which each commodity belongs, wherein each order comprises the commodities;
obtaining a plurality of first subgraphs from the undirected weight graph, wherein the first subgraphs are subgraphs with communication rate and/or weight larger than or equal to a set threshold; and
and obtaining the plurality of item sets according to the plurality of first subgraphs.
5. The method of claim 4, wherein the first subgraph is a full graph.
6. The method of claim 1, further comprising: and optimizing the candidate commodity set, and acquiring a commodity combination reaching preset discount strength as a combined discount album for each candidate commodity set:
and acquiring commodity combinations with the preference strength greater than or equal to the preset preference strength as combined preference albums for each optimized candidate commodity set.
7. The method of claim 6, wherein the candidate product portfolio is optimized based on an indicator of at least one of a strength of offer, a strength of goodness, a strength of purchase, and a strength of novelty.
8. The method of claim 7, wherein optimizing the candidate product portfolio based on an indicator of at least one of offer strength, goodness, purchase strength, and novelty strength further comprises:
setting respective weights of the preferential strength, the favorable evaluation strength, the purchasing strength and the new product strength;
calculating the value degree of each commodity in the candidate commodity combination according to the discount degree, the favorable evaluation degree, the purchasing degree, the new product degree and respective weights; and
and eliminating the commodities with the value degree equal to or larger than a second set threshold value in the candidate commodity combination.
9. The method of claim 1, wherein obtaining a combination of items greater than or equal to a predetermined offer strength as a combined offer album comprises:
establishing a target function taking the preset preferential strength as a target and taking the current preferential and/or promotion requirement and budget limitation as constraint conditions; and
and solving the objective function to obtain the combined preferential album.
10. A system for constructing a portfolio of merchandise, comprising:
the system comprises a scene mining module, a data processing module and a data processing module, wherein the scene mining module is used for acquiring a plurality of commodity class sets according to order data, each commodity class set comprises a plurality of commodity classes, each commodity class belongs to N-level commodity classes, commodities contained in at least two commodity classes appear in the same order, and N is greater than or equal to 1;
the commodity selection module is used for acquiring candidate commodities from a plurality of commodities contained in each commodity class set and forming a candidate commodity set, wherein the candidate commodities meet the current discount and/or promotion requirements; and
and the album optimization module is used for acquiring a commodity combination with the preference strength greater than or equal to the preset preference strength as a combined preference album for each candidate commodity set.
11. The system of claim 10, wherein the scene mining module comprises:
the drawing expression unit is used for acquiring the N-level commodity class to which each commodity belongs and contained in each order, and constructing a undirected weight drawing according to the N-level commodity class to which each commodity belongs and contained in each order;
the subgraph acquisition unit is used for obtaining a plurality of first subgraphs from the undirected weight graph, wherein the first subgraph is the subgraph of which the communication rate and/or the weight are greater than or equal to a set threshold; and
and the data output unit is used for obtaining the plurality of item sets according to the plurality of first subgraphs.
12. The system of claim 11, wherein the first sub-graph is a full graph.
13. The system of claim 10, wherein the selection of items module 602 comprises:
the information extraction unit is used for obtaining a plurality of candidate commodity sets according to the plurality of category sets;
a commodity optimization unit for optimizing the candidate commodity set;
and the data generating unit is used for establishing a data unit according to the optimized candidate commodity set.
14. The system of claim 10, wherein the album optimization module comprises:
the model establishing unit is used for establishing a target function which takes the preset preferential strength as a target and takes the current preferential, the promotion requirement and the budget limit as constraint conditions;
and the model solving unit is used for solving the objective function to obtain the combined preferential album.
15. A computer-readable storage medium storing computer instructions which, when executed, implement the method of any one of claims 1 to 9.
16. An apparatus, comprising:
a memory for storing computer instructions;
a processor coupled to the memory, the processor configured to perform implementing the method of any of claims 1-9 based on computer instructions stored by the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910335099.3A CN111738786A (en) | 2019-04-24 | 2019-04-24 | Method, system, apparatus and readable storage medium for building a combination of commodities |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910335099.3A CN111738786A (en) | 2019-04-24 | 2019-04-24 | Method, system, apparatus and readable storage medium for building a combination of commodities |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111738786A true CN111738786A (en) | 2020-10-02 |
Family
ID=72645795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910335099.3A Pending CN111738786A (en) | 2019-04-24 | 2019-04-24 | Method, system, apparatus and readable storage medium for building a combination of commodities |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111738786A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113919912A (en) * | 2021-10-13 | 2022-01-11 | 广州风雷益信息技术有限公司 | Intelligent product selection method, system, equipment and readable storage medium |
| WO2022011947A1 (en) * | 2020-10-23 | 2022-01-20 | 平安科技（深圳）有限公司 | Transaction data processing method and apparatus, and computer device and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002074129A (en) * | 2000-08-29 | 2002-03-15 | Dainippon Printing Co Ltd | Incentive setting device and sales promotion support system |
| KR100426348B1 (en) * | 2003-02-15 | 2004-04-08 | 김종희 | Business method of on-line shopping malls reduced the selling price in case of purchasing a numerous products at the same time |
| US20120123872A1 (en) * | 2010-11-16 | 2012-05-17 | Chiu Yi-Chia | Cooperative personalized promotion method according to consumer-store interactive transaction history and system using the same |
| US20150134442A1 (en) * | 2013-11-14 | 2015-05-14 | Target Brands Inc. | Best monetary discount determination methods and systems |
| CN106530017A (en) * | 2016-12-19 | 2017-03-22 | 车晴 | Online store discount coupon automatic acquisition and shopping combination recommendation method |
| WO2017124416A1 (en) * | 2016-01-21 | 2017-07-27 | 赵政荣 | Usage data acquisition method of coupon recommendation related technology, and recommendation system |
| CN107563859A (en) * | 2017-08-31 | 2018-01-09 | 深圳前海弘稼科技有限公司 | Method of Commodity Recommendation, device, equipment and storage medium |
| CN107767217A (en) * | 2017-10-19 | 2018-03-06 | 康佳集团股份有限公司 | Shopping recommendation method, mobile terminal and storage medium |
| CN108960992A (en) * | 2018-06-29 | 2018-12-07 | 黄宗治 | A kind of information recommendation method and relevant device |
| TWI652639B (en) * | 2018-02-01 | 2019-03-01 | 中華電信股份有限公司 | Recommended system and method of product promotion combination |
-
2019
- 2019-04-24 CN CN201910335099.3A patent/CN111738786A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002074129A (en) * | 2000-08-29 | 2002-03-15 | Dainippon Printing Co Ltd | Incentive setting device and sales promotion support system |
| KR100426348B1 (en) * | 2003-02-15 | 2004-04-08 | 김종희 | Business method of on-line shopping malls reduced the selling price in case of purchasing a numerous products at the same time |
| US20120123872A1 (en) * | 2010-11-16 | 2012-05-17 | Chiu Yi-Chia | Cooperative personalized promotion method according to consumer-store interactive transaction history and system using the same |
| US20150134442A1 (en) * | 2013-11-14 | 2015-05-14 | Target Brands Inc. | Best monetary discount determination methods and systems |
| WO2017124416A1 (en) * | 2016-01-21 | 2017-07-27 | 赵政荣 | Usage data acquisition method of coupon recommendation related technology, and recommendation system |
| CN106530017A (en) * | 2016-12-19 | 2017-03-22 | 车晴 | Online store discount coupon automatic acquisition and shopping combination recommendation method |
| CN107563859A (en) * | 2017-08-31 | 2018-01-09 | 深圳前海弘稼科技有限公司 | Method of Commodity Recommendation, device, equipment and storage medium |
| CN107767217A (en) * | 2017-10-19 | 2018-03-06 | 康佳集团股份有限公司 | Shopping recommendation method, mobile terminal and storage medium |
| TWI652639B (en) * | 2018-02-01 | 2019-03-01 | 中華電信股份有限公司 | Recommended system and method of product promotion combination |
| CN108960992A (en) * | 2018-06-29 | 2018-12-07 | 黄宗治 | A kind of information recommendation method and relevant device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022011947A1 (en) * | 2020-10-23 | 2022-01-20 | 平安科技（深圳）有限公司 | Transaction data processing method and apparatus, and computer device and storage medium |
| CN113919912A (en) * | 2021-10-13 | 2022-01-11 | 广州风雷益信息技术有限公司 | Intelligent product selection method, system, equipment and readable storage medium |
| CN113919912B (en) * | 2021-10-13 | 2023-06-02 | 广州风雷益信息技术有限公司 | Intelligent product selection method, system, equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7577579B2 (en) | Method of predicting sales based on triple-axis mapping of customer value | |
| US7996331B1 (en) | Computer-implemented systems and methods for performing pricing analysis | |
| Sadeghi et al. | An AHP decision making model for optimal allocation of energy subsidy among socio-economic subsectors in Iran | |
| CN108960992A (en) | A kind of information recommendation method and relevant device | |
| CN107180371A (en) | The method and system of commodity is bought using reward voucher | |
| CN109087177A (en) | To the method, apparatus and computer readable storage medium of target user's Recommendations | |
| CN104346698B (en) | Based on the analysis of the food and drink member big data of cloud computing and data mining and checking system | |
| CN110032606A (en) | A kind of sample clustering method and device | |
| CN110580649A (en) | Method and device for determining potential value of commodity | |
| CN104615721B (en) | For the method and system based on return of goods related information Recommendations | |
| Prado et al. | Integration of MCDA tools in valuation of comparative life cycle assessment | |
| Hemalatha | Market basket analysis–a data mining application in Indian retailing | |
| CN109727078A (en) | A kind of Method for Sales Forecast modification method based on merchandise classification tree | |
| CN111738786A (en) | Method, system, apparatus and readable storage medium for building a combination of commodities | |
| CN109886769A (en) | A kind of the displaying optimization method and device of virtual objects | |
| US20210090105A1 (en) | Technology opportunity mapping | |
| CN103903148A (en) | C2C system, B2C system, and application methods thereof | |
| CN111768243A (en) | Sales prediction method, prediction model construction method, device, equipment and medium | |
| CN108629467A (en) | A kind of sample message processing method and system | |
| US20140297372A1 (en) | Evaluation support device and evaluation support method | |
| Griffin et al. | Clustering retail stores for inventory transshipment | |
| Anusha et al. | Segmentation of retail mobile market using HMS algorithm | |
| Azadnia et al. | Integration model of Fuzzy C means clustering algorithm and TOPSIS Method for Customer Lifetime Value Assessment | |
| CN111340578A (en) | Method, device, medium and electronic equipment for generating commodity association relationship | |
| CN110968670A (en) | Method, device, equipment and storage medium for acquiring attributes of popular commodities |
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 |