CN112446752A - Information pushing method and device, electronic commerce system and storage medium - Google Patents
Information pushing method and device, electronic commerce system and storage medium Download PDFInfo
- Publication number
- CN112446752A CN112446752A CN201910804945.1A CN201910804945A CN112446752A CN 112446752 A CN112446752 A CN 112446752A CN 201910804945 A CN201910804945 A CN 201910804945A CN 112446752 A CN112446752 A CN 112446752A
- Authority
- CN
- China
- Prior art keywords
- obtaining
- user
- similar
- item
- information
- 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 48
- 230000006870 function Effects 0.000 claims description 22
- 238000001914 filtration Methods 0.000 claims description 13
- 238000006073 displacement reaction Methods 0.000 claims description 8
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 239000013598 vector Substances 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000011524 similarity measure Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000007704 transition Effects 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]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present disclosure provides an information push method, an information push device, an electronic commerce system and a storage medium, which relate to the technical field of information processing, wherein the method comprises the following steps: obtaining recommended articles corresponding to the similar user group, obtaining user positions of the similar users in the similar user group and warehousing positions of the recommended articles, and obtaining distribution distance information based on the user position information and the warehousing positions; obtaining a pushing target user in the similar user group according to the distribution distance and the inventory constraint condition corresponding to the recommended article; and generating an item sharing link corresponding to the recommended item, and pushing the item sharing link to a pushing target user. The method, the device, the electronic commerce system and the storage medium can automatically generate the item sharing link based on the personalized characteristics and the geographical position of the user and the sales volume of the items, can support more scenes, and improve the experience of the user.
Description
Technical Field
The present disclosure relates to the field of information processing technologies, and in particular, to an information pushing method and apparatus, an electronic commerce system, and a storage medium.
Background
The commodity grouping scheme of the e-commerce platform is to manually analyze and select commodities which can be grouped according to the inventory amount of the commodities and set grouping activities. The shopping spelling activity is open to all users on a single channel page, the E-commerce platform lacks personalized recommendation aiming at the users, the users need to screen and search interested commodities to determine whether to participate in the group, and when the number of the shopping spelling activities reaches a certain number, the searching difficulty of the users is increased, and the user experience is reduced.
Disclosure of Invention
In view of the above, an object of the present disclosure is to provide an information pushing method, an information pushing apparatus, an electronic commerce system, and a storage medium.
According to an aspect of the present disclosure, there is provided an information pushing method, including: obtaining at least one similar user group; obtaining recommended articles corresponding to the similar user group; obtaining user positions of similar users in the similar user groups and warehousing positions of the recommended articles, and obtaining distribution distance information based on the user position information and the warehousing positions; obtaining a pushing target user in the similar user group according to the distribution distance and an inventory constraint condition corresponding to the recommended article; and generating an item sharing link corresponding to the recommended item, and pushing the item sharing link to the pushing target user.
Optionally, the obtaining at least one similar user group comprises: obtaining historical data of the item sharing link, and obtaining a user set according to the historical data; obtaining at least one similar user group based on the user set according to a preset grouping rule; wherein the preset grouping rule comprises: collaborative filtering algorithms.
Optionally, the obtaining recommended items corresponding to the similar user group includes: obtaining an item recommendation set corresponding to each similar user in the group of similar users; and obtaining the intersection of the item recommendation sets, and taking the items in the intersection as the recommended items.
Optionally, the obtaining item recommendation sets corresponding to each similar user in the group of similar users comprises: obtaining historical item purchase information of the similar users, and determining preference information of the similar users based on the historical item purchase information; and determining the item recommendation set corresponding to the similar users according to the preference information.
Optionally, the preference information includes: frequency of item purchases; the determining preference information of the similar user based on the historical item purchase information comprises: obtaining purchased goods and goods purchase frequency with the similar user based on the historical goods purchase information; the determining the item recommendation set corresponding to the similar user direction according to the preference information comprises: sorting the item purchase frequency from top to bottom; selecting a preset number of the item purchasing frequencies based on the sorting result, and taking the purchased items corresponding to the selected item purchasing frequencies as preference items; and obtaining the classification information of the preferred articles, determining recommended articles according to the classification information and the current article inventory information, and generating the article recommendation set based on the recommended articles.
Optionally, within a preset time interval, obtaining a plurality of position coordinates corresponding to the similar users; obtaining a displacement distance between two adjacent position coordinates; and if the displacement distance is determined to be larger than a preset distance threshold value, removing the similar user from the similar user group.
Optionally, the obtaining of the push target user in the similar user group according to the delivery distance and the inventory constraint condition corresponding to the recommended item includes: obtaining a distribution route and a distribution distance between the current user position coordinate of the similar user and the warehousing position coordinate; obtaining a distribution cost corresponding to a unit distribution distance of the distribution route; establishing a distribution cost linear programming function according to the distribution lines and the distribution cost; and solving the linear distribution cost programming function based on the inventory constraint condition to obtain the push target user.
Optionally, the solving the delivery cost linear programming function based on the inventory constraint condition to obtain the push target user includes: and obtaining a distribution line set based on a solution result of the distribution cost linear programming function, and taking a similar user set corresponding to the distribution line set as a pushing target user set, so that the pushing target user number of the pushing target user set is maximum and the total distribution cost of the pushing target users of the pushing target user set is minimum.
Optionally, the delivery cost linear programming function is:
wherein n is the number of push target users in the similar user group, wkSaid delivery distance for the k-th similar user, DkDistributing costs for the unit distance for the kth similar user; the inventory constraint conditions are as follows: S-P-n>0; wherein s is the stock number of the recommended item, and p is the predicted sales volume of the recommended item.
According to another aspect of the present disclosure, there is provided an information pushing apparatus including: the user group obtaining module is used for obtaining at least one similar user group; a recommended article determining module for obtaining recommended articles corresponding to the similar user group; the distribution distance obtaining module is used for obtaining the user positions of similar users in the similar user groups and the warehousing positions of the recommended articles and obtaining distribution distance information based on the user position information and the warehousing positions; the target user determining module is used for obtaining a pushing target user in the similar user group according to the distribution distance and the inventory constraint condition corresponding to the recommended article; and the information pushing module is used for generating an article sharing link corresponding to the recommended article and pushing the article sharing link to the pushing target user.
According to still another aspect of the present disclosure, there is provided an information pushing apparatus including: a memory; and a processor coupled to the memory, the processor configured to perform the method as described above based on instructions stored in the memory.
According to still another aspect of the present disclosure, there is provided an electronic commerce system including: the information pushing device is described above.
According to yet another aspect of the present disclosure, a computer-readable storage medium is provided, which stores computer instructions for execution by a processor to perform the method as described above.
According to the information pushing method, the information pushing device, the electronic commerce system and the storage medium, the similar user group and the corresponding recommended articles are obtained, the delivery distance information is obtained based on the user positions of the similar users in the similar user group and the storage positions of the recommended articles, the pushing target users in the similar user group are obtained according to the delivery distance and the inventory constraint conditions corresponding to the recommended articles, article sharing links are generated and pushed to the pushing target users; the goods sharing link can be automatically generated based on the personalized characteristics and the geographical position of the user and the sales volume condition of the goods, more scenes can be supported, and the experience of the user is improved.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without inventive exercise.
FIG. 1 is a schematic flow chart diagram illustrating one embodiment of an information push method according to the present disclosure;
FIG. 2 is a schematic flow chart diagram of obtaining similar user groups in an embodiment of an information pushing method according to the present disclosure;
FIG. 3 is a schematic flow chart diagram illustrating a recommended item obtaining process in an embodiment of an information pushing method according to the present disclosure;
FIG. 4 is a schematic flow chart diagram illustrating filtering of similar users in one embodiment of an information push method according to the present disclosure;
fig. 5 is a schematic flowchart of obtaining a push target user in an embodiment of an information pushing method according to the present disclosure;
FIG. 6 is a block diagram illustration of one embodiment of an information pushing device according to the present disclosure;
fig. 7 is a block diagram of another embodiment of an information pushing device according to the present disclosure.
Detailed Description
The present disclosure now will be described more fully hereinafter with reference to the accompanying drawings, in which exemplary embodiments of the disclosure are shown. The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure. The technical solution of the present disclosure is described in various aspects below with reference to various figures and embodiments.
Fig. 1 is a schematic flow chart diagram of an embodiment of an information pushing method according to the present disclosure, as shown in fig. 1:
And 103, obtaining the user positions of the similar users in the similar user group and the warehousing positions of the recommended articles, and obtaining distribution distance information based on the user position information and the warehousing positions.
When the user uses the e-commerce APP, the location information of the user can be obtained, and the location information of the user can be coordinate information obtained through a GPS module in the user terminal, or the like. The warehousing position can be obtained in advance, and the warehousing position can be coordinates of a warehousing center and the like. The positions of the user and the warehousing center can be determined on the electronic map through the user coordinates and the warehousing coordinates, and the distribution lines, the distribution distances and the like between the user and the warehousing can be calculated by using the electronic map.
And 104, acquiring a pushing target user in the similar user group according to the distribution distance and the inventory constraint condition corresponding to the recommended item.
And 105, generating an item sharing link corresponding to the recommended item, and pushing the item sharing link to a pushing target user.
After the pushing target user is obtained, an article sharing link corresponding to the recommended article is generated and pushed to the pushing target user, and the pushing target user receiving the article sharing link can participate in the shopping-combining activity of the recommended article.
Fig. 2 is a schematic flowchart of obtaining similar user groups in an embodiment of an information pushing method according to the present disclosure, as shown in fig. 2:
The historical data of the article sharing link for the user to share the purchases is obtained, the user issues purchase sharing information through issuing the article sharing link, and the user can participate in purchase sharing after receiving the article sharing link. For example, a certain item SKU sets the buy-together campaign, the user places an order to buy through the share link url + activityId, and the user set { jdx1, jdx2, jdx3} can be obtained by obtaining activityId for all buy-together orders.
The collaborative filtering algorithm is one of recommendation algorithms and is also a machine learning algorithm. And obtaining users with the same preference based on a collaborative filtering algorithm, and finding several users with the closest preference to form a similar user group. And cooperatively filtering and analyzing the user interests, finding out similar (interested) users of the specified user in the user group, and integrating the evaluation of the similar users on certain information to form preference degree prediction of the specified user on the information by the system. The similarity calculation of the collaborative filtering algorithm mainly comprises three algorithms: a cosine theorem similarity measure, an Euclidean distance similarity measure, and a Jacard similarity measure.
And cooperatively filtering the sharing path based on the articles, taking each user as a node to count the degree of the access, and taking the node as a score based on the items for cooperative filtering. And solving a similar user set according to the scores to obtain a plurality of user groups. At least one similar user group may be obtained based on the set of users using existing collaborative filtering algorithms.
In one embodiment, there may be multiple ways to obtain recommended items corresponding to a group of similar users. For example, an item recommendation set corresponding to each similar user in the similar user group is obtained, an intersection of the item recommendation sets is obtained, and an item in the intersection is taken as a recommended item. Historical item purchase information of similar users is obtained, preference information of the similar users is determined based on the historical item purchase information, and item recommendation sets corresponding to the similar users are determined according to the preference information.
FIG. 3 is a schematic flow chart diagram illustrating a recommended item obtaining process in an embodiment of an information pushing method according to the present disclosure; the preference information includes the frequency of purchase of the item, etc., as shown in fig. 3,
And 304, obtaining the classification information of the preferred articles, determining recommended articles according to the classification information and the current article inventory information, and generating an article recommendation set based on the recommended articles.
For example, historical item purchase information of similar users in a group of similar users is obtained, purchased items with similar users are obtained, and item purchase frequency is obtained. The item purchase frequencies are sorted from top to bottom, the number of items in the item recommendation set can be set to be k, m item purchase frequencies arranged at the top are selected based on the sorting result, and m purchased items corresponding to the selected m item purchase frequencies are used as preference items. The method comprises the steps of obtaining classification information of m preferred articles, determining k recommended articles according to the classification information and current article inventory information, and generating an article recommendation set based on the k recommended articles. And obtaining the intersection of the item recommendation sets of all similar users in the similar user group, and taking the items in the intersection as recommended items.
Fig. 4 is a schematic flowchart of filtering similar users in an embodiment of an information pushing method according to the present disclosure, as shown in fig. 4:
In step 403, if it is determined that the displacement distance is greater than the preset distance threshold, the similar user is removed from the group of similar users.
The preset time interval can be one day and the like, and a plurality of pieces of position coordinate information corresponding to all similar users in the similar user group are obtained in the time interval. For example, the position coordinate set of the similar user a in the last day is obtained { (x1, y1), (x2, y2), (x3, y3) }, (xn, yn) }, and the values in the set are subtracted two by two and the absolute value is calculated.
Replacing (| x1-x2|, | y1-y2|), (| x1-x3|, | y1-y3|), (| x1-xn |, | y1-yn |)) with { (dx1, dy1), (dx2, dy2), (dx3, dy3), (dxn, dyn) }, if dx and dy are greater than a certain threshold M, then this similar user a may be in a different city during this period, this similar user a may be removed from the similar user group, or, instead of removing this similar user a, coordinate points corresponding to dx and dy that are greater than a certain threshold M are removed, and the position points in the remaining set are randomly selected as the position coordinates of this similar user.
Fig. 5 is a schematic flowchart of a process of obtaining a push target user in an embodiment of an information push method according to the present disclosure, as shown in fig. 5:
One user coordinate can be randomly selected from a plurality of user coordinates obtained in a preset time interval to serve as the current user position coordinate of the similar user. And determining a distribution route and a distribution distance between the current user position coordinates and the warehousing position coordinates of the similar users by using an electronic map and the like.
And step 504, solving the linear distribution cost programming function based on the inventory constraint condition to obtain a push target user.
Linear Programming (LP) refers to the optimization of the objective function and the constraint condition that are both Linear. The linear distribution cost planning function is an objective function, and the inventory constraint condition is a constraint condition. And obtaining a distribution line set based on a solving result of the distribution cost linear programming function, and taking a similar user set corresponding to the distribution line set as a pushing target user set, so that the pushing target user number of the pushing target user set is maximum, and the total distribution cost of the pushing target users of the pushing target user set is minimum.
For example, an optimal solution of a linear distribution cost planning function is obtained through linear planning, so that the logistics cost is the minimum value and meets the limitation of the inventory number, and the linear distribution cost planning function is as follows:
wherein n is the number of push target users in the similar user group, wkDistribution distance for the k-th similar user, DkUnit distance for the k-th similar user(ii) away from distribution costs; the inventory constraint conditions are as follows: S-P-n>0; wherein s is the inventory number of the recommended item, and p is the predicted sales volume of the recommended item. Sales forecast refers to forecast of future sales based on past sales and using sales forecasting models built into the system or customized by the user.
D in the linear distribution cost programming function identifies the distribution distance from the coordinates of the similar users to the storage center, w corresponds to the distribution cost of the unit distance of the area where the similar users are located, and the existing linear programming solving method can be used for continuously solving w and D to enable Z to be minimum, so that an optimal solution is obtained. And calculating a group of distribution line vectors according to the constraint conditions, and verifying whether the distribution line vectors are in the feasible region. And iteratively expanding the distribution line vector until the dimension of the distribution line vector approaches to maximize n and minimize the sum of the logistics cost, so that the distribution line vector is an optimal solution, and if no optimal solution exists, replacing the optimal solution by a suboptimal solution. And obtaining a distribution line set based on the distribution line vector, taking a similar user set corresponding to the distribution line set as a pushing target user set, generating an article sharing link corresponding to the recommended article, creating a purchase-sharing activity, and pushing the article sharing link to the pushing target user one by one.
In one embodiment, as shown in fig. 6, the present disclosure provides an information pushing apparatus 60, including: a user group obtaining module 61, a delivery distance obtaining module 62, a delivery distance obtaining module 63, a target user determining module 64 and an information pushing module 65.
The user group obtaining module 61 obtains at least one similar user group. The recommended item determination module 62 obtains recommended items corresponding to similar user groups. The delivery distance obtaining module 63 obtains the user positions of the similar users in the similar user group and the warehousing positions of the recommended articles, and obtains the delivery distance information based on the user position information and the warehousing positions. The target user determination module 64 obtains the push target users in the similar user group according to the delivery distance and the inventory constraint condition corresponding to the recommended item. The information pushing module 65 generates an item sharing link corresponding to the recommended item, and pushes the item sharing link to the pushing target user.
In one embodiment, the user group obtaining module 61 obtains historical data of the item sharing link, obtains a user set according to the historical data, and obtains at least one similar user group according to a preset grouping rule and based on the user set, where the preset grouping rule includes a collaborative filtering algorithm and the like. The recommended item determination module 62 obtains an item recommendation set corresponding to each similar user in the similar user group, obtains an intersection of the item recommendation sets, and takes items in the intersection as recommended items.
The recommended item determination module 62 obtains historical item purchase information of similar users, determines preference information of the similar users based on the historical item purchase information, and determines an item recommendation set corresponding to the similar users according to the preference information. The preference information includes: frequency of item purchases, etc.; the recommended item determination module 62 obtains purchased items and item purchase frequencies with similar users based on the historical item purchase information. The recommended item determination module 62 sorts the item purchase frequencies in the order from top to bottom, selects a preset number of item purchase frequencies based on the sorting result, and takes the purchased items corresponding to the selected item purchase frequencies as preference items. The recommended item determination module 62 obtains the classification information of the preferred item, determines the recommended item according to the classification information and the current item inventory information, and generates an item recommendation set based on the recommended item.
In one embodiment, the user group obtaining module 61 obtains a plurality of position coordinates corresponding to similar users within a preset time interval, and obtains a displacement distance between two adjacent position coordinates. If it is determined that the displacement distance is greater than the preset distance threshold, the user group obtaining module 61 removes the similar user from the similar user group.
The distribution distance obtaining module 63 obtains a distribution route and a distribution distance between the current user position coordinates and the warehouse position coordinates of the similar user. The target customer determination module 64 obtains a distribution cost corresponding to a unit distribution distance of the distribution line, and establishes a distribution cost linear programming function according to the distribution line and the distribution cost. The target user determination module 64 solves the linear distribution cost planning function based on the inventory constraint condition to obtain the pushed target user.
The target user determination module 64 obtains a distribution line set based on the solution result of the distribution cost linear programming function, and takes a similar user set corresponding to the distribution line set as a push target user set, so that the number of push target users of the push target user set is maximum and the total distribution cost of the push target users of the push target user set is minimum.
Fig. 7 is a block diagram of another embodiment of an information pushing device according to the present disclosure. As shown in fig. 7, the apparatus may include a memory 71, a processor 72, a communication interface 73, and a bus 74. The memory 71 is used for storing instructions, the processor 72 is coupled to the memory 71, and the processor 72 is configured to implement the information push method based on the instructions stored in the memory 71.
The memory 71 may be a high-speed RAM memory, a non-volatile memory (non-volatile memory), or the like, and the memory 71 may be a memory array. The storage 71 may also be partitioned and the blocks may be combined into virtual volumes according to certain rules. The processor 72 may be a central processing unit CPU, or an application Specific Integrated circuit asic, or one or more Integrated circuits configured to implement the information pushing method of the present disclosure.
In one embodiment, the present disclosure provides an electronic commerce system, including the information pushing apparatus in any one of the above embodiments.
In one embodiment, the present disclosure provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement an item storage location determination method as in any of the above embodiments.
According to the information pushing method and device, the electronic commerce system and the storage medium in the embodiment, the similar user group and the corresponding recommended articles are obtained, the delivery distance information is obtained based on the user positions of the similar users in the similar user group and the storage positions of the recommended articles, the pushing target users in the similar user group are obtained according to the delivery distance and the inventory constraint conditions corresponding to the recommended articles, article sharing links are generated and pushed to the pushing target users; the method can automatically generate the item sharing link based on the personalized characteristics and the geographic position of the user and the sales volume condition of the item; the logistics transportation cost and the article inventory can be combined, and personalized recommendation grouping can be realized; more scenes can be supported, and the user experience is improved.
The method and system of the present disclosure may be implemented in a number of ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
The description of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the disclosure in the form disclosed. Many modifications and variations will be apparent to practitioners skilled in this art. The embodiment was chosen and described in order to best explain the principles of the disclosure and the practical application, and to enable others of ordinary skill in the art to understand the disclosure for various embodiments with various modifications as are suited to the particular use contemplated.
Claims (13)
1. An information push method, comprising:
obtaining at least one similar user group;
obtaining recommended articles corresponding to the similar user group;
obtaining user positions of similar users in the similar user groups and warehousing positions of the recommended articles, and obtaining distribution distance information based on the user position information and the warehousing positions;
obtaining a pushing target user in the similar user group according to the distribution distance and an inventory constraint condition corresponding to the recommended article;
and generating an item sharing link corresponding to the recommended item, and pushing the item sharing link to the pushing target user.
2. The method of claim 1, the obtaining at least one similar user group comprising:
obtaining historical data of the item sharing link, and obtaining a user set according to the historical data;
obtaining at least one similar user group based on the user set according to a preset grouping rule; wherein the preset grouping rule comprises: collaborative filtering algorithms.
3. The method of claim 1 or 2, the obtaining recommended items corresponding to the similar user group comprising:
obtaining an item recommendation set corresponding to each similar user in the group of similar users;
and obtaining the intersection of the item recommendation sets, and taking the items in the intersection as the recommended items.
4. The method of claim 3, the obtaining a set of item recommendations corresponding to each of the group of similar users comprising:
obtaining historical item purchase information of the similar users, and determining preference information of the similar users based on the historical item purchase information;
and determining the item recommendation set corresponding to the similar users according to the preference information.
5. The method of claim 4, wherein the preference information comprises: frequency of item purchases; the determining preference information of the similar user based on the historical item purchase information comprises:
obtaining purchased goods and goods purchase frequency with the similar user based on the historical goods purchase information;
the determining the item recommendation set corresponding to the similar user direction according to the preference information comprises:
sorting the item purchase frequency from top to bottom;
selecting a preset number of the item purchasing frequencies based on the sorting result, and taking the purchased items corresponding to the selected item purchasing frequencies as preference items;
and obtaining the classification information of the preferred articles, determining recommended articles according to the classification information and the current article inventory information, and generating the article recommendation set based on the recommended articles.
6. The method of claim 3, further comprising:
obtaining a plurality of position coordinates corresponding to the similar users in a preset time interval;
obtaining a displacement distance between two adjacent position coordinates;
and if the displacement distance is determined to be larger than a preset distance threshold value, removing the similar user from the similar user group.
7. The method of claim 6, the obtaining push target users in the similar user group according to the delivery distance and the inventory constraint corresponding to the recommended item comprising:
obtaining a distribution route and a distribution distance between the current user position coordinate of the similar user and the warehousing position coordinate;
obtaining a distribution cost corresponding to a unit distribution distance of the distribution route;
establishing a distribution cost linear programming function according to the distribution lines and the distribution cost;
and solving the linear distribution cost programming function based on the inventory constraint condition to obtain the push target user.
8. The method of claim 7, wherein solving the delivery cost linear programming function based on the inventory constraints to obtain the push target user comprises:
and obtaining a distribution line set based on a solution result of the distribution cost linear programming function, and taking a similar user set corresponding to the distribution line set as a pushing target user set, so that the pushing target user number of the pushing target user set is maximum and the total distribution cost of the pushing target users of the pushing target user set is minimum.
9. The method of claim 8, wherein,
the distribution cost linear programming function is as follows:
wherein n is the number of push target users in the similar user group, wkSaid delivery distance for the k-th similar user, DkDistributing costs for the unit distance for the kth similar user;
the inventory constraint conditions are as follows: S-P-n > -0; wherein s is the stock number of the recommended item, and p is the predicted sales volume of the recommended item.
10. An information pushing apparatus comprising:
the user group obtaining module is used for obtaining at least one similar user group;
a recommended article determining module for obtaining recommended articles corresponding to the similar user group;
the distribution distance obtaining module is used for obtaining the user positions of similar users in the similar user groups and the warehousing positions of the recommended articles and obtaining distribution distance information based on the user position information and the warehousing positions;
the target user determining module is used for obtaining a pushing target user in the similar user group according to the distribution distance and the inventory constraint condition corresponding to the recommended article;
and the information pushing module is used for generating an article sharing link corresponding to the recommended article and pushing the article sharing link to the pushing target user.
11. An information pushing apparatus comprising:
a memory; and a processor coupled to the memory, the processor configured to perform the method of any of claims 1-9 based on instructions stored in the memory.
12. An electronic commerce system, comprising:
the information pushing device according to claim 10 or 11.
13. A computer-readable storage medium having stored thereon computer instructions for execution by a processor to perform the method of any one of claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910804945.1A CN112446752A (en) | 2019-08-29 | 2019-08-29 | Information pushing method and device, electronic commerce system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910804945.1A CN112446752A (en) | 2019-08-29 | 2019-08-29 | Information pushing method and device, electronic commerce system and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112446752A true CN112446752A (en) | 2021-03-05 |
Family
ID=74741568
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910804945.1A Pending CN112446752A (en) | 2019-08-29 | 2019-08-29 | Information pushing method and device, electronic commerce system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112446752A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106503028A (en) * | 2015-09-08 | 2017-03-15 | 北京邮电大学 | Recommend method and system |
CN107481114A (en) * | 2017-08-16 | 2017-12-15 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, e-commerce system and storage medium |
CN107527146A (en) * | 2017-08-23 | 2017-12-29 | 北京惠赢天下网络技术有限公司 | A kind of processing method of cargo transaction information, device, and system |
CN107784066A (en) * | 2017-08-25 | 2018-03-09 | 上海壹账通金融科技有限公司 | Information recommendation method, device, server and storage medium |
CN109214893A (en) * | 2018-08-31 | 2019-01-15 | 深圳春沐源控股有限公司 | Method of Commodity Recommendation, recommender system and computer installation |
-
2019
- 2019-08-29 CN CN201910804945.1A patent/CN112446752A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106503028A (en) * | 2015-09-08 | 2017-03-15 | 北京邮电大学 | Recommend method and system |
CN107481114A (en) * | 2017-08-16 | 2017-12-15 | 北京京东尚科信息技术有限公司 | Method of Commodity Recommendation, device, e-commerce system and storage medium |
CN107527146A (en) * | 2017-08-23 | 2017-12-29 | 北京惠赢天下网络技术有限公司 | A kind of processing method of cargo transaction information, device, and system |
CN107784066A (en) * | 2017-08-25 | 2018-03-09 | 上海壹账通金融科技有限公司 | Information recommendation method, device, server and storage medium |
CN109214893A (en) * | 2018-08-31 | 2019-01-15 | 深圳春沐源控股有限公司 | Method of Commodity Recommendation, recommender system and computer installation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107481114B (en) | Commodity recommendation method and device, electronic commerce system and storage medium | |
CN109087177B (en) | Method, device and computer-readable storage medium for recommending commodities to target user | |
US11449919B2 (en) | Commodity recommendation method and commodity recommendation device | |
US20230394432A1 (en) | Machine-learned model for optmizing selection sequence for items in a warehouse | |
US11295367B2 (en) | System for in-store consumer behaviour event metadata aggregation, data verification and the artificial intelligence analysis thereof for data interpretation and associated action triggering | |
US20190180301A1 (en) | System for capturing item demand transference | |
US20140278778A1 (en) | Method, apparatus, and computer-readable medium for predicting sales volume | |
JP2021511611A (en) | Recommended equipment and methods | |
CN104615721B (en) | For the method and system based on return of goods related information Recommendations | |
US20190272491A1 (en) | Inventory placement recommendation system | |
CN110570233A (en) | User buyback time prediction method and device for e-commerce platform | |
CN109146559A (en) | A kind of commodity purchase guiding system for Commercial Complex | |
CN111784428A (en) | Information pushing method and device, electronic commerce system and storage medium | |
CN109272351B (en) | Passenger flow line and passenger flow hot area determining method and device | |
CN114140193A (en) | Commodity recommendation method and device | |
CN113554455A (en) | Store commodity analysis method and device based on artificial intelligence and storage medium | |
CN110264219B (en) | Customer monitoring and analyzing system based on big data | |
CN117078360A (en) | Intelligent commodity display method, system and device based on off-line popularization | |
CN108416611B (en) | Supermarket path recommendation system and method thereof | |
CN112446752A (en) | Information pushing method and device, electronic commerce system and storage medium | |
CN110110222B (en) | Target object determination method and device and computer storage medium | |
KR101324907B1 (en) | Method for determining commendatory booth based on similarity of visiting booth and favorite order | |
JP7092845B2 (en) | Information processing equipment and information processing method | |
CN113762990A (en) | Commodity recommendation method and device, computing equipment and computer storage medium | |
CN108537604A (en) | Commodity attribute method, system and outlet server under line |
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 |