CN112052403B - Commodity community classification-based link degree propagation method, system and equipment - Google Patents
Commodity community classification-based link degree propagation method, system and equipment Download PDFInfo
- Publication number
- CN112052403B CN112052403B CN202010953826.5A CN202010953826A CN112052403B CN 112052403 B CN112052403 B CN 112052403B CN 202010953826 A CN202010953826 A CN 202010953826A CN 112052403 B CN112052403 B CN 112052403B
- Authority
- CN
- China
- Prior art keywords
- commodity
- node
- commodity node
- community
- degree
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000001960 triggered effect Effects 0.000 claims description 43
- 238000004364 calculation method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 238000009795 derivation Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 abstract description 6
- 230000002776 aggregation Effects 0.000 abstract description 4
- 238000004220 aggregation Methods 0.000 abstract description 4
- 238000009826 distribution Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 8
- 230000006399 behavior Effects 0.000 description 4
- 230000007480 spreading Effects 0.000 description 4
- 238000003892 spreading Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 235000008446 instant noodles Nutrition 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- 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
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (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 method calculates and acquires commodity node groups with the maximum linkage degree by carrying out group division on commodity nodes; finding out the node with the maximum linking degree in the commodity node group with the maximum linking degree for recommendation; the recommendation based on collaborative filtering is subjected to dimension raising, and the recommendation is raised from point recommendation to surface recommendation, so that the problem that the point is optimal and the surface is not considered is solved; in terms of precision, the method for effectively dividing the ideal propagation communities of the relational network is found, the problem that the traditional relational network does not divide communities or cannot find the optimal community division scale because the local distribution aggregation condition of the whole group is not considered, so that the propagation center points of the whole group are found too widely, and local distortion is caused is solved, and higher-quality accurate delivery is realized.
Description
Technical Field
The invention relates to the field of data mining, in particular to a link degree propagation method, a link degree propagation system and link degree propagation equipment based on commodity community classification.
Background
The existing commodity or video recommendation based on collaborative filtering and the center point based on a relation network are precisely put in and spread for 2 kinds of centrality. Based on collaborative filtering, predicting interesting or favorite commodities or videos based on historical purchasing or watching behaviors of a user; based on the center point of the relation network, the center degree is accurately put and spread, the spreading center point which can generate the secondary purchasing or watching behaviors in the commodity or the video is found, namely the element which can generate the spreading behaviors is found, and the influence and spreading effect of the whole group are obtained by accurately putting and exposing the element and utilizing the spreading effect.
Based on the collaborative filtered user's historical purchasing or viewing behavior, recommendations are made only by the individual users, and aggregate and propagation effects from the entire purchasing or viewing population, i.e., only "point-to-point recommendations", are not considered, analysis and calculation are not made from the "facets" of the entire viewing population, possibly only point-optimal rather than facet-optimal;
based on the central point of the relation network, the recommendation method of the centrality considers the recommendation of the 'face', has a good recommendation propagation effect on the whole, but has the defect that the internal community structure distribution of the whole relation network is not considered, and the accurate throwing or pushing is performed only through one or more points at the center in the whole group. If a relational network has several aggregation areas, the whole group of the multiple centers is distributed instead of the single center, local distortion is caused, and the whole propagation effect is affected.
Disclosure of Invention
The embodiment of the invention aims to provide a method, a system and equipment for transmitting a link degree based on commodity community classification, and aims to solve the problems of inaccurate recommending effect and low efficiency of unilateral collaborative filtering recommendation or relational network center point recommendation in the prior art.
A first object of an embodiment of the present invention is to provide a link propagation method based on commodity community classification, where the method includes:
counting commodity nodes which are purchased in a directed mode at the same time, and creating a triggered and triggered commodity node data table;
constructing a commodity node connection relation network according to the triggered and triggered commodity node data table;
deriving a set { G ] of k elements by taking commodity nodes as elements 1 ,G 2 ,G 3 ……G k The number calculation formula divided into different combinations of m subsets; k represents the total number of commodity nodes and k>0; m=1, 2, … … k; wherein each combination is referred to as a commodity node group;
statistics of the set of k elements { G 1 ,G 2 ,G 3 ……G k Total number Q of all different commodity node groups that are partitionable;
calculating the linking degree of each commodity node group in all commodity node groups;
and acquiring the commodity node group with the maximum linking degree from all the commodity node groups.
Further, the link degree propagation method based on commodity community classification further comprises the following steps:
acquiring the node with the maximum linking degree in each community in the commodity node group with the maximum linking degree, which is also called a central node of the community;
and recommending commodities corresponding to the central node of each community in the commodity node group with the maximum linking degree.
A second object of an embodiment of the present invention is to provide a link propagation system based on commodity community classification, the system including:
the system comprises a triggering and triggered commodity node data table creation module, a triggering and triggered commodity node data table creation module and a commodity node data table generation module, wherein the triggering and triggered commodity node data table creation module is used for counting commodity nodes which are purchased in a directed mode at the same time and creating a triggering and triggered commodity node data table;
the commodity node connection relation network construction module is used for constructing a commodity node connection relation network according to the triggered and triggered commodity node data table;
a commodity node group number calculation formula derivation module for deriving k element sets { G }, with commodity nodes as elements 1 ,G 2 ,G 3 ……G k The number calculation formula divided into different combinations of m subsets; k represents the total number of commodity nodes and k>0; m=1, 2, … … k; wherein each combination is referred to as a commodity node group;
a commodity node group total number statistics module for counting k element sets { G }, and 1 ,G 2 ,G 3 ……G k total number Q of all different commodity node groups that are partitionable;
the commodity node group link degree calculating device is used for calculating the link degree of each commodity node group in all commodity node groups;
and the product node group acquisition module with the maximum linking degree is used for acquiring the product node group with the maximum linking degree from all product node groups.
Further, the link propagation system based on commodity community classification further comprises:
the community center node acquisition module is used for acquiring the node with the largest linking degree in each community in the commodity node group with the largest linking degree, and the node is also called a center node of the community;
and the commodity recommending module is used for recommending commodities corresponding to the central node of each community in the commodity node group with the maximum linking degree.
A third object of an embodiment of the present invention is to provide an apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the link propagation method based on community classification of goods when the computer program is executed.
The beneficial effects of the invention are that
The method calculates and acquires commodity node groups with the maximum linkage degree by carrying out group division on commodity nodes; finding out the node with the maximum linking degree in the commodity node group with the maximum linking degree for recommendation; according to the method, in dimension, the recommendation based on collaborative filtering is subjected to dimension lifting, namely, point recommendation is lifted to be surface recommendation, so that the problem that the point is optimal and the surface is not considered is solved; in terms of precision, the method for effectively dividing the ideal propagation communities of the relational network is found, the problem that the traditional relational network does not consider the local distribution aggregation condition of the whole group, does not divide communities or cannot find the optimal community division scale, so that the propagation center points of the whole group are found too coarsely to cause local distortion is solved, the propagation effect of the multi-element center 1+1>2 is achieved, the local optimum of 'face' accurate delivery is realized, the sum of the local optimum is integrated into the optimal propagation link of the whole group, and further higher-quality accurate delivery is realized, so that the delivery efficiency is truly and effectively improved.
Drawings
FIG. 1 is a flowchart of a method for link propagation based on commodity community classification provided by an embodiment of the present invention;
FIG. 2 is a flowchart of a method for calculating a degree of linkage for each group of product nodes according to an embodiment of the present invention;
FIG. 3 shows a commodity node G according to an embodiment of the present invention 1 、G 2 、G 3 、G 4 、G 5 A connection relation network diagram of (1);
FIG. 4 is a network diagram showing the connection relationship of commodity nodes in a commodity node group with the maximum degree of linkage according to the present invention;
FIG. 5 is a block diagram of a link propagation system based on community classification of goods, provided by an embodiment of the invention;
FIG. 6 is a block diagram of a device for calculating the degree of linkage of a group of product nodes according to an embodiment of the present invention;
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples, and only the portions related to the examples of the present invention are shown for convenience of description. It is to be understood that the specific embodiments described herein are for illustrative purposes only and are not limiting, as other equivalent embodiments according to the present invention may be made by those of ordinary skill in the relevant art without departing from the inventive concepts herein.
The method calculates and acquires commodity node groups with the maximum linkage degree by carrying out group division on commodity nodes; finding out the node with the maximum linking degree in the commodity node group with the maximum linking degree for recommendation; according to the method, in dimension, the recommendation based on collaborative filtering is subjected to dimension lifting, namely, point recommendation is lifted to be surface recommendation, so that the problem that the point is optimal and the surface is not considered is solved; in terms of precision, the method for effectively dividing the ideal propagation communities of the relational network is found, the problem that the traditional relational network does not consider the local distribution aggregation condition of the whole group, does not divide communities or cannot find the optimal community division scale, so that the propagation center points of the whole group are found too coarsely to cause local distortion is solved, the propagation effect of the multi-element center 1+1>2 is achieved, the local optimum of 'face' accurate delivery is realized, the sum of the local optimum is integrated into the optimal propagation link of the whole group, and further higher-quality accurate delivery is realized, so that the delivery efficiency is truly and effectively improved.
FIG. 1 is a flowchart of a method for link propagation based on commodity community classification provided by an embodiment of the present invention; the method comprises the following steps:
step1, counting commodity nodes purchased in a directed mode at the same time, and creating a triggered and triggered commodity node data table;
the trigger and triggered commodity node data table comprises the fields: triggering commodity nodes and triggered commodity nodes;
in the embodiment of the invention, the set G= { G is used on the assumption that k commodity nodes are in total 1 ，G 2 ，…G k -representation;
in the embodiment of the invention, the commodity node is a specific commodity; for example, if the commodity platform is a shopping platform such as a commercial brand, an electronic commercial brand and the like, the commodity node can be a commodity of unified instant noodles or a commodity of Yibao mineral water; if the commodity platform is a video or information stream watching platform, the commodity node can be a specific short video or news information; purchase may also represent click, like, selected, collected, added shopping cart, and the like; those skilled in the art will appreciate that it is not intended to limit the scope of the present invention.
| Triggering commodity node | Triggered commodity node |
| G 1 | G 2 |
| G 3 | G 1 |
| G 4 | G 3 |
| G 9 | G 5 |
| G 6 | G 2 |
| … | … |
TABLE 1
Step2, constructing a commodity node connection relation network according to the triggered and triggered commodity node data table;
the method comprises the following steps: the commodity is taken as a node, the connection relation among the commodities is taken as an edge, the frequency of directional simultaneous purchase among the commodities is taken as an edge weight, and a commodity connection relation network is constructed;
if commodity node G i And G j The commodity node G has a directed simultaneous purchase triggering relationship (direct connection relationship) i And G j A connecting edge is added between the two connecting edges; commodity node G i And G j There may also be an indirect connection between the two, connected by a path comprising at least 1 intermediate node and at least 2 connecting edges, at least one of the number of paths;
step3, deriving a set { G ] of k elements by taking commodity nodes as elements 1 ,G 2 ,G 3 ……G k The number of different combinations of m subsets can be divided into a number of formulas (i.e., set { G } 1 ,G 2 ,G 3 ……G k How many different combinations }) may be partitioned into; k represents the total number of commodity nodes and k>0; m=1, 2, … … k; wherein each combination is referred to as a commodity node group, and each subset within the commodity node group is referred to as a community of the commodity node group;
a set of k elements { G 1 ,G 2 ,G 3 ……G k The number of different combinations that can be divided into m subsets is calculated as: t (k, m) =t (k-1, m-1) +mxt (k-1, m);
where T (k, m) represents a set { G ] of k elements 1 ,G 2 ,G 3 ……G k The number of different combinations consisting of m subsets;
the calculation formula derivation method of T (k, m) is as follows:
when the number of product nodes k=1, it can be divided into:
(A1) The commodity node group consisting of m=1 subsets is: { G 1 }}；T(1,1)＝1；
When the number of product nodes k=2, it can be divided into:
(B1) The commodity node group consisting of m=1 subsets is: { G 1 ,G 2 }}；T(2,1)＝1；
(B2) The commodity node group consisting of m=2 subsets is: { G 1 },{G 2 }}；T(2,2)＝1；
When the number of product nodes k=3, it can be divided into:
(C1) The commodity node group consisting of m=1 subsets is: { G 1 ,G 2 ,G 3 }}；T(3,1)＝1；
(C2) The commodity node group consisting of m=2 subsets is 3, respectively: { G 1 ,G 2 },{G 3 }}，{{G 1 },{G 2 ,G 3 }}，{{G 1 ,G 3 },{G 2 }}；T(3,2)＝3；
(C3) The commodity node group consisting of m=3 subsets is: { G 1 },{G 2 },{G 3 }}；T(3,3)＝1；
For example, when k=3, m=2, it can be divided into T (3, 2) =3 commodity node groups, { { G 1 ,G 2 },{G 3 One commodity node group, which contains 2 communities: { G 1 ,G 2 Sum { G } 3 }；
If statistics of T (4, 2) is required, the steps are:
adding an element G to (C1) 4 The method comprises the following steps: { G 1 ,G 2 ,G 3 },{G 4 }}；
Adding an element G to any subset of (C2) 4 The method comprises the following steps: { G 1 ,G 2 ,G 4 },{G 3 }}，{{G 1 ,G 2 },{G 3 ,G 4 }}，{{G 1 ,G 4 },{G 2 ,G 3 }}，{{G 1 },{G 2 ,G 3 ,G 4 }}，{{G 1 ,G 3 ,G 4 },{G 2 }}，{{G 1 ,G 3 },{G 2 ,G 4 }}；
T(4,2)＝7；
The formula is: t (4, 2) =t (3, 1) +2×t (3, 2) =1+2×3=7;
by analogy, T (4, 3) =t (3, 2) +3×t (3, 3) =3+3×1=6;
and (3) pushing: t (k, m) =t (k-1, m-1) +mxt (k-1, m);
step4, counting the set { G ] of k elements 1 ,G 2 ,G 3 ……G k Total number Q of all different commodity node groups that are partitionable;
the calculation formula is as follows:
for example, if the total number of commodity nodes k=4, then
Step5, calculating the linking degree of each commodity node group in all commodity node groups;
fig. 2 is a flowchart of a method for calculating a link degree of each product node group according to an embodiment of the present invention, including the following steps:
s51, calculating the link degree P (i) of each node in each community contained in each commodity node group;
P(i)＝N b (i)+M b (i)；
wherein i, j represents a commodity node elementElement in set { G 1 ,G 2 ,G 3 ……G k Sequence number in }; i, j e {1,2,3, …, k }; p (i) represents a commodity node G i Chain length, N b (i) Representing commodity node G i Is a primary degree of linkage; commodity node G i Is one-level chain degree N b (i) Is a commodity node G in the commodity connection relation network i The sum of edge weights of the directly connected edges; m is M b (i) Representing commodity node G i Is a network location of (2); lev (Lev) ij Representation and commodity node G i Directly or indirectly connected commodity node G j Is a node level of (2); (R) i ) j Representation and commodity node G i Directly or indirectly connected node G j The frequency of total associated purchases of corresponding commodities, k representing the number of commodity nodes;
as shown in FIG. 3, the commodity node G according to the embodiment of the present invention 1 、G 2 、G 3 、G 4 、G 5 A connection relation network diagram of (1);
wherein G is 1 And G 2 If there is a direct connection relationship, G 2 Is G 1 Is a level 1 node of (2);
G 1 and G 3 An indirect connection relationship exists, and the first node path and the second node path can be indirectly connected; the first node path includes 2 connection edges: g 1 -G 2 And G 2 -G 3 The method comprises the steps of carrying out a first treatment on the surface of the The second node path includes 4 connection edges: g 1 -G 2 、G 2 -G 4 、G 4 -G 5 And G 5 -G 3 The method comprises the steps of carrying out a first treatment on the surface of the Then G 3 Is G 1 Is a level 2 node of (2);
the value on the connecting edge represents the edge weight (i.e., the frequency of simultaneous purchases) between two directly connected commodity nodes, such as G 1 And G 2 The edge weight of (2) is 10, G 2 And G 3 The edge weight of (2) is 5;
s52, calculating the linkage degree of each community;
the connectivity of each community is the sum of the connectivity P (i) of all nodes contained in each community;
the invention is trueIn the embodiment, a commodity node group is assumed to be: { G 1 ,G 2 ,G 3 }，{G 4 ,G 5 ,G 6 ,G 7 ，G 8 -commodity node group comprising 2 communities: first community { G 1 ,G 2 ,G 3 Second community { G } 4 ,G 5 ,G 6 ,G 7 ，G 8 -a }; then
The degree of linkage of the first community=p (1) +p (2) +p (3);
the degree of linkage of the second community = P (4) +p (5) +p (6) +p (7) +p (8);
s53, calculating the linkage degree of each commodity node group;
the link degree of each commodity node group is the sum of the link degrees of all communities contained in each commodity node group;
in the embodiment of the present invention, the commodity node group { { { G 1 ,G 2 ,G 3 }，{G 4 ,G 5 ,G 6 ,G 7 ，G 8 Linkage degree of } = linkage degree of first community + linkage degree of first community;
step6, obtaining the commodity node group with the maximum linking degree from all the commodity node groups.
The commodity node group with the chain degree plantar surface is the commodity node group which is most suitable for popularization;
further, the link degree propagation method based on commodity community classification further comprises the following steps:
step7, obtaining the node with the maximum linking degree in each community in the commodity node group with the maximum linking degree, which is also called a central node of the community;
step8, recommending commodities corresponding to the central node of each community in the commodity node group with the maximum linking degree;
FIG. 4 is a network diagram of connection relationships between commodity nodes in a commodity node group with the maximum degree of linkage according to the embodiment of the present invention;
in the embodiment of the present invention, as shown in fig. 4, it is assumed that the commodity node group with the largest degree of linkage is { { { G 1 ,G 3 ,G 6 ,G 8 },{G 2 ,G 5 ,G 12 ,G 13 },{G 4 ,G 7 ,G 9 ,G 10 ,G 11 -comprising 3 communities { G } 1 ,G 3 ,G 6 ,G 8 },{G 2 ,G 5 ,G 12 ,G 13 },{G 4 ,G 7 ,G 9 ,G 10 ,G 11 First community { G } 1 ,G 3 ,G 6 ,G 8 The central node of } is G 8 Second community { G 2 ,G 5 ,G 12 ,G 13 The central node of } is G 5 Third community { G 4 ,G 7 ,G 9 ,G 10 ,G 11 The central node of } is G 4 The method comprises the steps of carrying out a first treatment on the surface of the In practical application, the G is pushed again 8 ，G 5 ,G 4 Commodities corresponding to the 3 nodes;
in the implementation of the invention, community division is used for more efficient propagation in the area, and the community and nodes between communities may not be propagated; the high degree of linkage of the nodes in the community indicates that the nodes have high degree of propagation in the community; the high link degree of the community indicates that the community has high propagation degree in the group; a high degree of linkage of a group means that the group has high degree of linkage in all groups; through the central node of each community in the group with highest link degree, the communication is carried out to the community where each central node is located through the central node, so that efficient communication of all communities is realized.
Corresponding to the link degree propagation method based on commodity community classification described in the above embodiment, fig. 5 is a block diagram of a link degree propagation system based on commodity community classification according to the embodiment of the present invention. The system comprises:
the system comprises a triggering and triggered commodity node data table creation module, a triggering and triggered commodity node data table creation module and a commodity node data table generation module, wherein the triggering and triggered commodity node data table creation module is used for counting commodity nodes which are purchased in a directed mode at the same time and creating a triggering and triggered commodity node data table;
the trigger and triggered commodity node data table comprises the fields: triggering commodity nodes and triggered commodity nodes;
the commodity node connection relation network construction module is used for constructing a commodity node connection relation network according to the triggered and triggered commodity node data table;
the method comprises the following steps: the commodity is taken as a node, the connection relation among the commodities is taken as an edge, the frequency of directional simultaneous purchase among the commodities is taken as an edge weight, and a commodity connection relation network is constructed;
a commodity node group number calculation formula derivation module for deriving k element sets { G }, with commodity nodes as elements 1 ,G 2 ,G 3 ……G k The number of different combinations of m subsets can be divided into a number of formulas (i.e., set { G } 1 ,G 2 ,G 3 ……G k How many different combinations }) may be partitioned into; k represents the total number of commodity nodes and k>0; m=1, 2, … … k; wherein each combination is referred to as a commodity node group, and each subset within the commodity node group is referred to as a community of the commodity node group;
a set of k elements { G 1 ,G 2 ,G 3 ……G k The number of different combinations that can be divided into m subsets is calculated as: t (k, m) =t (k-1, m-1) +mxt (k-1, m);
where T (k, m) represents a set { G ] of k elements 1 ,G 2 ,G 3 ……G k The number of different combinations consisting of m subsets;
a commodity node group total number statistics module for counting k element sets { G }, and 1 ,G 2 ,G 3 ……G k total number Q of all different commodity node groups that are partitionable;
the calculation formula is as follows:
the commodity node group link degree calculating device is used for calculating the link degree of each commodity node group in all commodity node groups;
the commodity node group acquisition module is used for acquiring commodity node groups with the maximum linkage degree from all commodity node groups;
further, the link degree propagation system based on commodity community classification further comprises
The community center node acquisition module is used for acquiring the node with the largest linking degree in each community in the commodity node group with the largest linking degree, and the node is also called a center node of the community;
and the commodity recommending module is used for recommending commodities corresponding to the central node of each community in the commodity node group with the maximum linking degree.
Further, a set of k elements { G 1 ,G 2 ,G 3 ……G k The number of different combinations that can be divided into m subsets is calculated as: t (k, m) =t (k-1, m-1) +mxt (k-1, m);
where T (k, m) represents a set { G ] of k elements 1 ,G 2 ,G 3 ……G k The number of different combinations consisting of m subsets;
the calculation formula derivation method of T (k, m) is as follows:
when the number of product nodes k=1, it can be divided into:
(A1) The commodity node group consisting of m=1 subsets is: { G 1 }}；T(1,1)＝1；
When the number of product nodes k=2, it can be divided into:
(B1) The commodity node group consisting of m=1 subsets is: { G 1 ,G 2 }}；T(2,1)＝1；
(B2) The commodity node group consisting of m=2 subsets is: { G 1 },{G 2 }}；T(2,2)＝1；
When the number of product nodes k=3, it can be divided into:
(C1) The commodity node group consisting of m=1 subsets is: { G 1 ,G 2 ,G 3 }}；T(3,1)＝1；
(C2) The commodity node group consisting of m=2 subsets is 3, respectively: { G 1 ,G 2 },{G 3 }}，{{G 1 },{G 2 ,G 3 }}，{{G 1 ,G 3 },{G 2 }}；T(3,2)＝3；
(C3) The commodity node group consisting of m=3 subsets is: { G 1 },{G 2 },{G 3 }}；T(3,3)＝1；
For example, when k=3, m=2, it can be divided into T (3, 2) =3 commodity node groups, { { G 1 ,G 2 },{G 3 One commodity node group, which contains 2 communities: { G 1 ,G 2 Sum { G } 3 }；
If statistics of T (4, 2) is required, the steps are:
adding an element G to (C1) 4 The method comprises the following steps: { G 1 ,G 2 ,G 3 },{G 4 }}；
Adding an element G to any subset of (C2) 4 The method comprises the following steps: { G 1 ,G 2 ,G 4 },{G 3 }}，{{G 1 ,G 2 },{G 3 ,G 4 }}，{{G 1 ,G 4 },{G 2 ,G 3 }}，{{G 1 },{G 2 ,G 3 ,G 4 }}，{{G 1 ,G 3 ,G 4 },{G 2 }}，{{G 1 ,G 3 },{G 2 ,G 4 }}；
T(4,2)＝7；
The formula is: t (4, 2) =t (3, 1) +2×t (3, 2) =1+2×3=7;
by analogy, T (4, 3) =t (3, 2) +3×t (3, 3) =3+3×1=6;
and (3) pushing: t (k, m) =t (k-1, m-1) +mxt (k-1, m);
further, fig. 6 is a block diagram of a commercial node group link degree calculating device according to an embodiment of the present invention; the commodity node group link degree calculating device comprises:
the node link degree calculation module is used for calculating the link degree P (i) of each node in each community contained in each commodity node group;
P(i)＝N b (i)+M b (i)；
where i, j represents the commodity node element in the set { G } 1 ,G 2 ,G 3 ……G k Sequence number in }; i, j e {1,2,3, …, k }; p (i) represents a commodity node G i Chain length, N b (i) Representing commodity node G i Is a primary degree of linkage; commodity node G i Is one-level chain degree N b (i) Is a commodity node G in the commodity connection relation network i The sum of edge weights of the directly connected edges; m is M b (i) Representing commodity node G i Is a network location of (2); lev (Lev) ij Representation and commodity node G i Directly or indirectly connected commodity node G j Is a node level of (2); (R) i ) j Representation and commodity node G i Directly or indirectly connected node G j The frequency of total associated purchases of corresponding commodities, k representing the number of commodity nodes;
the community linkage calculation module is used for calculating the linkage P (i) of each community;
the connectivity of each community is the sum of the connectivity P (i) of all nodes contained in each community;
the commodity node group counting link degree calculating module is used for calculating the link degree of each commodity node group;
the link degree of each product node group is the sum of the link degrees of all communities included in each product node group.
The embodiment of the invention also provides a terminal device, which comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor. The steps in the above-mentioned link degree propagation method embodiment based on commodity community classification are implemented when the processor executes the computer program. Alternatively, the processor may implement the functions of the units in the above-described system embodiments when executing the computer program.
It will be appreciated by those of ordinary skill in the art that implementing all or part of the steps of the methods of the embodiments described above may be accomplished by program instruction related hardware, and the program may be stored on a computer readable storage medium, which may be a ROM, a RAM, a magnetic disk, an optical disk, etc.
The sequence numbers of the steps in the above embodiments do not mean the execution sequence, and the execution sequence of the processes should be determined according to the functions and internal logic, and should not limit the implementation process of the embodiments of the present invention.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (3)
1. A method of link propagation based on community classification of goods, the method comprising:
counting commodity nodes which are purchased in a directed mode at the same time, and creating a triggered and triggered commodity node data table;
constructing a commodity node connection relation network according to the triggered and triggered commodity node data table;
deriving a set { G ] of k elements by taking commodity nodes as elements 1 ,G 2 ,G 3 ……G k The number calculation formula divided into different combinations of m subsets; k represents the total number of commodity nodes and k>0; m=1, 2, … … k; wherein each combination is referred to as a commodity node group;
statistics of the set of k elements { G 1 ,G 2 ,G 3 ……G k Total number Q of all different commodity node groups that are partitionable;
calculating the linking degree of each commodity node group in all commodity node groups;
acquiring the commodity node group with the maximum linking degree from all commodity node groups;
the link degree propagation method based on commodity community classification further comprises the following steps:
acquiring the node with the maximum linking degree in each community in the commodity node group with the maximum linking degree, which is also called a central node of the community;
recommending commodities corresponding to the central node of each community in the commodity node group with the maximum linking degree;
the trigger and triggered commodity node data table comprises the fields: triggering commodity nodes and triggered commodity nodes;
each subset within the commodity node group is referred to as a community of the commodity node group;
the construction of the commodity node connection relation network according to the triggered and triggered commodity node data table specifically comprises the following steps: the commodity is taken as a node, the connection relation among the commodities is taken as an edge, the frequency of directional simultaneous purchase among the commodities is taken as an edge weight, and a commodity connection relation network is constructed; if commodity node G i And G j If a directed simultaneous purchase triggering relationship exists, the commodity node G i And G j A connecting edge is added between the two connecting edges;
the set of k elements { G 1 ,G 2 ,G 3 ……G k The number of different combinations that can be divided into m subsets is calculated as: t (k, m) =t (k-1, m-1) +mxt (k-1, m);
where T (k, m) represents a set { G ] of k elements 1 ,G 2 ,G 3 ……G k The number of different combinations consisting of m subsets;
the statistics of the set of k elements { G 1 ,G 2 ,G 3 ……G k The total number Q of all the different commodity node groups which can be divided is calculated as follows:
the method for calculating the link degree of each commodity node group comprises the following steps: calculating the link degree P (i) of each node in each community contained in each commodity node group;
P(i)＝N b (i))+M b (i)；
where i, j represents the commodity node element in the set { G } 1 ,G 2 ,G 3 ……G k Sequence number in }; i, j e {1,2,3, …, k }; p (i) represents a commodity node G i Chain length, N b (i) Representing commodity node G i Is a primary degree of linkage; commodity node G i Is one-level chain degree N b (i) Is a commodity node G in the commodity connection relation network i The sum of edge weights of the directly connected edges; m is M b (i) Representing commodity node G i Is a network location of (2); lev (Lev) ij Representation and commodity node G i Directly or indirectly connected commodity node G j Is a node level of (2); (R) i ) j Representation and commodity node G i Directly or indirectly connected node G j The frequency of total associated purchases of corresponding commodities, k representing the number of commodity nodes;
calculating the linking degree of each community;
the connectivity of each community is the sum of the connectivity P (i) of all nodes contained in each community;
calculating the linking degree of each commodity node group;
the link degree of each product node group is the sum of the link degrees of all communities included in each product node group.
2. A link propagation system based on community classification of goods, the system comprising:
the system comprises a triggering and triggered commodity node data table creation module, a triggering and triggered commodity node data table creation module and a commodity node data table generation module, wherein the triggering and triggered commodity node data table creation module is used for counting commodity nodes which are purchased in a directed mode at the same time and creating a triggering and triggered commodity node data table;
the commodity node connection relation network construction module is used for constructing a commodity node connection relation network according to the triggered and triggered commodity node data table;
a commodity node group number calculation formula derivation module for deriving k element sets { G }, with commodity nodes as elements 1 ,G 2 ,G 3 ……G k The number calculation formula divided into different combinations of m subsets; k represents the total number of commodity nodes and k>0；m=1, 2, … … k; wherein each combination is referred to as a commodity node group;
a commodity node group total number statistics module for counting k element sets { G }, and 1 ,G 2 ,G 3 ……G k total number Q of all different commodity node groups that are partitionable;
the commodity node group link degree calculating device is used for calculating the link degree of each commodity node group in all commodity node groups;
the commodity node group acquisition module is used for acquiring commodity node groups with the maximum linkage degree from all commodity node groups;
the link degree propagation system based on commodity community classification further comprises:
the community center node acquisition module is used for acquiring the node with the largest linking degree in each community in the commodity node group with the largest linking degree, and the node is also called a center node of the community;
the commodity recommending module is used for recommending commodities corresponding to the central node of each community in the commodity node group with the maximum linking degree;
the trigger and triggered commodity node data table comprises the fields: triggering commodity nodes and triggered commodity nodes;
the construction of the commodity node connection relation network according to the triggered and triggered commodity node data table specifically comprises the following steps: the commodity is taken as a node, the connection relation among the commodities is taken as an edge, the frequency of directional simultaneous purchase among the commodities is taken as an edge weight, and a commodity connection relation network is constructed; if commodity node G i And G j If a directed simultaneous purchase triggering relationship exists, the commodity node G i And G j A connecting edge is added between the two connecting edges;
each subset within the commodity node group is referred to as a community of the commodity node group;
a set of k elements { G 1 ,G 2 ,G 3 ……G k The number of different combinations that can be divided into m subsets is calculated as: t (k, m) =t (k-1, m-1) +mxt (k-1, m);
wherein the method comprises the steps ofT (k, m) represents a set { G ] of k elements 1 ,G 2 ,G 3 ……G k The number of different combinations consisting of m subsets;
statistics of the set of k elements { G 1 ,G 2 ,G 3 ……G k The total number Q of all the different commodity node groups which can be divided is calculated as follows:
the commodity node group link degree calculating device comprises: the node link degree calculation module is used for calculating the link degree P (i) of each node in each community contained in each commodity node group;
P(i)＝N b (i)+M b (i)；
where i, j represents the commodity node element in the set { G } 1 ,G 2 ,G 3 ……G k Sequence number in }; i, j e {1,2,3, …, k }; p (i) represents a commodity node G i Chain length, N b (i) Representing commodity node G i Is a primary degree of linkage; commodity node G i Is one-level chain degree N b (i) Is a commodity node G in the commodity connection relation network i The sum of edge weights of the directly connected edges; m is M b (i) Representing commodity node G i Is a network location of (2); lev (Lev) ij Representation and commodity node G i Directly or indirectly connected commodity node G j Is a node level of (2); (R) i ) j Representation and commodity node G i Directly or indirectly connected node G j The frequency of total associated purchases of corresponding commodities, k representing the number of commodity nodes;
the community linkage calculation module is used for calculating linkage P (i) of each community;
the connectivity of each community is the sum of the connectivity P (i) of all nodes contained in each community;
the commodity node group counting link degree calculating module is used for calculating the link degree of each commodity node group;
the link degree of each product node group is the sum of the link degrees of all communities included in each product node group.
3. An apparatus comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the steps of the method of link propagation based on community classification of goods of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010953826.5A CN112052403B (en) | 2020-09-11 | 2020-09-11 | Commodity community classification-based link degree propagation method, system and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010953826.5A CN112052403B (en) | 2020-09-11 | 2020-09-11 | Commodity community classification-based link degree propagation method, system and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112052403A CN112052403A (en) | 2020-12-08 |
| CN112052403B true CN112052403B (en) | 2024-01-02 |
Family
ID=73611627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010953826.5A Active CN112052403B (en) | 2020-09-11 | 2020-09-11 | Commodity community classification-based link degree propagation method, system and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112052403B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112667753B (en) * | 2020-12-24 | 2023-08-18 | 平安科技（深圳）有限公司 | Method for mining physical node path and computer equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228411A (en) * | 2016-07-31 | 2016-12-14 | 江西理工大学 | A kind of method for solving of the commodity sales promotion combination analyzed based on commodity power of influence |
| CN108257036A (en) * | 2018-01-12 | 2018-07-06 | 西安电子科技大学 | Discovery method, the Web Community's system of overlapping community are extended based on seed node |
| CN110969491A (en) * | 2019-12-17 | 2020-04-07 | 深圳市梦网百科信息技术有限公司 | Commodity pushing method, system and equipment based on network path |
| CN110992153A (en) * | 2019-12-17 | 2020-04-10 | 深圳市梦网百科信息技术有限公司 | Commodity recommendation method, system and equipment based on user attributes and commodity types |
| CN111080411A (en) * | 2019-12-17 | 2020-04-28 | 深圳市梦网百科信息技术有限公司 | Commodity pushing method and system based on network centrality and terminal equipment |
-
2020
- 2020-09-11 CN CN202010953826.5A patent/CN112052403B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228411A (en) * | 2016-07-31 | 2016-12-14 | 江西理工大学 | A kind of method for solving of the commodity sales promotion combination analyzed based on commodity power of influence |
| CN108257036A (en) * | 2018-01-12 | 2018-07-06 | 西安电子科技大学 | Discovery method, the Web Community's system of overlapping community are extended based on seed node |
| CN110969491A (en) * | 2019-12-17 | 2020-04-07 | 深圳市梦网百科信息技术有限公司 | Commodity pushing method, system and equipment based on network path |
| CN110992153A (en) * | 2019-12-17 | 2020-04-10 | 深圳市梦网百科信息技术有限公司 | Commodity recommendation method, system and equipment based on user attributes and commodity types |
| CN111080411A (en) * | 2019-12-17 | 2020-04-28 | 深圳市梦网百科信息技术有限公司 | Commodity pushing method and system based on network centrality and terminal equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112052403A (en) | 2020-12-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109697629B (en) | Product data pushing method and device, storage medium and computer equipment | |
| US20190104197A1 (en) | Discovering signature of electronic social networks | |
| Santé-Riveira et al. | GIS-based planning support system for rural land-use allocation | |
| US8751618B2 (en) | Method and system for maximizing content spread in social network | |
| CN102467709A (en) | Product information sending method and device | |
| CN105159910A (en) | Information recommendation method and device | |
| CN103605714B (en) | The recognition methods of website abnormal data and device | |
| CN108090197A (en) | A kind of community discovery method of multidimensional social networks | |
| CN112085615A (en) | Method and device for training graph neural network | |
| CN112052403B (en) | Commodity community classification-based link degree propagation method, system and equipment | |
| CN103744904A (en) | Method and device for providing information | |
| Sun et al. | Evaluating user reputation of online rating systems by rating statistical patterns | |
| Ishfaq et al. | Identifying the influential nodes in complex social networks using centrality-based approach | |
| CN107741967A (en) | Method, apparatus and electronic equipment for behavioral data processing | |
| Jain et al. | Opinion leaders for information diffusion using graph neural network in online social networks | |
| CN105631732A (en) | Method and device for determining user authority | |
| CN110929172A (en) | Information selection method and device, electronic equipment and readable storage medium | |
| Khavandi et al. | Maximizing the Impact on Social Networks using the Combination of PSO and GA Algorithms | |
| CN112560105B (en) | Joint modeling method and device for protecting multi-party data privacy | |
| Pintér et al. | Analyzing the behavior and financial status of soccer fans from a mobile phone network perspective: Euro 2016, a case study | |
| MohamadiBaghmolaei et al. | Continuous states latency aware influence maximization in social networks | |
| CN110457387B (en) | Method and related device applied to user tag determination in network | |
| CN104967643A (en) | Method for acquiring transferred data, and apparatus thereof | |
| CN110992153B (en) | Commodity recommendation method, system and equipment based on user attribute and commodity type | |
| CN112053210B (en) | Commodity community classification-based association value propagation method, system and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |