CN110969491B - Commodity pushing method, system and equipment based on network path - Google Patents
Commodity pushing method, system and equipment based on network path Download PDFInfo
- Publication number
- CN110969491B CN110969491B CN201911304859.0A CN201911304859A CN110969491B CN 110969491 B CN110969491 B CN 110969491B CN 201911304859 A CN201911304859 A CN 201911304859A CN 110969491 B CN110969491 B CN 110969491B
- Authority
- CN
- China
- Prior art keywords
- commodity
- node
- frequency
- purchase
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0254—Targeted advertisements based on statistics
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Business, Economics & Management (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Probability & Statistics with Applications (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a commodity pushing method, a system and equipment based on a network path, which are implemented by calculating a commodity G i Is a network core degree of (1), a first ratio of commodity (commodity G i Related purchase frequency of commodity G i Proportion of total purchase frequency), a second proportion (commodity G i The ratio of the total frequency of purchase to the sum of the total frequency of purchase for all merchandise types); and then carrying out weighted normalization processing on the network core degree, the first proportion and the second proportion of the commodity, carrying out weighted summation on the network core degree, the first proportion and the second proportion after normalization processing to obtain the optimal network core degree of the commodity, and finally carrying out commodity recommendation on the user according to the optimal network core degree. The method of the invention considers not only the transmissibility of the commodity but also the weight and influence of the commodity, and can effectively improve the recommendation effect and the accuracy.
Description
Technical Field
The present invention relates to the field of data mining, and in particular, to a method, a system, and an apparatus for pushing commodities based on a network path.
Background
The commodity recommendation method in the prior art generally adopts collaborative filtering recommendation technology or click degree centrality technology of a relational network.
Drawbacks of collaborative filtering recommendation are: (1) it depends on recommendations; that is, the user can only purchase a certain amount of commodities (in practical application, purchase can also represent clicking, like, selected, collected, added shopping cart and other like preference selection conditions), and then can have a recommendation target, which belongs to passive recommendation. (2) The recommended merchandise only considers a single purchase (i.e., based on only one exact correlation behavior), and does not consider a secondary derivative purchase, with subsequent derivative recommendations being poor.
The defect of the centrality of the point degree of the relation network is: only the transmissibility of the commodity (whether the commodity is coupled with many other commodities) is considered, but the influence of the commodity is not considered. In practical application, when a relation network is utilized to push commodities, there are two cases, namely, the commodities are related to a plurality of commodities, but the proportion of the number of times of related simultaneous purchase of the commodities to the total number of times of purchase of the commodities is very low, for example, commodity A purchases 10 times in total, 9 times are all single purchases, and only 1 time purchases other commodities simultaneously; and secondly, although the commodity is connected with a plurality of other commodities, the commodity is low in purchase frequency, is not a popular commodity, has poor influence, is likely to be not purchased at all by a spectator, and has poor overall effect.
Disclosure of Invention
The embodiment of the invention aims to provide a commodity pushing method, a system and equipment based on a network path, and aims to solve the problem of inaccurate recommendation caused by poor follow-up derivative recommendation effect or consideration of influence and weight of commodities in the existing commodity recommendation method.
A first object of an embodiment of the present invention is to provide a commodity pushing method based on a network path, where the method includes:
counting the frequency of simultaneous purchase of commodities and creating a commodity purchase frequency matrix;
counting the individual purchase frequency and the associated purchase frequency of each commodity, and calculating the total purchase frequency of each commodity;
constructing a commodity connection relation network according to the commodity purchase frequency matrix;
calculating the network core degree of each commodity node;
calculating a first proportion and a second proportion of each commodity;
respectively carrying out normalization processing on the network core degree, the first proportion and the second proportion of the commodity nodes to obtain corresponding weighted network core degree, first weight degree and second weight degree;
carrying out weighted summation on the weighted network core degree, the first weight degree and the second weight degree to obtain the optimal network core degree of the commodity;
and recommending the commodity according to the optimal network core degree of the commodity.
Optionally, "the weighted network core degree, the first weight degree and the second weight degree are weighted and summed to obtain the optimal network core degree of the commodity," the weighted network core degree, the first weight degree and the weight of the second weight degree in the commodity recommendation decision target are calculated according to the analytic hierarchy process "the weighted network core degree, the first weight degree and the second weight degree are weighted and summed to obtain the optimal network core degree of the commodity.
A second object of an embodiment of the present invention is to provide a commodity pushing system based on a network path, where the system includes:
the commodity purchase frequency matrix creation module is used for counting the frequency of simultaneous purchase of commodities and creating a commodity purchase frequency matrix;
the commodity purchasing frequency statistics and calculation module is used for counting the independent purchasing frequency and the associated purchasing frequency of each commodity and calculating the total purchasing frequency of each commodity;
the commodity connection relation network construction module is used for constructing a commodity connection relation network according to the commodity purchase frequency matrix;
the network core degree calculating device is used for calculating the network core degree of each commodity node;
the first proportion and second proportion calculating module is used for calculating the first proportion and the second proportion of each commodity;
the first normalization processing module is used for respectively normalizing the network core degree, the first proportion and the second proportion of the commodity node to obtain corresponding weighted network core degree, first weight degree and second weight degree;
the optimal network core degree calculation module is used for carrying out weighted summation on the weighted network core degree, the first weight degree and the second weight degree to obtain the optimal network core degree of the commodity;
and the commodity pushing module is used for recommending commodities according to the optimal network core degree of the commodities.
Optionally, the best network core calculation module is replaced with a second best network core calculation module,
the second optimal network core degree calculation module is used for calculating the weights of the weighted network core degree, the first weight degree and the second weight degree in the commodity recommendation decision target according to the analytic hierarchy process, and carrying out weighted summation on the weighted network core degree, the first weight degree and the second weight degree to obtain the optimal network core degree of the commodity;
a third object of the embodiment of the present invention is to provide a terminal device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, where the processor implements the steps of the network path-based commodity pushing method when executing the computer program.
The beneficial effects of the invention are that
The embodiment of the invention provides a commodity pushing method, a system and equipment based on a network path, which are implemented by calculating a commodity G i Is a network core degree of (1), a first ratio of commodity (commodity G i Related purchase frequency of commodity G i Proportion of total purchase frequency), a second proportion (commodity G i The ratio of the total frequency of purchase to the sum of the total frequency of purchase for all merchandise types); and then carrying out weighted normalization processing on the network core degree, the first proportion and the second proportion of the commodity, carrying out weighted summation on the network core degree, the first proportion and the second proportion after normalization processing to obtain the optimal network core degree of the commodity, and finally carrying out commodity recommendation on the user according to the optimal network core degree. The method of the invention considers not only the transmissibility of the commodity but also the weight and influence of the commodity, and can effectively improve the recommendation effect and the accuracy.
Drawings
FIG. 1 is a flow chart of a commodity pushing method based on a network path provided by an embodiment of the present invention;
fig. 2 is a flowchart of a method for calculating core degree of a commodity node network according to an embodiment of the present invention;
FIG. 3 is 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 diagram of a commodity pushing system based on a network path according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a core computing device of a commodity node network 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 should be understood that the particular embodiments described herein are illustrative only and are not intended to limit the invention.
The embodiment of the invention provides a commodity pushing method, a system and equipment based on a network path, which are implemented by calculating a commodity G i Is a network core degree of (1), a first ratio of commodity (commodity G i Related purchase frequency of commodity G i Proportion of total purchase frequency), a second proportion (commodity G i The ratio of the total frequency of purchase to the sum of the total frequency of purchase for all merchandise types); and then carrying out weighted normalization processing on the network core degree, the first proportion and the second proportion of the commodity, carrying out weighted summation on the network core degree, the first proportion and the second proportion after normalization processing to obtain the optimal network core degree of the commodity, and finally carrying out commodity recommendation on the user according to the optimal network core degree. The method of the invention considers not only the transmissibility of the commodity but also the weight and influence of the commodity, and can effectively improve the recommendation effect and the accuracy.
FIG. 1 is a flow chart of a commodity pushing method based on a network path provided by an embodiment of the present invention; the method comprises the following steps:
s1, counting the frequency of simultaneous purchase of commodities and creating a commodity purchase frequency matrix T11;
in the embodiment of the invention, the commodity platform is assumed to have n commodities in total, corresponding to n commodity nodes, and the set G= { G is used 1 ，G 2 ，…G n -representation; commodity G i And G j The frequency of simultaneous purchase is represented by an n x n matrix t11= { (R) 3 ) ij -representation; (R) 3 ) ij The value of the value indicates that the commodity G is purchased simultaneously i And G j Frequency of (3);
the product G is purchased simultaneously i And G j Frequency = purchase of good G i Time triggered purchase of commodity G j Frequency of purchase of goods G j Time triggered purchase of commodity G i ；
In practical application, the purchase can also represent clicking, liking, selected, collected, added shopping cart and the like liking selection conditions; those skilled in the art will appreciate that it is not intended to limit the scope of the present invention;
the data table of the commodity purchase frequency matrix T11 is shown in the table 1;
TABLE 1
S2, counting the individual purchase frequency and the associated purchase frequency of each commodity, and calculating the total purchase frequency of each commodity;
commodity G i Frequency of individual purchase of (R) 2 ) i : purchase of only a single commodity G i Frequency of (3);
commodity G i Related purchase frequency (R) 4 ) i : the purchased commodity comprises commodity G i Frequency of (i.e. commodity G) i The frequency of simultaneous purchases with all other items,
commodity G i Total frequency of purchase (R) 5 ) i Commodity G i Frequency of individual purchase of (R) 2 ) i + commodity G i Related purchase frequency of (R4) i ；
The data table of the individual purchase frequency, the associated purchase frequency and the total purchase frequency of the commodity according to the embodiment of the present invention is shown in table 2;
TABLE 2
S3, constructing a commodity connection relation network according to the commodity purchase frequency matrix T11;
the method comprises the following steps: the commodity is taken as a node, the connection relation between commodities is taken as an edge, the frequency of simultaneous purchase between 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 is in a 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;
s4, calculating the network core degree D of each commodity node 1 (i)；
Fig. 2 is a flowchart of a method for calculating core degree of a commodity node network according to an embodiment of the present invention; the method comprises the following steps:
s401, for commodity node G with direct or indirect connection i And G j Obtaining commodity node G j Opposite node G i Node level lev of (a);
set G i As the original node, if the commodity node G i And G j If there is a direct connection relationship, node G j Is G i Is a level 1 node of (2);
if commodity node G i And G j There is indirect connection relation and connected by m node paths, m is more than or equal to 1, and p= { path is used for m node path collection 1 ，path 2 ，…G m -representation; the number of connecting edges correspondingly contained in each node path in P is S= { side 1 ，side 2 ，…side m Indicated, node G j Opposite node G i Node level lev=min (S), min (S) > 2, min () represents taking the minimum value;
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 2And (3) connecting 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;
s402, calculating the network position F of each commodity node b (i)；
Wherein F is 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) 5 ) j Representing commodity G j G, total frequency of purchase of j With commodity node G i A direct or indirect connection; n represents the total number of commodity nodes;
in the embodiment of the invention, with commodity G 2 The number of the connected 1-level nodes is 3G 1 ，G 3 ,G 4 The respective total purchase frequencies were: 10,20,400; and G 2 The number of the 2-level nodes connected is G 5 The total purchase frequency is 100, F b (2)＝10+20+400+100×0.25；
S403, calculating the network core degree D of each commodity node 1 (i)；
S5, calculating a first proportion W of each commodity 1 (i) Second proportion V 1 (i)；
Wherein W is 1 (i) Representing a first proportion of the products, i.e. product G i Related purchase frequency of commodity G i A ratio of total purchase frequency of (2);
wherein V is 1 (i) Representing commodity G i Is a second ratio of commodity G i The total frequency of purchase of the commodity accounts for the sum of the total frequency of purchase of all commodity types;
s6, respectively setting the network core degree D of the commodity nodes 1 (i) First ratio W 1 (i) Second proportion V 1 (i) Normalization processing is carried out to obtain the corresponding weighted network core degree D 2 (i) First weight W 2 (i) Second weight V 2 (i)；
The normalized calculation formula is:
wherein F represents the normalized numerical value; r respectively represents the network core degree, the first proportion and the second proportion of a certain commodity; min represents the minimum numerical value in the network core degree, the first proportion and the second proportion data of all commodities respectively; max respectively represents the maximum numerical value in network core degree, first proportion and second proportion data of all commodities;
for example, if F represents the network core after normalization, R represents the commodity node G i Network core degree D of (2) 1 (i) Min represents the network core set { D of all commodity nodes 1 (i) Minimum value in i=1, 2,3 … … n }, max represents the network core set { D for all commodity nodes 1 (i) I=maximum of 1,2,3 … … n. Others and so on;
s7, weighting the network core degree D 2 (i) First weight W 2 (i) Second weight V 2 (i) Carrying out weighted summation to obtain the optimal network core degree S (i) of the commodity;
S(i)＝(D 2 (i)+W 2 (i)+V 2 (i))/3。
alternatively, the process may be carried out in a single-stage,
calculating the core degree D of a weighted network according to an analytic hierarchy process 2 (i) First weight W 2 (i) Second weight V 2 (i) Weights in commodity recommendation decision targets weight network core degree D 2 (i) First weight W 2 (i) Second weight V 2 (i) Carrying out weighted summation to obtain the optimal network core degree S (i) of the commodity;
S(i)＝α 1 D 2 (i)+α 2 W 2 (i)+α 3 V 2 (i)
wherein alpha is 1 、α 2 、α 3 Respectively represent D 2 (i)、W 2 (i)、V 2 (i) Weights in the commodity recommendation decision target;
specifically, commodity recommendation is taken as a decision target, and the weighted network core degree D is taken as 2 (i) First weight W 2 (i) Second weight V 2 (i) As a judgment matrix element in the analytic hierarchy process, carrying out pairwise comparison evaluation on the importance degree of the element; the analytic hierarchy process is a conventional process and is further described herein;
in the application scene, judging according to specific business; specific evaluation filling of the judgment model is assumed to be shown in table 3;
TABLE 3 Table 3
Weighted network core degree D calculated according to analytic hierarchy process 2 (i) First weight W 2 (i) Second weight V 2 (i) The weights are respectively as follows: 0.654,0.258,0.088;
the optimal node degree S (i) of the commodity is:
S(i)＝0.654D 2 (i)+0.258W 2 (i)+0.088V 2 (i)；
and S8, recommending the commodity according to the optimal network core degree of the commodity.
Specifically, in the embodiment, sorting the commodities according to the size of the optimal network core degree of the commodities, and selecting the commodities with the large optimal network core degree value for pushing preferentially;
corresponding to the above-mentioned commodity pushing method based on the network path, fig. 4 is a diagram of a commodity pushing system based on the network path according to the embodiment of the present invention; the system comprises:
the commodity purchase frequency matrix creation module is used for counting the frequency of simultaneous purchase of commodities and creating a commodity purchase frequency matrix T11;
the commodity purchasing frequency statistics and calculation module is used for counting the independent purchasing frequency and the associated purchasing frequency of each commodity and calculating the total purchasing frequency of each commodity;
the commodity connection relation network construction module is used for constructing a commodity connection relation network according to the commodity purchase frequency matrix T11;
network core degree calculating device for calculating network core degree D of each commodity node 1 (i)；
A first proportion and a second proportion calculating module for calculating a first proportion W of each commodity 1 (i) Second proportion V 1 (i)；
A first normalization processing module for respectively processing network core degree D of commodity nodes 1 (i) First ratio W 1 (i) Second proportion V 1 (i) Normalization processing is carried out to obtain the corresponding weighted network core degree D 2 (i) First weight W 2 (i) Second weight V 2 (i)；
An optimal network core degree calculation module for calculating the weighted network core degree D 2 (i) First weight W 2 (i) Second weight V 2 (i) Carrying out weighted summation to obtain the optimal network core degree S (i) of the commodity;
and the commodity pushing module is used for recommending commodities according to the optimal network core degree of the commodities.
Further, the best network core calculation module is replaced with a second best network core calculation module,
the second optimal network core degree calculation module is used for calculating the weights of the weighted network core degree, the first weight degree and the second weight degree in the commodity recommendation decision target according to the analytic hierarchy process, and carrying out weighted summation on the weighted network core degree, the first weight degree and the second weight degree to obtain the optimal network core degree of the commodity;
specifically, in the embodiment of the invention, the commodity platform is assumed to have n commodities in total, corresponding to n commodity nodes, and the set g= { G is used 1 ，G 2 ，…G n -representation; commodity G i And G j The frequency of simultaneous purchase is represented by an n x n matrix t11= { (R) 3 ) ij -representation; (R) 3 ) ij The value of the value indicates that the commodity G is purchased simultaneously i And G j Frequency of (3);
in practical application, the purchase can also represent clicking, liking, selected, collected, added shopping cart and the like liking selection conditions; those skilled in the art will appreciate that it is not intended to limit the scope of the present invention;
the product G is purchased simultaneously i And G j Frequency = purchase of good G i Time triggered purchase of commodity G j Frequency of purchase of goods G j Time triggered purchase of commodity G i ；
In the embodiment of the invention, commodity G i Frequency of individual purchase of (R) 2 ) i : purchase of only a single commodity G i Frequency of (3);
commodity G i Related purchase frequency (R) 4 ) i : the purchased commodity comprises commodity G i Frequency of (i.e. commodity G) i The frequency of simultaneous purchases with all other items,
commodity G i Total frequency of purchase (R) 5 ) i Commodity G i Frequency of individual purchase of (R) 2 ) i + commodity G i Related purchase frequency (R) 4 ) i ；
In the embodiment of the invention, a commodity connection relation network is constructed according to the commodity purchase frequency matrix T11;
the method comprises the following steps: the commodity is taken as a node, the connection relation between commodities is taken as an edge, the frequency of simultaneous purchase between 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 is in a 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;
further, fig. 5 is a schematic diagram of a core computing device of a commodity node network according to an embodiment of the present invention. The device comprises:
a node grade acquisition module for acquiring commodity node G with direct or indirect connection i And G j Obtaining commodity node G j Opposite node G i Node level lev of (a);
set G i As the original node, if the commodity node G i And G j If there is a direct connection relationship, node G j Is G i Is a level 1 node of (2);
if commodity node G i And G j There is indirect connection relation and connected by m node paths, m is more than or equal to 1, and p= { path is used for m node path collection 1 ，path 2 ，…G m -representation; the number of connecting edges correspondingly contained in each node path in P is S= { side 1 ，side 2 ，…side m Indicated, node G j Opposite node G i Node level lev=min (S), min (S) > 2, min () represents taking the minimum value;
the network position calculating module is used for calculating the network position F of each commodity node b (i)；
Wherein F is 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) 5 ) j Representing commodity G j G, total frequency of purchase of j With commodity node G i A direct or indirect connection; n represents the total number of commodity nodes;
the network core degree calculation module is used for calculating the network core degree D of each commodity node 1 (i)；
Further, the first ratio calculation formula is:
wherein W is 1 (i) Representing a first proportion of the products, i.e. product G i Related purchase frequency of commodity G i A ratio of total purchase frequency of (2);
the second ratio calculation formula is:
wherein V is 1 (i) Representing commodity G i Is a second ratio of commodity G i The total frequency of purchase of the commodity accounts for the sum of the total frequency of purchase of all commodity types;
further, the network core degree D of the commodity nodes is respectively calculated 1 (i) First ratio W 1 (i) Second proportion V 1 (i) The normalization process is carried out, the processing is carried out,
the normalized calculation formula is:
wherein F represents the normalized numerical value; r respectively represents the network core degree, the first proportion and the second proportion of a certain commodity; min represents the minimum numerical value in the network core degree, the first proportion and the second proportion data of all commodities respectively; max respectively represents the maximum numerical value in network core degree, first proportion and second proportion data of all commodities;
further, the weighted network core degree D 2 (i) First weight W 2 (i) Second weight V 2 (i) Carrying out weighted summation to obtain the optimal network core degree S (i) of the commodity;
the calculation formula of S (i) is as follows:
S(i)＝(D 2 (i)+W 2 (i)+V 2 (i))/3。
further, in the second optimal network core degree calculating module, the optimal network core degree S (i) of the commodity;
S(i)＝α 1 D 2 (i)+α 2 W 2 (i)+α 3 V 2 (i)
wherein alpha is 1 、α 2 、α 3 Respectively represent D 2 (i)、W 2 (i)、V 2 (i) Weights in the commodity recommendation decision target;
specifically, commodity recommendation is taken as a decision target, and the weighted network core degree D is taken as 2 (i) First weight W 2 (i) Second weight V 2 (i) As a judgment matrix element in the analytic hierarchy process, carrying out pairwise comparison evaluation on the importance degree of the element; the analytic hierarchy process is a conventional process and is further described herein;
in the application scene, judging according to specific business; specific evaluation filling of the judgment model is assumed to be shown in table 3;
TABLE 3 Table 3
Weighted network core degree D calculated according to analytic hierarchy process 2 (i) First weight W 2 (i) Second weight V 2 (i) The weights are respectively as follows: 0.654,0.258,0.088;
the optimal node degree S (i) of the commodity is:
S(i)＝0.654D 2 (i)+0.258W 2 (i)+0.088V 2 (i)；
further, the recommending the commodity according to the optimal network core degree of the commodity specifically comprises the following steps:
sorting the commodities according to the optimal network core degree of the commodities, and selecting the commodities with the optimal network core degree value to push preferentially;
the embodiment of the invention also provides a terminal device, which comprises a memory, a processor and a computer program stored in the memory and capable of being run by the processor, wherein the processor realizes the steps S1-S9 of the commodity pushing method based on the network path 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 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 (13)
1. A method for pushing goods based on a network path, the method comprising:
counting the frequency of simultaneous purchase of commodities and creating a commodity purchase frequency matrix;
counting the individual purchase frequency and the associated purchase frequency of each commodity, and calculating the total purchase frequency of each commodity;
constructing a commodity connection relation network according to the commodity purchase frequency matrix:
the commodity is taken as a node, the connection relation between commodities is taken as an edge, the frequency of simultaneous purchase between 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 simultaneous purchase triggering relationship, which is also called a direct connection relationship i And G j A connecting edge is added between the two connecting edges; if commodity node G i And G j An indirect connection relationship exists, and the connection is formed by paths comprising at least 1 intermediate node and at least 2 connection edges, wherein the number of the paths is at least one;
calculating the network core degree of each commodity node:
for commodity nodes G with direct or indirect connection i And G j Obtaining commodity node G j Opposite node G i Node level lev of (a);
set G i As the original node, if the commodity node G i And G j If there is a direct connection relationship, node G j Is G i Is a level 1 node of (2); if commodity node G i And G j There is indirect connection relation and connected by m node paths, m is more than or equal to 1, and p= { path is used for m node path collection 1 ，path 2 ，…G m -representation; the number of connecting edges correspondingly contained in each node path in P is S= { side 1 ，side 2 ，…side m Indicated, node G j Opposite node G i Node level lev=min (S), min (S) > 2, min () represents taking the minimum value;
calculating the network position F of each commodity node b (i)；
Wherein F is 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) 5 ) j Representing commodity G j G, total frequency of purchase of j With commodity node G i A direct or indirect connection; n represents the total number of commodity nodes;
calculating network core degree D of each commodity node 1 (i)；
Calculating a first proportion and a second proportion of each commodity; wherein the first proportion is commodity G i Related purchase frequency of commodity G i The second proportion is the proportion of the total purchase frequency of the commodity G i The total frequency of purchase of the commodity accounts for the sum of the total frequency of purchase of all commodity types;
respectively carrying out normalization processing on the network core degree, the first proportion and the second proportion of the commodity nodes to obtain corresponding weighted network core degree, first weight degree and second weight degree:
the normalized calculation formula is:
wherein F represents the normalized numerical value; r respectively represents the network core degree, the first proportion and the second proportion of a certain commodity; min represents the minimum numerical value in the network core degree, the first proportion and the second proportion data of all commodities respectively; max respectively represents the maximum numerical value in network core degree, first proportion and second proportion data of all commodities;
carrying out weighted summation on the weighted network core degree, the first weight degree and the second weight degree to obtain the optimal network core degree of the commodity;
and recommending the commodity according to the optimal network core degree of the commodity.
2. The method for pushing commodities according to claim 1, wherein said counting individual purchase frequency, associated purchase frequency of each commodity and calculating total purchase frequency of each commodity,
commodity G i Frequency of individual purchase of (R) 2 ) i : purchasing only a single merchantProduct G i Frequency of (3);
commodity G i Related purchase frequency (R) 4 ) i : the purchased commodity comprises commodity G i Frequency of (i.e. commodity G) i The frequency of simultaneous purchases with all other items,(R 3 ) ij the value of the value indicates that the commodity G is purchased simultaneously i And G j Frequency of (3);
commodity G i Total frequency of purchase (R) 5 ) i Commodity G i Frequency of individual purchase of (R) 2 ) i + commodity G i Related purchase frequency of (R4) i 。
3. The commodity transportation method according to claim 2, wherein,
the first proportional calculation formula is:
wherein W is 1 (i) A first scale representing the commodity;
the second ratio calculation formula is:
wherein V is 1 (i) Representing commodity G i Is a second ratio of (2).
4. The commodity transportation method according to claim 3, wherein,
the calculation formula of the optimal network core degree S (i) is as follows:
S(i)＝(D 2 (i)+W 2 (i)+V 2 (i))/3；
wherein S (i) represents the optimal network core of the commodity; d (D) 2 (i)、W 2 (i)、V 2 (i) Respectively represents normalizing the network core degree, the first proportion and the second proportion of the commodityAnd (3) obtaining the corresponding weighted network core degree, the first weight degree and the second weight degree.
5. The method for pushing commodity in a network path according to claim 1,
the method comprises the steps of carrying out weighted summation on the weighted network core degree, the first weight degree and the second weight degree to obtain the optimal network core degree of the commodity, replacing the weighted network core degree, the first weight degree and the weight of the second weight degree in a commodity recommendation decision target according to a hierarchical analysis method, and carrying out weighted summation on the weighted network core degree, the first weight degree and the second weight degree to obtain the optimal network core degree of the commodity.
6. The method for pushing commodity according to claim 5, wherein,
the calculation formula of the optimal network core degree S (i) is as follows: s (i) =α 1 D 2 (i)+α 2 W 2 (i)+α 3 V 2 (i)
Wherein alpha is 1 、α 2 、α 3 Respectively represent the weighted network core degree D 2 (i) First weight W 2 (i) Second weight V 2 (i) Weights in commodity recommendation decision targets.
7. A network path-based merchandise pushing system, the system comprising:
the commodity purchase frequency matrix creation module is used for counting the frequency of simultaneous purchase of commodities and creating a commodity purchase frequency matrix;
the commodity purchasing frequency statistics and calculation module is used for counting the independent purchasing frequency and the associated purchasing frequency of each commodity and calculating the total purchasing frequency of each commodity;
the commodity connection relation network construction module is used for constructing a commodity connection relation network according to the commodity purchase frequency matrix:
the commodity is taken as a node, the connection relation between commodities is taken as an edge, the frequency of simultaneous purchase between 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 simultaneous purchase triggering relationship, which is also called a direct connection relationship i And G j A connecting edge is added between the two connecting edges; if commodity node G i And G j An indirect connection relationship exists between the two paths, and the two paths are connected through paths comprising at least 1 intermediate node and at least 2 connection edges, wherein the number of the paths is at least one;
the network core degree calculating device is used for calculating the network core degree of each commodity node and comprises:
a node grade acquisition module for acquiring commodity node G with direct or indirect connection i And G j Obtaining commodity node G j Opposite node G i Node level lev of (a);
set G i As the original node, if the commodity node G i And G j If there is a direct connection relationship, node G j Is G i Is a level 1 node of (2);
if commodity node G i And G j There is indirect connection relation and connected by m node paths, m is more than or equal to 1, and p= { path is used for m node path collection 1 ，path 2 ，…G m -representation; the number of connecting edges correspondingly contained in each node path in P is S= { side 1 ，side 2 ，…side m Indicated, node G j Opposite node G i Node level lev=min (S), min (S) > 2, min () represents taking the minimum value;
the network position calculating module is used for calculating the network position F of each commodity node b (i)；
Wherein F is 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) 5 ) j Representation ofCommodity G j G, total frequency of purchase of j With commodity node G i A direct or indirect connection; n represents the total number of commodity nodes;
the network core degree calculation module is used for calculating the network core degree D of each commodity node 1 (i)；
The first proportion and second proportion calculating module is used for calculating the first proportion and the second proportion of each commodity; wherein the first proportion is commodity G i Related purchase frequency of commodity G i The second proportion is the proportion of the total purchase frequency of the commodity G i The total frequency of purchase of the commodity accounts for the sum of the total frequency of purchase of all commodity types;
the first normalization processing module is used for respectively carrying out normalization processing on the network core degree, the first proportion and the second proportion of the commodity node to obtain corresponding weighted network core degree, first weight degree and second weight degree:
the normalized calculation formula is:
wherein F represents the normalized numerical value; r respectively represents the network core degree, the first proportion and the second proportion of a certain commodity; min represents the minimum numerical value in the network core degree, the first proportion and the second proportion data of all commodities respectively; max respectively represents the maximum numerical value in network core degree, first proportion and second proportion data of all commodities;
the optimal network core degree calculation module is used for carrying out weighted summation on the weighted network core degree, the first weight degree and the second weight degree to obtain the optimal network core degree of the commodity;
and the commodity pushing module is used for recommending commodities according to the optimal network core degree of the commodities.
8. The network path based commodity pushing system according to claim 7, wherein said counting individual purchase frequency, associated purchase frequency of each commodity and calculating a total purchase frequency of each commodity,
simultaneous purchase of goods G i And G j Frequency = purchase of good G i Time triggered purchase of commodity G j Frequency of purchase of goods G j Time triggered purchase of commodity G i ；
Commodity G i Frequency of individual purchase of (R) 2 ) i : purchase of only a single commodity G i Frequency of (3);
commodity G i Related purchase frequency (R) 4 ) i : the purchased commodity comprises commodity G i Frequency of (i.e. commodity G) i The frequency of simultaneous purchases with all other items,
commodity G i Total frequency of purchase (R) 5 ) i Commodity G i Frequency of individual purchase of (R) 2 ) i + commodity G i Related purchase frequency (R) 4 ) i 。
9. The network path based merchandise pushing system of claim 8,
the first proportional calculation formula is:
wherein W is 1 (i) A first scale representing the commodity;
the second ratio calculation formula is:
wherein V is 1 (i) Representing commodity G i Is a second ratio of (2).
10. The network path based merchandise pushing system of claim 9,
the weighted network core degree D 2 (i) First weight W 2 (i) Second weight V 2 (i) Carrying out weighted summation to obtain the optimal network core degree S (i) of the commodity;
the calculation formula of S (i) is as follows:
S(i)＝(D 2 (i)+W 2 (i)+V 2 (i))/3；
wherein S (i) represents the optimal network core of the commodity; d (D) 2 (i)、W 2 (i)、V 2 (i) And respectively representing the network core degree, the first proportion and the second proportion of the commodity, and obtaining corresponding weighted network core degree, first weight degree and second weight degree.
11. The network path based merchandise pushing system of claim 7,
the best network core computation module is replaced with a second best network core computation module,
and the second optimal network core degree calculation module is used for calculating the weights of the weighted network core degree, the first weight degree and the second weight degree in the commodity recommendation decision target according to the analytic hierarchy process, and carrying out weighted summation on the weighted network core degree, the first weight degree and the second weight degree to obtain the optimal network core degree of the commodity.
12. The network path based merchandise pushing system of claim 11,
in the second optimal network core degree calculating module, the optimal network core degree S (i) of the commodity;
S(i)＝α 1 D 2 (i)+α 2 W 2 (i)+α 3 V 2 (i)；
wherein alpha is 1 、α 2 、α 3 Respectively represent the weighted network core degree D 2 (i) First weight W 2 (i) Second weight V 2 (i) Weights in commodity recommendation decision targets.
13. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable by the processor, the processor implementing the steps of the network path based commodity pushing method according to any one of claims 1 to 6 when the computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911304859.0A CN110969491B (en) | 2019-12-17 | 2019-12-17 | Commodity pushing method, system and equipment based on network path |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911304859.0A CN110969491B (en) | 2019-12-17 | 2019-12-17 | Commodity pushing method, system and equipment based on network path |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110969491A CN110969491A (en) | 2020-04-07 |
| CN110969491B true CN110969491B (en) | 2023-08-29 |
Family
ID=70034672
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911304859.0A Active CN110969491B (en) | 2019-12-17 | 2019-12-17 | Commodity pushing method, system and equipment based on network path |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110969491B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112052403B (en) * | 2020-09-11 | 2024-01-02 | 深圳市梦网视讯有限公司 | Commodity community classification-based link degree propagation method, system and equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106600A (en) * | 2012-11-15 | 2013-05-15 | 深圳中兴网信科技有限公司 | Commodity information push system and commodity information push method |
| CN109934654A (en) * | 2017-12-18 | 2019-06-25 | 中国移动通信集团山东有限公司 | Method of Commodity Recommendation and system |
| WO2019223379A1 (en) * | 2018-05-22 | 2019-11-28 | 阿里巴巴集团控股有限公司 | Product recommendation method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150187024A1 (en) * | 2013-12-27 | 2015-07-02 | Telefonica Digital España, S.L.U. | System and Method for Socially Aware Recommendations Based on Implicit User Feedback |
| US20190066231A1 (en) * | 2015-11-09 | 2019-02-28 | Deskera Singapore Pte Ltd | Methods and systems for providing content to a user of a relationship network |
| CN106919582A (en) * | 2015-12-24 | 2017-07-04 | 阿里巴巴集团控股有限公司 | The association of network articles and related information statistical method and device |
-
2019
- 2019-12-17 CN CN201911304859.0A patent/CN110969491B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103106600A (en) * | 2012-11-15 | 2013-05-15 | 深圳中兴网信科技有限公司 | Commodity information push system and commodity information push method |
| CN109934654A (en) * | 2017-12-18 | 2019-06-25 | 中国移动通信集团山东有限公司 | Method of Commodity Recommendation and system |
| WO2019223379A1 (en) * | 2018-05-22 | 2019-11-28 | 阿里巴巴集团控股有限公司 | Product recommendation method and device |
Non-Patent Citations (1)
| Title |
|---|
| 基于关联规则的商品智能推荐算法;张勇杰;杨鹏飞;段群;韩丽娜;;现代计算机(专业版)(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110969491A (en) | 2020-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107146089B (en) | Method and device for identifying bill swiping and electronic equipment | |
| CN107016026B (en) | User tag determination method, information push method, user tag determination device, information push device | |
| CN103577988B (en) | A kind of method and apparatus for recognizing specific user | |
| CN108550052A (en) | Brush list detection method and system based on user behavior data feature | |
| CN105975483A (en) | User preference-based message pushing method and platform | |
| WO2019233077A1 (en) | Ranking of business object | |
| CN103353880B (en) | A kind of utilization distinctiveness ratio cluster and the data digging method for associating | |
| CN102841946A (en) | Commodity data retrieval sequencing and commodity recommendation method and system | |
| CN107301592A (en) | The method and device excavated for commodity substitute | |
| CN111626767B (en) | Resource data issuing method, device and equipment | |
| CN108229826A (en) | A kind of net purchase risk class appraisal procedure based on improvement bayesian algorithm | |
| CN111340566B (en) | Commodity classification method and device, electronic equipment and storage medium | |
| CN107679898A (en) | A kind of Method of Commodity Recommendation and device | |
| CN107247728B (en) | Text processing method and device and computer storage medium | |
| CN114330752A (en) | Ranking model training method and ranking method | |
| CN107093122B (en) | Object classification method and device | |
| CN106919582A (en) | The association of network articles and related information statistical method and device | |
| CN115860880B (en) | Personalized commodity recommendation method and system based on multi-layer heterogeneous graph convolution model | |
| CN112560105A (en) | Joint modeling method and device for protecting multi-party data privacy | |
| CN112819404A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110969491B (en) | Commodity pushing method, system and equipment based on network path | |
| CN111754287A (en) | Article screening method, apparatus, device and storage medium | |
| CN111340601A (en) | Commodity information recommendation method and device, electronic equipment and storage medium | |
| Zhang et al. | The approaches to contextual transaction trust computation in e‐Commerce environments | |
| CN108090794A (en) | A kind of merchandise items sort method and device based on dynamic sliding time window |
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 | ||
| CB02 | Change of applicant information |
Address after: 518000 Guangdong city of Shenzhen province Nanshan District Guangdong streets high in the four Longtaili Technology Building Room 325 No. 30 Applicant after: Shenzhen mengwang video Co.,Ltd. Address before: 518000 Guangdong city of Shenzhen province Nanshan District Guangdong streets high in the four Longtaili Technology Building Room 325 No. 30 Applicant before: SHENZHEN MONTNETS ENCYCLOPEDIA INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |