CN112287210A - Template recommendation method and device, electronic equipment and computer readable medium - Google Patents
Template recommendation method and device, electronic equipment and computer readable medium Download PDFInfo
- Publication number
- CN112287210A CN112287210A CN202010789826.6A CN202010789826A CN112287210A CN 112287210 A CN112287210 A CN 112287210A CN 202010789826 A CN202010789826 A CN 202010789826A CN 112287210 A CN112287210 A CN 112287210A
- Authority
- CN
- China
- Prior art keywords
- network
- network node
- node
- modularity
- complex
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000006399 behavior Effects 0.000 claims abstract description 20
- 238000012163 sequencing technique Methods 0.000 claims abstract description 14
- 230000008859 change Effects 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 abstract description 5
- 230000002776 aggregation Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 15
- 238000003860 storage Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000000638 solvent extraction Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Images
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
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q30/0276—Advertisement creation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure relates to a template recommendation method and device, electronic equipment and a computer readable medium, and belongs to the technical field of computers. The method comprises the following steps: acquiring objects obtained by all users in a preset time period through ownership acquisition behaviors, and generating a complex network of the objects by taking the objects as network nodes; dividing network nodes in the complex network into a plurality of network node sets according to the modularity of the complex network; the network nodes in each network node set are sequenced according to the node degrees, and a target network node in each network node set is determined according to the sequencing result; obtaining the identification information of each network node in the network node set where the target network node is located according to the identification information of the target network node; and determining a recommendation template of an object corresponding to the network node according to the identification information of the network node. By combining the aggregation characteristics of the complex network, different templates can be provided for objects in different sets, and the template recommendation efficiency is improved.
Description
Technical Field
The present disclosure relates to the field of computer technologies, and in particular, to a template recommendation method, a template recommendation apparatus, an electronic device, and a computer-readable medium.
Background
In the internet age, internet advertising has become the most common form of advertising. In order to improve the advertisement putting efficiency, the method for making advertisements through templates becomes a preferred advertisement creative making mode for many advertisers.
For the selection mode of the template, in the prior art, different tag attributes are generally manually labeled, or the template is recommended based on the click rate of the delivered advertisement, however, the template is recommended by the method, on one hand, the efficiency is low, on the other hand, the characteristics and the positioning of the popularization object cannot be combined, and the result that the template is not matched with the popularization object is easily caused.
In view of the above, there is a need in the art for a method for template recommendation that can effectively combine the characteristics of the subject.
It is to be noted that the information disclosed in the above background section is only for enhancement of understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art.
Disclosure of Invention
The purpose of the present disclosure is to provide a template recommendation method, a template recommendation apparatus, an electronic device, and a computer-readable medium, which can perform template recommendation at least to some extent by combining characteristics of an object, thereby improving efficiency and accuracy of template recommendation.
According to a first aspect of the present disclosure, there is provided a template recommendation method, including:
acquiring an object obtained by each user through ownership acquisition behavior in a preset time period, and generating a complex network of the object by taking the object as a network node;
dividing network nodes in the complex network into a plurality of network node sets according to the modularity of the complex network;
sequencing the network nodes in each network node set according to the node degrees, and determining target network nodes in each network node set according to the sequencing result;
obtaining the identification information of each network node in the network node set where the target network node is located according to the identification information of the target network node;
and determining the recommendation template of the object corresponding to the network node according to the identification information of the network node.
In an exemplary embodiment of the present disclosure, the generating a complex network of the object with the object as a network node includes:
putting the objects obtained by the same user through the ownership obtaining behavior in the preset time period into the same object set;
and taking the object as a network node, and connecting every two network nodes in the same object set through node connecting edges to obtain a complex network of the object.
In an exemplary embodiment of the present disclosure, the connecting network nodes in the same object set pairwise by node connecting edges to obtain a complex network of the object includes:
connecting every two network nodes in the same object set through node connecting edges, and determining the weight value of each node connecting edge according to the times of acquiring the objects by a user in the preset time period;
and obtaining the complex network of the object according to the node connecting edges with the weight values larger than the weight threshold value and the network nodes connected with the node connecting edges.
In an exemplary embodiment of the present disclosure, the dividing the network nodes in the complex network into a plurality of network node sets according to the modularity of the complex network includes:
initializing each network node in the complex network into a plurality of separate network node sets respectively;
determining adjacent network nodes of each network node, and pre-distributing the network nodes to a network node set where each adjacent network node is located;
determining a change value of the modularity of the complex network after pre-allocation, and determining a target network node set where an adjacent network node which enables the change value of the modularity of the complex network to be maximum is located;
and distributing the network nodes to the target network node set, and distributing the network nodes again according to the change value of the modularity until the network node set where all the network nodes are located does not change any more.
In an exemplary embodiment of the present disclosure, the determining a variation value of the modularity of the complex network after pre-allocation includes:
determining a first modularity of a network node set in which the adjacent network node is located after the network node is pre-allocated to the network node set in which the adjacent network node is located;
determining a second modularity of a network node set where the network node before pre-allocation is located and a network node set where the adjacent network node is located;
and obtaining a change value of the modularity of the complex network after pre-allocation according to the difference value of the first modularity and the second modularity.
In an exemplary embodiment of the present disclosure, the method for generating the modularity includes:
acquiring the number of first node connecting edges among all network nodes in the network node set;
acquiring the number of second node connection edges connected with each network node in the network node set;
and acquiring the total number of connecting edges of the node connecting edges in the complex network, and acquiring the modularity of the network node set according to the total number of the connecting edges, the number of the first node connecting edges and the number of the second node connecting edges of the network node set.
In an exemplary embodiment of the present disclosure, the sorting the network nodes in each network node set according to node degrees, and determining the target network node in each network node set according to a sorting result includes:
sequencing the network nodes in each network node set according to the order of node degrees from large to small;
and acquiring network nodes with preset screening quantity according to the sorting result to be used as target network nodes in the network node set.
According to a second aspect of the present disclosure, there is provided a recommendation apparatus for a template, including:
the complex network generation module is used for acquiring an object obtained by each user in a preset time period through ownership acquisition behavior, and generating a complex network of the object by taking the object as a network node;
the node set dividing module is used for dividing the network nodes in the complex network into a plurality of network node sets according to the modularity of the complex network;
the target node determining module is used for sequencing the network nodes in each network node set according to the node degrees and determining the target network nodes in each network node set according to the sequencing result;
the identification information determining module is used for obtaining the identification information of each network node in the network node set where the target network node is located according to the identification information of the target network node;
and the recommendation template determining module is used for determining the recommendation template of the object corresponding to the network node according to the identification information of the network node.
According to a third aspect of the present disclosure, there is provided an electronic device comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the method of recommending templates of any of the above via execution of the executable instructions.
According to a fourth aspect of the present disclosure, there is provided a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a method of recommending a template as in any one of the above.
The exemplary embodiments of the present disclosure may have the following advantageous effects:
in the template recommendation method according to the exemplary embodiment of the present disclosure, a complex network of objects is constructed through ownership obtaining behaviors of users, the objects are divided into a plurality of community sets by using aggregation characteristics of the complex network, and different templates are provided for features of the objects in different sets. According to the template recommendation method in the disclosed example embodiment, on one hand, the template recommendation can be performed more intelligently by combining the characteristics and the positioning of the popularization object, and then a user is attracted more accurately; on the other hand, by recommending the template according with the object characteristics, the content manufactured by the template can be standardized, the efficiency of template manufacturing is improved, and the workload of personnel is reduced.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure. It is to be understood that the drawings in the following description are merely exemplary of the disclosure, and that other drawings may be derived from those drawings by one of ordinary skill in the art without the exercise of inventive faculty.
FIG. 1 shows a flow diagram of a method of recommendation of a template in an example embodiment of the present disclosure;
FIG. 2 schematically illustrates a schematic diagram of a complex network, according to an embodiment of the present disclosure;
FIG. 3 illustrates a flow diagram of generating a complex network of objects of an example embodiment of the present disclosure;
fig. 4 shows a flow diagram of network node partitioning in an example embodiment of the present disclosure;
FIG. 5 illustrates a flow chart diagram for determining a change value of a module degree in an example embodiment of the present disclosure;
FIG. 6 is a flow diagram illustrating a method for recommending templates in accordance with an embodiment of the present disclosure;
FIG. 7 shows a block diagram of a recommendation device for a template of an example embodiment of the present disclosure;
FIG. 8 illustrates a schematic structural diagram of a computer system suitable for use in implementing the electronic device of an embodiment of the present disclosure.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and the like. In other instances, well-known technical solutions have not been shown or described in detail to avoid obscuring aspects of the present disclosure.
Furthermore, the drawings are merely schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repetitive description will be omitted. Some of the block diagrams shown in the figures are functional entities and do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The present exemplary embodiment first provides a template recommendation method. Referring to fig. 1, the method for recommending the template may include the following steps:
and S110, acquiring an object obtained by each user in a preset time period through ownership acquisition behavior, and generating a complex network of the object by taking the object as a network node.
And S120, dividing the network nodes in the complex network into a plurality of network node sets according to the modularity of the complex network.
S130, sequencing the network nodes in each network node set according to the node degrees, and determining the target network nodes in each network node set according to the sequencing result.
And S140, obtaining the identification information of each network node in the network node set where the target network node is located according to the identification information of the target network node.
And S150, determining a recommendation template of an object corresponding to the network node according to the identification information of the network node.
In a long historical course, the style of advertising is constantly changing with business forms, for example, from the earliest physical advertisements, outdoor advertisements, to current internet advertisements. Although the form of the advertisement is continuously changing, the content shown in the advertisement is a part of most concern to the advertiser. Therefore, it is extremely important to create a good creative advertisement because it can be personalized, accurately attracted to users and make their formation into a transaction the most important part of internet advertising. At present, making advertisements through templates is a preferred mode of many advertisers, but how to effectively select favorite images and video templates of users and make the templates conform to the positioning of commodities becomes a problem to be solved by the advertisers at present.
For example, some users are interested in pursuing cost-effective commodities, some users prefer brands with higher popularity, and some users prefer more favorable commodities. For example, when purchasing commodities such as watches and mobile phones, users with good economic conditions may choose to purchase a large brand, and some users who like science and technology may purchase mobile phones and watches with fresh functions.
When an advertiser promotes a sku (stock serving unit), the template recommendation method in the exemplary embodiment is used to group the same type of commodities together by analyzing the purchasing behavior data of the user, intelligently analyze the attributes of the commodities, and then recommend creative templates that conform to the attributes. For example, when an advertiser creates a creative for a certain brand bag, some creative templates with a high-end luxury style can be selected and recommended by the template recommendation method in the present example embodiment.
In the template recommendation method according to the exemplary embodiment of the present disclosure, a complex network of objects is constructed through ownership obtaining behaviors of users, the objects are divided into a plurality of community sets by using aggregation characteristics of the complex network, and different templates are provided for features of the objects in different sets. According to the template recommendation method in the disclosed example embodiment, on one hand, the template recommendation can be performed more intelligently by combining the characteristics and the positioning of the popularization object, and then a user is attracted more accurately; on the other hand, by recommending the template according with the object characteristics, the content manufactured by the template can be standardized, the efficiency of template manufacturing is improved, and the workload of personnel is reduced.
Next, the above steps of the present exemplary embodiment will be described in more detail with reference to fig. 2 to 6.
In step S110, an object obtained by each user through the ownership obtaining behavior in a preset time period is obtained, and the object is used as a network node to generate a complex network of the object.
In this exemplary embodiment, the ownership obtaining behavior of the user refers to a purchasing behavior of the user, and the object obtained by the ownership obtaining behavior of the user is an article or a commodity purchased by the user. A large-scale complex network is constructed by acquiring the purchased articles of all users within a preset time period, such as one month, and utilizing the purchasing behavior data of the users.
A complex network generally refers to a network with many nodes and complex connection relationships. Due to the flexible and universal description capability, the method is widely applied to various subject fields. Fig. 2 is a schematic diagram of a complex network, in which different objects may be respectively used as network nodes. When the same user purchases both article a and article B, an edge is generated between node a and node B, and the weight of this edge is increased by one.
The complex network has the characteristics of small world, scale-free aggregation and the like. Many complex networks have a community structure, that is, the whole network is composed of several communities, the connections between communities are relatively sparse, and the connections inside communities are relatively dense. The community discovery is to analyze the modularized community structure from the complex network by using the information in the topological structure of the complex network graph. Fig. 2 shows the aggregations of the complex network, and as can be seen from fig. 2, the network nodes can be divided into 3 communities, including community 201, community 202 and community 203.
The method in the present exemplary embodiment is to utilize the community characteristics of the complex network, abstract the purchasing behavior data of the user into the complex network, discover the community structure in the network by using the modularity optimization method, consider that the objects in the same community belong to the same class, and recommend templates of different styles for the commodities in different communities.
Based on the above, as shown in fig. 3, the method for generating a complex network of objects by using objects as network nodes may specifically include the following steps:
and S310, putting the objects obtained by the same user through the ownership obtaining behavior in the preset time period into the same object set.
And S320, taking the object as a network node, and connecting every two network nodes in the same object set through node connecting edges to obtain a complex network of the object.
In this example embodiment, since the possibility that the commodities purchased by the same user belong to the same type is high, the objects acquired by the same user within the preset time period may be placed in the same object set, and then the network nodes corresponding to the objects in the set may be connected to each other.
Further, under the condition of overlarge data volume, connecting every two network nodes in the same object set through node connecting edges, and determining the weight value of each node connecting edge according to the times of obtaining objects by a user in a preset time period; and obtaining the complex network of the object according to the node connecting edges with the weight values larger than the weight threshold value and the network nodes connected with the node connecting edges. That is, if two commodities are purchased by the same user, each time the two commodities are purchased simultaneously, the weight value of the node connecting edge between the two commodities is added by 1, and then the node connecting edge with a higher weight value and the corresponding network node thereof can be retained by setting a weight threshold value, for example, the weight value is greater than or equal to 10, so as to generate a final complex network.
In step S120, the network nodes in the complex network are divided into a plurality of network node sets according to the modularity of the complex network.
In the present example embodiment, the network nodes in the complex network may be divided into a plurality of network node sets according to the modularity of the complex network, where each network node set represents one network community.
In the present example embodiment, the discovery community may be optimized using modularity (modeling). The modularity is an important index for measuring the network partition in Community discovery (Community Detection). The closer the value is to 1, the stronger the intensity of the community structure divided by the network is, namely, the better the dividing quality is. Thus, optimal network community partitioning can be achieved by maximizing modularity. The method using the optimization modularity as the recommendation template can greatly improve the accuracy of the recommendation result.
The Louvain algorithm is adopted in the example embodiment, and the theoretical basis of the Louvain algorithm is that the modularity which can best measure the community dividing result is taken as a starting point. The value range of the modularity is (0, 1), and the calculation formula is as follows:
where m is the total number of edges in the network; i and j represent index parameters of the network node; a. theijThe weight of the connecting edge is obtained, when an edge exists between the node i and the node j, the value is 1, otherwise, the value is 0; k is a radical ofi，kjRespectively representing the degrees of the node i and the node j (the degrees of the nodes represent the number of edges connected with the nodes); ci,CjRepresenting the communities of the node i and the node j; when node i and node j are in the same community,
is 1, otherwise is 0. So another definition of modularity is as follows:
the sigma in represents the number of first node connecting edges among the network nodes in the community C, and the sigma tot represents the number of second node connecting edges connected with the network nodes in the community C. When the modularity of the network node set is calculated, the modularity of the network node set is obtained by obtaining the number of first node connecting edges among network nodes in the network node set, obtaining the number of second node connecting edges connected with the network nodes in the network node set, obtaining the total number of connecting edges of node connecting edges in a complex network, and referring to the formula according to the total number of the connecting edges and the number of the first node connecting edges and the number of the second node connecting edges of the network node set.
In the process of optimizing the community structure, when the community in which all the nodes are located is found, the value of the modularity can be maximized, so that the final community structure is determined. For the same community, it can be considered that the objects corresponding to the network nodes in the community can attract users of the same type, so that the objects in the same community can recommend creative templates with almost the same style.
As shown in fig. 4, the method for dividing network nodes in a complex network into a plurality of network node sets according to the modularity of the complex network may specifically include the following steps:
step S410, each network node in the complex network is respectively initialized into a plurality of independent network node sets.
First, each network node in the network is initialized to a separate community.
Step S420, determining adjacent network nodes of each network node, and pre-distributing the network nodes to the network node set where each adjacent network node is located.
And taking other network nodes connected with the network nodes through the node connecting edges as the adjacent network nodes of the network nodes, and pre-distributing the network nodes to the communities where the adjacent network nodes are located.
And S430, determining the change value of the modularity of the complex network after pre-allocation, and determining a target network node set where the adjacent network node with the largest change value of the modularity of the complex network is located.
After the network nodes are pre-distributed to the communities where the adjacent network nodes are located, the change values of the modularity of the pre-distributed complex network are calculated respectively, one adjacent network node which enables the change value of the modularity to be maximum is selected, and the network nodes are distributed to the communities which enable the change value of the modularity to be maximum.
As shown in fig. 5, a specific method for determining the variation value of the modularity of the complex network after pre-allocation is as follows:
step 510, determining a first modularity of a network node set where an adjacent network node is located after the network node is pre-allocated to the network node set where the adjacent network node is located.
And S520, determining a second modularity of the network node set where the network node before pre-allocation is located and the network node set where the adjacent network node is located.
And S530, obtaining a variation value of the modularity of the pre-distributed complex network according to the difference value of the first modularity and the second modularity.
The calculation formula of the change value of the modularity is divided into two parts, wherein one part is the first modularity after the network node is added into the community where the adjacent network node is located, the other part is the second modularity before the network node is added into the community where the adjacent network node is located, the network node is used as an independent community and the community where the adjacent network node is located, and the change value of the modularity is obtained through the difference between the first modularity and the second modularity. The specific calculation formula of the change value delta Q of the modularity is as follows:
wherein, Ki,inIs the sum of the node connecting edges of the network nodes in the community where the adjacent network nodes are located and the network nodes to be distributed.
And S440, distributing the network nodes to the target network node set, and distributing the network nodes again according to the change value of the modularity until the network node sets where all the network nodes are located are not changed any more.
After the network nodes are distributed, the steps are sequentially repeated, each network node is distributed again until the community structure is not changed, namely the delta Q is not changed, and the final community structure of the complex network can be obtained.
In step S130, the network nodes in each network node set are sorted according to the node degrees, and the target network node in each network node set is determined according to the sorting result.
After a community structure of the complex network is divided, network nodes in each network node set are sequenced according to the node degrees from large to small, and then network nodes with preset screening quantity are obtained according to sequencing results and serve as target network nodes in the network node sets. That is, several network nodes with a large node degree in each community are screened out as target network nodes.
In step S140, the identification information of each network node in the network node set where the target network node is located is obtained according to the identification information of the target network node.
And acquiring identification information of target network nodes, including style labels and the like of commodities corresponding to the nodes, as the identification information of all network nodes in the community. For example, if the commodity corresponding to the target network node is office-type stationery, style labels such as concise and practical office-type stationery are obtained and used as identification information of network nodes of all stationery types in the community.
In step S150, a recommended template of an object corresponding to the network node is determined according to the identification information of the network node.
Finally, when the template recommendation is carried out, a series of picture templates, video templates and the like with corresponding styles can be recommended to carry out template making according to the community where the recommendation object is located.
In this exemplary embodiment, the recommended template may include a picture template, a video template, and other common internet advertisement templates, wherein different style tags may be embodied in the template by different pattern designs or typesetting, and when the template is manufactured, the manufacturing of the template is finally completed by adding corresponding text and publicity phrases, and the like.
Fig. 6 shows a complete flow chart in one embodiment of the present disclosure, which is an illustration of the above steps in this exemplary embodiment, and the specific steps in the flow chart are as follows:
and S610, constructing a network.
Firstly, data processing is carried out, skus purchased by a user in a month are used as nodes (nodes) of a network, two skus purchased by the same user form an edge, and the weight value of the edge is added with 1 every time the skus are purchased simultaneously. And because the data volume is large, only edges with weight values larger than 10 are reserved finally, and an initial complex network is formed.
And S620, initializing a community.
Each node in the network is initialized as a separate community.
And S630, calculating the variable quantity of the modularity.
For each node i, distributing the node i to the community where each adjacent node j is located, and calculating the modularity variation value (delta Q) corresponding to each different partition, wherein the calculation formula is as follows;
different Δ Q are obtained according to different distribution methods, and then the node i is distributed into the community that maximizes Δ Q.
And S640, judging whether the modularity is changed.
Step S630 is repeated in sequence until the community structure is no longer changed, i.e., Δ Q is unchanged.
And S650, determining a community structure.
After the communities are divided, the degrees (degrees) of the nodes in the communities are sorted from large to small, and a plurality of nodes with larger node degrees in each community are screened out.
And S660, obtaining brand information.
And marking the style label of the community by combining the brand information corresponding to the nodes.
And S670, recommending the template.
When the advertiser manufactures the creative popularization object, the community where the object is located is determined according to the object, and therefore a series of creative pictures and video templates are recommended to be manufactured for the advertiser.
It should be noted that although the various steps of the methods of the present disclosure are depicted in the drawings in a particular order, this does not require or imply that these steps must be performed in this particular order, or that all of the depicted steps must be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step execution, and/or one step broken down into multiple step executions, etc.
Furthermore, the disclosure also provides a recommendation device for the template. Referring to fig. 7, the recommending means of the template may include a complex network generating module 710, a node set dividing module 720, a target node determining module 730, an identification information determining module 740, and a recommended template determining module 750. Wherein:
the complex network generation module 710 may be configured to acquire an object obtained by each user through an ownership acquisition behavior within a preset time period, and generate a complex network of the object by using the object as a network node;
the node set dividing module 720 may be configured to divide the network nodes in the complex network into a plurality of network node sets according to the modularity of the complex network;
the target node determining module 730 may be configured to rank the network nodes in each network node set according to the node degrees, and determine the target network node in each network node set according to a ranking result;
the identification information determining module 740 may be configured to obtain identification information of each network node in the network node set where the target network node is located according to the identification information of the target network node;
the recommended template determining module 750 may be configured to determine a recommended template of an object corresponding to a network node according to the identification information of the network node.
In some exemplary embodiments of the present disclosure, the complex network generating module 710 may include an object set acquiring unit and a network node connecting unit. Wherein:
the object set acquiring unit may be configured to put objects obtained by the same user through an ownership acquiring behavior in a preset time period into the same object set;
the complex network generation unit may be configured to use the object as a network node, and connect every two network nodes in the same object set through node connection edges to obtain a complex network of the object.
In some exemplary embodiments of the present disclosure, the complex network generating unit may include a weight value determining unit and a network node connecting unit. Wherein:
the weight value determining unit may be configured to connect every two network nodes in the same object set by using node connection edges, and determine a weight value of each node connection edge according to the number of times that a user acquires an object within a preset time period;
the network node connection unit may be configured to obtain a complex network of the object according to the node connection edge whose weight value is greater than the weight threshold and the network node to which the node connection edge is connected.
In some example embodiments of the present disclosure, the node set partitioning module 720 may include a network node initialization unit, a network node pre-allocation unit, a target node set determination unit, and a network node allocation unit. Wherein:
the network node initialization unit may be configured to initialize each network node in the complex network into a plurality of separate network node sets respectively;
the network node pre-allocation unit may be configured to determine neighboring network nodes of each network node, and pre-allocate the network nodes to a network node set in which the neighboring network nodes are located;
the target node set determining unit may be configured to determine a variation value of the modularity of the complex network after pre-allocation, and determine a target network node set where an adjacent network node that maximizes the variation value of the modularity of the complex network is located;
the network node allocation unit may be configured to allocate the network nodes to the target network node set, and allocate the network nodes again according to the change value of the modularity until the network node set where all the network nodes are located does not change any more.
In some exemplary embodiments of the present disclosure, the target node set determination unit may include a first modularity determination unit, a second modularity determination unit, and a modularity change value determination unit. Wherein:
the first modularity determining unit may be configured to determine a first modularity of a network node set in which an adjacent network node is located after a network node is pre-allocated to the network node set in which the adjacent network node is located;
the second modularity determining unit may be configured to determine a second modularity of a network node set where the network node before pre-allocation is located and a network node set where the neighboring network node is located;
the modularity variation value determining unit may be configured to obtain a variation value of the modularity of the complex network after the pre-allocation according to a difference between the first modularity and the second modularity.
In some exemplary embodiments of the present disclosure, the node set partitioning module 720 may further include a modularity calculating unit, which may include a first connecting edge number determining unit, a second connecting edge number determining unit, and a node set modularity determining unit. Wherein:
the first connection edge number determining unit may be configured to obtain a first node connection edge number between each network node in the network node set;
the second connection edge number determining unit may be configured to obtain a number of second node connection edges connected to each network node in the network node set;
the node set modularity determining unit may be configured to obtain a total number of connection edges of node connection edges in the complex network, and obtain the modularity of the network node set according to the total number of connection edges, and the number of first node connection edges and the number of second node connection edges of the network node set.
In some exemplary embodiments of the present disclosure, the target node determination module 730 may include a network node sorting unit and a network node screening unit. Wherein:
the network node sorting unit may be configured to sort the network nodes in each network node set in an order from a node degree to a node degree;
the network node screening unit may be configured to obtain, according to the sorting result, a preset screening number of network nodes as target network nodes in the network node set.
The details of each module/unit in the recommendation apparatus for the template have been described in detail in the corresponding method embodiment section, and are not described herein again.
FIG. 8 illustrates a schematic structural diagram of a computer system suitable for use with the electronic device to implement an embodiment of the invention.
It should be noted that the computer system 800 of the electronic device shown in fig. 8 is only an example, and should not bring any limitation to the functions and the scope of the application of the embodiment of the present invention.
As shown in fig. 8, the computer system 800 includes a Central Processing Unit (CPU)801 that can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data necessary for system operation are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other via a bus 804. An input/output (I/O) interface 805 is also connected to bus 804.
The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, a mouse, and the like; an output section 807 including a signal such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 808 including a hard disk and the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. A drive 810 is also connected to the I/O interface 805 as necessary. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as necessary, so that a computer program read out therefrom is mounted on the storage section 808 as necessary.
In particular, according to an embodiment of the present invention, the processes described below with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the invention include a computer program product comprising a computer program embodied on a computer-readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 809 and/or installed from the removable medium 811. When the computer program is executed by the Central Processing Unit (CPU)801, various functions defined in the system of the present application are executed.
It should be noted that the computer readable media shown in the present disclosure may be computer readable signal media or computer readable storage media or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer-readable signal medium may include a propagated data signal with computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by an electronic device, cause the electronic device to implement the method as described in the embodiments below.
It should be noted that although in the above detailed description several modules of the device for action execution are mentioned, this division is not mandatory. Indeed, the features and functionality of two or more of the modules described above may be embodied in one module, in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module described above may be further divided into embodiments by a plurality of modules.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A method for recommending templates is characterized by comprising the following steps:
acquiring an object obtained by each user through ownership acquisition behavior in a preset time period, and generating a complex network of the object by taking the object as a network node;
dividing network nodes in the complex network into a plurality of network node sets according to the modularity of the complex network;
sequencing the network nodes in each network node set according to the node degrees, and determining target network nodes in each network node set according to the sequencing result;
obtaining the identification information of each network node in the network node set where the target network node is located according to the identification information of the target network node;
and determining the recommendation template of the object corresponding to the network node according to the identification information of the network node.
2. The template recommendation method according to claim 1, wherein the generating a complex network of the object by using the object as a network node comprises:
putting the objects obtained by the same user through the ownership obtaining behavior in the preset time period into the same object set;
and taking the object as a network node, and connecting every two network nodes in the same object set through node connecting edges to obtain a complex network of the object.
3. The template recommendation method according to claim 2, wherein the connecting network nodes in the same object set by node connecting edges to each other to obtain the complex network of the object comprises:
connecting every two network nodes in the same object set through node connecting edges, and determining the weight value of each node connecting edge according to the times of acquiring the objects by a user in the preset time period;
and obtaining the complex network of the object according to the node connecting edges with the weight values larger than the weight threshold value and the network nodes connected with the node connecting edges.
4. The method for recommending templates according to claim 1, wherein said dividing network nodes in the complex network into a plurality of network node sets according to modularity of the complex network comprises:
initializing each network node in the complex network into a plurality of separate network node sets respectively;
determining adjacent network nodes of each network node, and pre-distributing the network nodes to a network node set where each adjacent network node is located;
determining a change value of the modularity of the complex network after pre-allocation, and determining a target network node set where an adjacent network node which enables the change value of the modularity of the complex network to be maximum is located;
and distributing the network nodes to the target network node set, and distributing the network nodes again according to the change value of the modularity until the network node set where all the network nodes are located does not change any more.
5. The method for recommending templates according to claim 4, wherein said determining the variation value of the modularity of the complex network after pre-allocation comprises:
determining a first modularity of a network node set in which the adjacent network node is located after the network node is pre-allocated to the network node set in which the adjacent network node is located;
determining a second modularity of a network node set where the network node before pre-allocation is located and a network node set where the adjacent network node is located;
and obtaining a change value of the modularity of the complex network after pre-allocation according to the difference value of the first modularity and the second modularity.
6. The template recommendation method according to claim 1, wherein the modularity generation method comprises:
acquiring the number of first node connecting edges among all network nodes in the network node set;
acquiring the number of second node connection edges connected with each network node in the network node set;
and acquiring the total number of connecting edges of the node connecting edges in the complex network, and acquiring the modularity of the network node set according to the total number of the connecting edges, the number of the first node connecting edges and the number of the second node connecting edges of the network node set.
7. The template recommendation method according to claim 1, wherein the sorting the network nodes in each network node set according to node degrees and determining the target network node in each network node set according to the sorting result comprises:
sequencing the network nodes in each network node set according to the order of node degrees from large to small;
and acquiring network nodes with preset screening quantity according to the sorting result to be used as target network nodes in the network node set.
8. An apparatus for recommending templates, comprising:
the complex network generation module is used for acquiring an object obtained by each user in a preset time period through ownership acquisition behavior, and generating a complex network of the object by taking the object as a network node;
the node set dividing module is used for dividing the network nodes in the complex network into a plurality of network node sets according to the modularity of the complex network;
the target node determining module is used for sequencing the network nodes in each network node set according to the node degrees and determining the target network nodes in each network node set according to the sequencing result;
the identification information determining module is used for obtaining the identification information of each network node in the network node set where the target network node is located according to the identification information of the target network node;
and the recommendation template determining module is used for determining the recommendation template of the object corresponding to the network node according to the identification information of the network node.
9. An electronic device, comprising:
a processor; and
memory for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement a method of recommendation of a template as claimed in any one of claims 1 to 7.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of recommendation of a template according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010789826.6A CN112287210A (en) | 2020-08-07 | 2020-08-07 | Template recommendation method and device, electronic equipment and computer readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010789826.6A CN112287210A (en) | 2020-08-07 | 2020-08-07 | Template recommendation method and device, electronic equipment and computer readable medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112287210A true CN112287210A (en) | 2021-01-29 |
Family
ID=74420716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010789826.6A Pending CN112287210A (en) | 2020-08-07 | 2020-08-07 | Template recommendation method and device, electronic equipment and computer readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287210A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007021556A2 (en) * | 2005-08-11 | 2007-02-22 | Qurio Holdings, Inc. | Real-time recommendation of album templates for online photosharing |
| CN103678531A (en) * | 2013-12-02 | 2014-03-26 | 三星电子（中国）研发中心 | Friend recommendation method and friend recommendation device |
| CN103793476A (en) * | 2014-01-08 | 2014-05-14 | 西安电子科技大学 | Network community based collaborative filtering recommendation method |
| CN105338071A (en) * | 2015-10-15 | 2016-02-17 | 北京金山安全软件有限公司 | Information pushing method and device |
| CN105427125A (en) * | 2015-10-29 | 2016-03-23 | 电子科技大学 | Goods clustering method based on goods network connection graph |
| CN106780058A (en) * | 2016-11-29 | 2017-05-31 | 北京邮电大学 | The group dividing method and device of dynamic network |
| CN109191058A (en) * | 2018-07-18 | 2019-01-11 | 北京科技大学 | A kind of workflow template recommended method and system towards numerical simulation community |
| CN110474944A (en) * | 2018-05-10 | 2019-11-19 | 腾讯科技（深圳）有限公司 | Processing method, device and the storage medium of the network information |
| CN110727863A (en) * | 2019-09-27 | 2020-01-24 | 东北大学 | Project recommendation method based on complex network collaborative filtering |
| CN111030854A (en) * | 2019-12-04 | 2020-04-17 | 兰州交通大学 | Complex network community discovery method under Spark cloud service environment |
-
2020
- 2020-08-07 CN CN202010789826.6A patent/CN112287210A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007021556A2 (en) * | 2005-08-11 | 2007-02-22 | Qurio Holdings, Inc. | Real-time recommendation of album templates for online photosharing |
| CN103678531A (en) * | 2013-12-02 | 2014-03-26 | 三星电子（中国）研发中心 | Friend recommendation method and friend recommendation device |
| CN103793476A (en) * | 2014-01-08 | 2014-05-14 | 西安电子科技大学 | Network community based collaborative filtering recommendation method |
| CN105338071A (en) * | 2015-10-15 | 2016-02-17 | 北京金山安全软件有限公司 | Information pushing method and device |
| CN105427125A (en) * | 2015-10-29 | 2016-03-23 | 电子科技大学 | Goods clustering method based on goods network connection graph |
| CN106780058A (en) * | 2016-11-29 | 2017-05-31 | 北京邮电大学 | The group dividing method and device of dynamic network |
| CN110474944A (en) * | 2018-05-10 | 2019-11-19 | 腾讯科技（深圳）有限公司 | Processing method, device and the storage medium of the network information |
| CN109191058A (en) * | 2018-07-18 | 2019-01-11 | 北京科技大学 | A kind of workflow template recommended method and system towards numerical simulation community |
| CN110727863A (en) * | 2019-09-27 | 2020-01-24 | 东北大学 | Project recommendation method based on complex network collaborative filtering |
| CN111030854A (en) * | 2019-12-04 | 2020-04-17 | 兰州交通大学 | Complex network community discovery method under Spark cloud service environment |
Non-Patent Citations (1)
| Title |
|---|
| 卢丹;王君博;武森;: "电子商务中基于复杂网络社团发现的商品推荐研究", 工业技术创新, no. 01, 25 February 2015 (2015-02-25) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Miao et al. | Context‐based dynamic pricing with online clustering | |
| US20230306491A1 (en) | User feature-based page displaying method and apparatus, medium, and electronic device | |
| CN109783539A (en) | Usage mining and its model building method, device and computer equipment | |
| CN112528164B (en) | User collaborative filtering recall method and device | |
| CN108109004A (en) | Similar crowd's extended method, device and electronic equipment | |
| CN109359834A (en) | Supply of commodities management system and method | |
| CN110097287A (en) | A kind of group's portrait method of logistics driver | |
| CN112749323A (en) | Method and device for constructing user portrait | |
| CN112836128A (en) | Information recommendation method, device, equipment and storage medium | |
| CN115860870A (en) | Commodity recommendation method, system and device and readable medium | |
| US11720927B2 (en) | Method and apparatus for generating user-ad matching list for online advertisement | |
| CN113011911B (en) | Data prediction method and device based on artificial intelligence, medium and electronic equipment | |
| CN112950321A (en) | Article recommendation method and device | |
| CN113327132A (en) | Multimedia recommendation method, device, equipment and storage medium | |
| CN111340566B (en) | Commodity classification method and device, electronic equipment and storage medium | |
| CN113763004A (en) | Information matching method and device | |
| CN111754300A (en) | Commodity recommendation method, commodity recommendation device, commodity recommendation equipment and storage medium | |
| CN113744009A (en) | Target object output method and device, computer readable medium and electronic equipment | |
| CN112287210A (en) | Template recommendation method and device, electronic equipment and computer readable medium | |
| CN112015970A (en) | Product recommendation method, related equipment and computer storage medium | |
| CN112948701B (en) | Information recommendation device, method, equipment and storage medium | |
| CN111611469A (en) | Identification information determination method and device, electronic equipment and storage medium | |
| CN113191840A (en) | Article information display method and device, electronic equipment and computer readable medium | |
| CN113554438B (en) | Account identification method and device, electronic equipment and computer readable medium | |
| CN113052635A (en) | Population attribute label prediction method, system, computer device and storage medium |
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 |