CN113158025B

CN113158025B - Method and device for generating product release strategy and electronic equipment

Info

Publication number: CN113158025B
Application number: CN202110245351.9A
Authority: CN
Inventors: 林岳
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2021-03-05
Filing date: 2021-03-05
Publication date: 2023-11-21
Anticipated expiration: 2041-03-05
Also published as: CN113158025A

Abstract

The disclosure provides a method and a device for generating a product release strategy and electronic equipment, and relates to the technical field of product release. The method comprises the following steps: acquiring user interaction behaviors related to a plurality of users, and constructing a network diagram according to each user and the user interaction behaviors; performing community division on the network graph to divide the network graph into a plurality of sub-network graphs; determining importance of each node in each sub-network graph, determining a delivery strategy according to the importance of each node, and delivering products based on the delivery strategy. The method and the device can realize automatic generation of the product release strategy, improve the product release efficiency and accuracy, and realize maximization of input-output ratio.

Description

Method and device for generating product release strategy and electronic equipment

Technical Field

The disclosure relates to the technical field of product delivery, in particular to a method for generating a product delivery strategy, a device for generating the product delivery strategy, a computer readable medium and electronic equipment.

Background

With the rapid development of internet technology, more and more product operations are performed in an online manner, such as online promotion of financial products, commodities, and the like. For merchants, the resources are limited, and in order to maximize the input-output ratio, it is necessary to perform product delivery for some specific users, such as users with strong sharing will, purchasing will, and the like.

At present, in the actual operation process of a product, a user group to be put in is often determined by means of personal experience of a product manager, the product manager outputs rules for extracting the user group to lock the put-in group, and from experience, the result of the experience decision is often not ideal, the efficiency is low, automation is not realized, and the put-in effect is poor.

It should be noted that the information disclosed in the above background section is only for enhancing 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 embodiment of the disclosure provides a method and a device for generating a product release strategy, a computer readable medium and electronic equipment, so that automatic product release can be realized at least to a certain extent, the product release efficiency is improved, and the maximization of input and output is realized.

Other features and advantages of the present disclosure will be apparent from the following detailed description, or may be learned in part by the practice of the disclosure.

According to an aspect of the embodiments of the present disclosure, there is provided a method for generating a product release policy, including: acquiring user interaction behaviors related to a plurality of users, and constructing a network diagram according to each user and the user interaction behaviors; performing community division on the network graph to divide the network graph into a plurality of sub-network graphs; determining importance of each node in each sub-network graph, determining a delivery strategy according to the importance of each node, and delivering products based on the delivery strategy.

According to an aspect of the embodiments of the present disclosure, there is provided a generating device of a product release policy, including: the network diagram construction module is used for acquiring user interaction behaviors related to a plurality of users and constructing a network diagram according to each user and the user interaction behaviors; the community division module is used for carrying out community division on the network graph so as to divide the network graph into a plurality of sub-network graphs; and the delivery strategy generation module is used for determining the importance degree of each node in each sub-network diagram, determining the delivery strategy according to the importance degree of each node, and delivering the product based on the delivery strategy.

In some embodiments of the disclosure, based on the foregoing solution, the network map construction module is configured to: taking the users as nodes, setting edges between the users with interactive relations, and constructing a graph according to the nodes and the edges; and determining the weight of the edge corresponding to the user interaction behavior according to the number of the user interaction behaviors, and determining the network graph according to the weight of the edge and the graph.

In some embodiments of the disclosure, based on the foregoing solution, the community dividing module includes: the first community dividing unit is used for dividing communities of all nodes in the network graph, and determining an intermediate network graph according to the modularity of communities formed by the community division; and the second community dividing unit is used for taking all communities in the intermediate network graph as update nodes, dividing the update nodes into communities, and determining the sub-network graph according to the modularity of all update communities formed by the community division.

In some embodiments of the present disclosure, based on the above-described scheme, the first community dividing unit includes: an initial division unit, configured to perform initial community division on each node in the network graph, so as to obtain an initial community corresponding to each node; a subdivision unit, configured to divide, with any node in the network map as a target node, the target node into initial communities where nodes adjacent to the target node are located, so as to form subdivision communities; the module degree comparison unit is used for acquiring a first module degree of the sub-divided communities and a second module degree of an initial community where a node adjacent to the target node is located, and executing target operation on the sub-divided communities according to the first module degree and the second module degree; and the repeated dividing unit is used for repeating the functions of the sub-dividing unit and the modularity comparing unit until the modularity of the finally formed sub-dividing community is maximum, so as to obtain the intermediate network graph.

In some embodiments of the present disclosure, based on the above-described scheme, the modularity comparing unit is configured to: obtaining a difference between the first modularity and the second modularity; when the difference value is positive, reserving the sub-division communities; and discarding the sub-divided communities when the difference value is not positive.

In some embodiments of the present disclosure, based on the above-described scheme, the second community dividing unit includes: an update community forming unit, configured to take any one of the update nodes as a target update node, and divide the target update node into communities where update nodes adjacent to the target update node are located, so as to form an update community; the module degree comparison unit is used for acquiring a third module degree of the updated community and a fourth module degree of the community where the updated node adjacent to the target updated node is located, and executing target operation on the updated community according to the third module degree and the fourth module degree; and the repeated dividing unit is used for repeatedly updating the functions of the community forming unit and the modularity comparing unit until the modularity of the finally formed updated community is maximum.

In some embodiments of the present disclosure, based on the above-described scheme, the modularity comparing unit is configured to: obtaining a difference between the third modularity and the fourth modularity; when the difference value is positive, reserving the updated community; and discarding the updated community when the difference value is not positive.

In some embodiments of the present disclosure, based on the foregoing solution, the delivery policy generating module includes: the node transfer unit is used for recursively transferring nodes with all degree values smaller than or equal to a preset degree value in each sub-network diagram to a corresponding network layer, wherein the preset degree value is smaller than or equal to a core degree value in each sub-network diagram; and the importance determining unit is used for determining the importance corresponding to the node according to the core value of the network layer where the node is located.

In some embodiments of the present disclosure, based on the above scheme, the node transfer unit is configured to: moving the node with the degree value of N in each sub-network graph to a network layer with the core value of N so as to obtain a target sub-network graph; judging whether a node with a degree value of N exists in the target sub-network diagram; when the node with the degree value of N exists, the node with the degree value of N is moved to the network layer with the core value of N; when the node with the degree value of N+1 in the target sub-network diagram does not exist, moving the node with the degree value of N+1 to a network layer with the core value of N+1; repeating the steps until the degree value of each node in the finally obtained core network diagram is equal to the preset degree value; wherein N is an integer greater than or equal to 0, and N is less than or equal to the preset value.

In some embodiments of the present disclosure, based on the above scheme, the importance of the node is positively correlated with the core value of the network layer in which the node is located.

In some embodiments of the disclosure, based on the above scheme, the delivery policy generation module is further configured to: sequencing the importance of each node from big to small to obtain node importance sequencing; and determining the delivery strategy according to the node importance degree sequence.

According to an aspect of the disclosed embodiments, there is provided a computer storage medium having a computer program stored thereon, wherein the program when executed by a processor implements the method of generating a product release strategy provided in the above-described alternative implementation.

According to one aspect of the disclosed embodiments, a computer program product or computer program is provided, the computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer readable storage medium and executes the computer instructions to cause the computer device to perform the method of generating a product release strategy provided in the alternative implementation described above.

According to an aspect of an embodiment of the present disclosure, there is provided an electronic device including: one or more processors; and storage means for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the methods provided in the alternative implementations described above.

In the technical schemes provided by some embodiments of the present disclosure, first, user interaction behaviors related to a plurality of users are obtained, a network diagram is constructed according to each user and the user interaction behaviors, then community division is performed on the network diagram to form a plurality of sub-network diagrams, finally importance of each node in each sub-network diagram is determined, a release strategy is determined according to the importance of each node, and further product release is performed based on the release strategy. According to the technical scheme, on one hand, a target user group and priority ordering with stronger sharing will in the sub-network diagram can be determined through an automatic data method, so that automatic product delivery strategy generation and accurate automatic product delivery are realized, and errors of experience sense and manual judgment of a product manager are avoided; on the other hand, by carrying out product delivery on users with sharing will, the users with low sharing will and no sharing will are prevented from carrying out product delivery, and further unnecessary user harassment is avoided; on the other hand, the method and the device can help products and business teams to improve operation efficiency and drive products to increase, improve product release efficiency and accuracy, and maximize input-output ratio.

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 disclosure and together with the description, serve to explain the principles of the disclosure. It will be apparent to those of ordinary skill in the art that the drawings in the following description are merely examples of the disclosure and that other drawings may be derived from them without undue effort. In the drawings:

FIG. 1 shows a schematic diagram of an exemplary system architecture to which the technical solution of embodiments of the present disclosure may be applied;

FIG. 2 schematically illustrates a flow diagram of a method of generating a product release strategy according to one embodiment of the disclosure;

FIG. 3 schematically illustrates a structural schematic of a network diagram according to one embodiment of the present disclosure;

FIG. 4 schematically illustrates a flow diagram for obtaining an intermediate network graph according to one embodiment of the disclosure;

FIG. 5 schematically illustrates a flow diagram of recursive transfer of nodes in a sub-network graph, according to one embodiment of the disclosure;

FIG. 6 schematically illustrates a network layer structure corresponding to a sub-network diagram according to one embodiment of the present disclosure;

FIG. 7 schematically illustrates a block diagram of a generating device of a product release strategy according to one embodiment of the disclosure;

fig. 8 shows a schematic diagram of a computer system suitable for use in implementing embodiments of the present disclosure.

Detailed Description

Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many 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 the example embodiments to those skilled in the art.

Furthermore, 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 disclosed aspects may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the disclosure.

The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.

The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.

Fig. 1 shows a schematic diagram of an exemplary system architecture to which the technical solution of the embodiments of the present disclosure may be applied.

As shown in fig. 1, system architecture 100 may include a terminal device 101, a network 102, and a server 103. The terminal device 101 may specifically be a terminal device including a display screen, for example, a smart phone, a notebook, a tablet computer, a desktop computer, a portable computer, etc., and is configured to allow a product delivery party to deliver a product, and a user to obtain product information online and perform corresponding operations on the delivered product, such as downloading, purchasing, using, sharing, etc. Network 102 is a medium used to provide a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired communication links, wireless communication links, etc., and in embodiments of the present disclosure, the network between terminal device 101 and server 103 may be a wireless communication link, and in particular may be a mobile network.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. It should be noted that the server in the present disclosure may be an independent server or a server cluster formed by a plurality of servers.

In one embodiment of the present disclosure, a product delivering party may collect user interaction behaviors of all users through a terminal device 101, send the collected user information and the user interaction behaviors to a server 103 through a network, and construct a network graph according to the user information and the user interaction behaviors through the server 103, where the user information (user) is a node, sides are set between users having the user interaction behaviors, and meanwhile, a weight corresponding to the side corresponding to the user interaction behaviors is determined according to the number of the user interaction behaviors, and the network graph can be determined according to the node, the sides and the weight. The server 103 may then perform community division on the network graph, divide the network graph into a plurality of sub-network graphs according to a community division algorithm based on modularity, then determine importance of each node in the network graph for each sub-network graph, determine node importance ranking according to importance of all nodes, and the product dispenser may determine a dispensing policy according to node importance ranking fed back by the server, for example, only dispensing products for number packages of which users, or first dispensing products for number packages of which users, then dispensing products for number packages of which users, and so on. Of course, the server 103 may also determine the delivery policy according to the node importance ranking, and then feed back the delivery policy to the terminal device, so that the product delivery party performs product delivery according to the delivery policy. After determining the delivery strategy, product delivery can be performed based on the delivery strategy.

It should be noted that, the method for generating the product release policy provided by the embodiment of the present disclosure is generally executed by a server, and accordingly, the device for generating the product release policy is generally disposed in the server. However, in other embodiments of the present disclosure, the method for generating the product release policy provided by the embodiments of the present disclosure may also be performed by the terminal device.

In the field, in the actual operation process of the product, the product is limited by the consideration of resource release or user harassment reduction, certain specific user groups meeting the conditions need to be directionally released, the maximization of input-output ratio is realized on the premise of limited resources, and meanwhile, the sharing will of the users is combined, so that the activity effect is exponentially improved by the user sharing or conference spreading.

In the related art in the field, the user group to be put is often determined by means of personal experience of a product manager, the product manager outputs some rules for extracting the user group to lock the put group, a corresponding number package can be screened according to the rules, and then the product is put into the user group corresponding to the number package. From experience, the result of relying on experience decision is often not ideal, the screening of the number package based on rules is low in efficiency, cannot be automated, cannot be further learned, and the throwing effect is often not ideal.

In view of the problems existing in the related art, the embodiments of the present disclosure provide a method for generating a product release policy, where the method for generating the product release policy is implemented based on a Complex Network (Complex Network), which refers to a Network with self-organization, self-similarity, attractors, small worlds, and scale-free, partial or complete properties. The research direction of the complex network comprises three aspects of key node discovery, community discovery and link prediction, wherein the key node discovery aims at discovering nodes playing a key role in the structure and the function of the network, the community discovery aims at discovering community structures in the complex network so as to reasonably divide the composition of network nodes, and the link prediction aims at predicting the possibility of links among any nodes in the complex network.

The system according to the embodiments of the present disclosure may be a distributed system formed by connecting a terminal device of a product delivering party, and a plurality of nodes (any form of computing device in an access network, such as a server, a user terminal) through a form of network communication. Taking a distributed system as an example of a blockchain system, the distributed system is formed by a plurality of nodes (any form of computing device in an access network, such as a server and a user terminal) and terminal equipment of a product delivery party, a point-To-point (P2P, peer To Peer) network is formed between the nodes, and the P2P protocol is an application layer protocol running on top of a transmission control protocol (TCP, transmission Control Protocol) protocol. Blockchains are novel application modes of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanisms, encryption algorithms, and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, and an application services layer.

The blockchain underlying platform may include processing modules for user management, basic services, smart contracts, operation monitoring, and the like. The user management module is responsible for identity information management of all blockchain participants, including maintenance of public and private key generation (account management), key management, maintenance of corresponding relation between the real identity of the user and the blockchain address (authority management) and the like, and under the condition of authorization, supervision and audit of transaction conditions of certain real identities, and provision of rule configuration (wind control audit) of risk control; the basic service module is deployed on all block chain node devices, is used for verifying the validity of a service request, recording the service request on a storage after the effective request is identified, for a new service request, the basic service firstly analyzes interface adaptation and authenticates the interface adaptation, encrypts service information (identification management) through an identification algorithm, and transmits the encrypted service information to a shared account book (network communication) in a complete and consistent manner, and records and stores the service information; the intelligent contract module is responsible for registering and issuing contracts, triggering contracts and executing contracts, a developer can define contract logic through a certain programming language, issue the contract logic to a blockchain (contract registering), invoke keys or other event triggering execution according to the logic of contract clauses to complete the contract logic, and simultaneously provide a function of registering contract upgrading; the operation monitoring module is mainly responsible for deployment in the product release process, modification of configuration, contract setting, cloud adaptation and visual output of real-time states in product operation, for example: alarms, monitoring network conditions, monitoring node device health status, etc.

The platform product service layer provides basic capabilities and implementation frameworks of typical applications, and developers can complete the blockchain implementation of business logic based on the basic capabilities and the characteristics of the superposition business. The application service layer provides the application service based on the block chain scheme to the business participants for use.

According to the scheme provided by the embodiment of the disclosure, the data is mined based on the complex network to obtain the target seed users, and the product is put in aiming at the target seed users, so that the refined automatic operation and putting are realized, the product effect and the operation efficiency are improved, and the return on investment is improved. The following examples are provided to illustrate the invention:

fig. 2 schematically illustrates a flow chart of a method of generating a product release policy, which may be performed by a server, which may be the server 103 illustrated in fig. 1, according to one embodiment of the disclosure. Referring to fig. 2, the method for generating the product release strategy at least includes steps S210 to S230, which are described in detail as follows:

in step S210, user interaction behaviors related to a plurality of users are acquired, and a network graph is constructed according to each user and the user interaction behaviors.

In one embodiment of the present disclosure, it is first necessary to construct a complex network, which is presented in the form of a graph, containing nodes, edges, and weights for the respective edges. In the embodiment of the disclosure, user interaction behaviors related to a plurality of users can be obtained, then a network diagram is constructed according to the users and the user interaction behaviors, when the network diagram is constructed, each independent user is used as a node, edges are arranged among users with interaction relationships, the diagram can be constructed according to the nodes and the edges, then the weight of the edges corresponding to the user interaction behaviors is determined according to the number of the user interaction behaviors, and then the network diagram can be determined according to the weights of the edges and the diagram. In the embodiments of the present disclosure, the network graph may be a directed graph or an undirected graph, and directions in the directed graph are determined according to directionality of user interaction behavior, and for convenience of description, the embodiments of the present disclosure will be described below taking the undirected graph as an example of the network graph.

Fig. 3 shows a schematic diagram of a network diagram, as shown in fig. 3, there are 7 nodes numbered 1-7, the 7 nodes respectively represent 7 users, there is an interaction behavior between the users, the interaction behavior is embodied in the form of edges, specifically, the node 1 respectively has edges with the nodes 2, 3 and 6, the node 2 respectively has edges with the nodes 1, 3-7, the node 3 respectively has edges with the nodes 1, 2, 4 and 6, the node 4 respectively has edges with the nodes 2, 3, 5 and 6, the node 5 respectively has edges with the nodes 2, 4 and 7, the node 6 respectively has edges with the nodes 1-4 and 7, the node 7 respectively has edges with the nodes 2, 5 and 6, and weights corresponding to the edges are respectively present.

In the embodiment of the disclosure, in order to improve the product delivering effect, a network diagram can be constructed in combination with the sharing intention of a user, for example, when the user generates interaction or event behaviors such as message generation, approval, sharing, etc., the user is considered to have the sharing intention, when the user a sends a message to the user B, the user C approves the message shared by the user D, the user E shares the product link, etc., to the user F, the user a and the user B are considered to have the interaction behaviors between the user C and the user D, and the user E and the user F, and when the network diagram is constructed, the user having the interaction behaviors can directly set the edge. As for the weight of the edge, the determination may be specifically performed according to the number of user interaction behaviors, for example, the user A sends M messages to the user B, and the user B shares N products with the user A, and then the determination of the representation of the user A and the use of the representation in the network diagram may be performed according to the number of messages sent by the user A to the user B, the number of products shared by the user B to the user A (M+N), and the number of user interaction behaviors Q between all the usersThe weight of the edge between the nodes of the user B, such as (m+n)/Q. Of course, other calculations may be used to determine the weights, e.g., e ^(M+N)-Q Etc., embodiments of the present disclosure are not described in detail herein.

In step S220, the network map is community-divided to divide the network map into a plurality of sub-network maps.

In one embodiment of the disclosure, for a complex network, the complex network may be divided into a plurality of sub-networks by a community division manner, and further, by calculating importance degrees of nodes in each sub-network, a ranking of importance degrees of all nodes in the complex network may be obtained, and a delivery policy may be determined according to the ranking. In the embodiment of the present disclosure, when all nodes in the network graph are partitioned, the nodes may be partitioned based on Modularity (Modularity), which is also called a Modularity value, and is a method for measuring the structural strength of the network community, which is defined as:

wherein,representing all weights in the network graph, A _ij Representing the weight, k, between node i and node j _i ＝∑ _j A _ij Representing the weight of the edge connected to node i, c _i Representing the community to which node i is assigned, delta (c _i ,c _j ) And the method is used for judging whether the node i and the node j are divided into the same community, if so, returning to 1, and otherwise, returning to 0.

From the definition of the modularity, it can be seen that the modularity refers to the proportion of edges connecting nodes inside a community structure in a network, and the expected value of the proportion of any two nodes connected under the same community structure is subtracted. The magnitude of the module degree value mainly depends on the community distribution c of the nodes in the network, namely the community division condition of the network, and can be used for quantitatively measuring the network community division quality, wherein the closer the value is 1, the stronger the intensity of the community structure divided by the network is, namely the better the division quality is. An optimal web community partitioning can be obtained by maximizing the modularity Q.

In one embodiment of the disclosure, when a social division is performed on a network graph, firstly, performing community division on all nodes in the network graph, and determining an intermediate network graph according to the modularity of communities formed by the social division; and then taking all communities in the intermediate network graph as update nodes, carrying out community division on the update nodes, and determining a sub-network graph according to the modularity of all the update communities formed by the community division, wherein the sub-network graph is the finally formed community.

Fig. 4 shows a schematic flow chart of obtaining an intermediate network diagram, as shown in fig. 4, specifically as follows:

in step S401, initial community division is performed on each node in the network map to obtain an initial community corresponding to each node.

In one embodiment of the present disclosure, when each node is initially partitioned, each node may be separately partitioned into different communities, that is, each node corresponds to one community, and each community is not repeated.

In step S402, any node in the network diagram is taken as a target node, and the target node is partitioned into initial communities where nodes adjacent to the target node are located, so as to form sub-partitioned communities.

In one embodiment of the present disclosure, the formation of the sub-divided communities is essentially community merging, i.e., dividing the target node into communities where nodes adjacent thereto are located, e.g., target node a is adjacent to nodes B and C, then target node a and node B may be divided into one community, and target node a and node C may be divided into one community, respectively.

In step S403, a first modularity of the sub-divided communities and a second modularity of the initial communities where nodes adjacent to the target node are located are obtained, and the target operation is performed on the sub-divided communities according to the first modularity and the second modularity.

In one embodiment of the present disclosure, the modularity before and after the partitioning is calculated and a determination is made as to whether to accept the partitioning based on the modularity before and after the partitioning. The method comprises the steps of marking the modularity of a divided community as a first modularity, marking the modularity of an initial community where a node adjacent to a target node is located before division as a second modularity, and executing target operation on a sub-divided community according to the difference value of the first modularity and the second modularity, wherein the target operation is specifically to receive the division and discard the division, and particularly, when the difference value is a positive number, the sub-divided community is reserved; and when the difference value is not positive, discarding the sub-divided community.

In step S404, steps S402 and S403 are repeated until the modularity of the finally formed sub-divided communities is maximum, so as to obtain an intermediate network graph.

By circularly executing the above flow for all nodes in the network graph, the community with the highest modularity can be obtained. And then reconstructing the network according to the community structure generated in the previous step, and obtaining a final sub-network diagram through continuous cyclic division until the structure in the network is not changed. In the process of reconstructing the network, each community in the intermediate network graph can be reduced by using points to replace, namely each community is taken as an update node, a method adopted in the process of dividing the update nodes into communities is similar to a method for dividing the nodes in the network graph, specifically, any one of the update nodes is taken as a target update node, and the target update node is divided into communities where update nodes adjacent to the target update node are located, so that an update community is formed; acquiring a third modularity of the updated community and a fourth modularity of the community where an updated node adjacent to the target updated node is located, and executing target operation on the updated community according to the third modularity and the fourth modularity; and repeating the steps until the modularity of the finally formed updated community is maximum, and obtaining a final community structure, namely dividing the network graph into a plurality of sub-network graphs. The target operation is executed on the updated community according to the third modularity and the fourth modularity, and the difference value between the third modularity and the fourth modularity is obtained; when the difference value is positive, reserving an updated community; and when the difference value is not positive, discarding updating the community.

Because all nodes in the network diagram are subjected to community division, users corresponding to each node have a corresponding attribution community, namely circle layer division, so that the importance of the nodes in each community can be determined, and then the delivery strategy is determined. A huge complex network can be decomposed into a plurality of sub-networks through community division, so that the network structure can be simplified, and a foundation is laid for the subsequent rapid determination of the node importance.

In step S230, the importance of each node in each sub-network graph is determined, so as to determine a delivery policy according to the importance of each node, and product delivery is performed based on the delivery policy.

In one embodiment of the present disclosure, after community division is completed, an evaluation may be performed on the importance of each user in the community, and then a delivery policy may be determined according to the importance of each user. In the disclosure, the nodes in the sub-network graph are divided into different network layers by performing layer division according to the degree value and the preset degree value of the nodes in the sub-network graph, and the different network layers correspond to different core values, which means that the nodes located in the different network layers have different importance. When nodes in the sub-network graphs are divided into different network layers, specifically, nodes with all degree values smaller than or equal to the preset degree value in the sub-network graphs are recursively moved to the corresponding network layers, and it is noted that the preset degree values of the corresponding different sub-network graphs can be the same or different, and the preset degree value of each sub-network graph is smaller than or equal to the core degree value in each sub-network graph.

Fig. 5 schematically illustrates a flow chart of recursively transferring nodes in the sub-network graphs, as shown in fig. 5, in step S501, a node with a degree value N in each sub-network graph is moved to a network layer with a core value N to obtain a target sub-network graph; in step S502, it is determined whether a node with a degree value N exists in the target subnetwork diagram; in step S503, when present, a node with a degree value of N is moved to a network layer with a core value of N; in step S504, when there is no node with a degree value of n+1 in the target sub-network graph is moved to a network layer with a core value of n+1; in step S505, repeating steps S501-S504 until the degree value of each node in the core network diagram finally obtained is equal to the preset degree value; wherein N is an integer greater than or equal to 0, and N is less than or equal to a preset degree value.

Fig. 6 schematically illustrates a network layer structure corresponding to the sub-network map, and as shown in fig. 6, the map structure consisting of points and connecting lines in the map is a sub-network map, and the sub-network map is divided into multiple layers of rings as network layers, where each network layer corresponds to a different kernel value Ks. When the preset degree value corresponding to fig. 6 is the core degree value 3 in the sub-network diagram, firstly removing the node with the degree value 0 when recursively transferring the node in the sub-network diagram, and as no isolated node with the degree value 0 exists in fig. 6, continuing to remove the node with the degree value 1 (such as the node shown by the dotted circle in fig. 6), and transferring the node with the degree value 1 to the network layer with the core value ks=1; then judging whether the nodes with the degree value of 1 still exist in the target sub-network graph after removing part of the nodes, and if so (as shown by the black coil in fig. 6), continuing to transfer the nodes into a network layer with Ks=1; then still judging whether a node with a degree value of 1 exists in the new target sub-network diagram, if not, transferring the node with a degree value of 2 in the new target sub-network diagram to a network layer with a kernel value Ks=2 (such as a node shown by a solid circle in fig. 6); and then judging whether a node with the degree value of 2 exists in the target sub-network graph formed by the node with the degree value of 2, if yes, continuing to transfer to a network layer with Ks=2, if no, transferring the node with the degree value of 3 to a network layer with the core value Ks=3, wherein the core degree value of the sub-network graph in fig. 6 is 3, and the maximum preset degree value is 3, and the maximum degree value of the removable node is 3, so that the decomposition of the sub-network graph is completed, and a structure comprising three network layers is obtained, and the distribution of the nodes in each network layer is particularly shown in fig. 6.

In one embodiment of the present disclosure, the importance of a node is positively correlated with the core value of the network layer where the node is located, so that the importance of each node in each sub-network graph can be determined according to the core value of the network layer where each node is located. As a specific embodiment, the importance of the node may be the same as the core value of the network layer where the node is located, for example, the importance of the node shown by the dotted and black circles in fig. 6 is 1, the importance of the node shown by the solid circles is 2, the importance of the remaining nodes is 3, and of course, the importance of the node may be determined according to other calculation methods, for example, according to the aKs +b mode, where a and b are constants, ks is the core value of the network layer where the node is located, and so on, which is not specifically limited in the embodiments of the disclosure.

In one embodiment of the present disclosure, after determining the importance of each node in each sub-network graph, the nodes may be ranked according to the importance of each node, and then a delivery policy is determined according to the ranking, where determining the delivery policy means that the target user is determined, then further the number package of the target user may be obtained, and automatic product delivery may be performed according to the obtained number package of the target user. Specifically, the importance of each node may be ranked in order from large to small to obtain a node importance ranking, and then the delivery policy is determined according to the node importance ranking. It should be noted that, there may be multiple nodes with the same importance, and then the priorities corresponding to the nodes with the same importance are the same, and further taking fig. 6 as an example, the node importance ranks in order as follows: the node at the network layer with ks=3 > and the node at the network layer with ks=2 > are nodes at the network layer with ks=1, so that when the user is put in, the user corresponding to the node at the network layer with ks=3 is put in preferentially, the user corresponding to the node at the network layer with ks=2 is inferior, and the user corresponding to the node at the network layer with ks=1 is lowest in priority. In the embodiment of the present disclosure, the delivery policy is specifically set by the product delivery party according to the node importance ranking and the delivery resource, for example, when the delivery resource is less, the product delivery may be performed only for the user corresponding to the node with the greatest importance, when the delivery resource is more, the product delivery may be performed for the user corresponding to the node with the greatest importance and the next greatest importance, etc., and the embodiment of the present disclosure is not specifically limited with respect to the specific form of the delivery policy.

Next, in order to make the technical solution of the present disclosure clearer, a scenario of delivering a WeChat payment product is taken as an example, and embodiments of the present disclosure are described in detail.

On the premise of limited release resources, it is impractical to release WeChat payment products for each WeChat user, so that WeChat payment product release parties need to popularize in a large area by means of sharing behaviors of users, in this case, the product release parties need to collect interaction behaviors of all WeChat users through a WeChat platform, such as the behaviors of users sending messages to other users, sharing products, and praying for sharing of other users, and the like. After the user interaction behaviors of all users are obtained, a network diagram is constructed according to each user and the user interaction behaviors related to each user, then community division can be carried out based on the network diagram, the importance degree of nodes in each sub-network diagram formed by the division can be calculated and sequenced, so that node importance degree sequencing corresponding to each sub-network diagram is obtained, finally a corresponding throwing strategy can be determined based on the node importance degree, after the throwing strategy is determined, a WeChat payment product throwing party can grab a number packet of a target user group, and the WeChat payment product is thrown aiming at the target user group corresponding to the number packet, so that the large-scale popularization of the products can be realized through sharing of the users in the target user group, and the maximization of input and output is realized. It should be noted that, in the WeChat platform, the user may send a message to one or more WeChat groups or circles of friends or share a product link, etc., and when it is determined that the user has interactive behavior, user confirmation is performed according to which users view the message or open the product link, and the user who does not view the message or open the product link is not used as a node in the network diagram. After the technical scheme of the embodiment of the disclosure is applied to the WeChat payment product operation and release system, the operation efficiency of product release and the product growth are over 50%, and the method has remarkable effects.

According to the method for generating the product release strategy in the embodiment of the disclosure, firstly, user interaction behaviors related to a plurality of users are obtained, a network diagram is constructed according to the users and the user interaction behaviors, then community division is carried out on the network diagram to form a plurality of sub-network diagrams, finally, the importance degree of each node in each sub-network diagram is determined, the release strategy is determined according to the importance degree of each node, and further product release is carried out based on the release strategy. According to the technical scheme, on one hand, a target user group and priority ordering with stronger sharing will in the sub-network diagram can be determined through an automatic data method, so that automatic product delivery strategy generation and accurate automatic product delivery are realized, and errors of experience sense and manual judgment of a product manager are avoided; on the other hand, by carrying out product delivery on users with sharing will, the users with low sharing will and no sharing will are prevented from carrying out product delivery, and further unnecessary user harassment is avoided; on the other hand, the method and the device can help products and business teams to improve operation efficiency and drive products to increase, improve product release efficiency and accuracy, and maximize input-output ratio.

The following describes an embodiment of an apparatus of the present disclosure, which may be used to execute a method for generating a product delivery policy in the foregoing embodiment of the present disclosure. For details not disclosed in the embodiments of the apparatus of the present disclosure, please refer to an embodiment of a method for generating a product release policy described in the present disclosure.

Fig. 7 schematically illustrates a block diagram of a generating device of a product release strategy according to one embodiment of the disclosure.

Referring to fig. 7, a generating apparatus 700 of a product delivery policy according to an embodiment of the present disclosure includes: a network graph construction module 701, a community division module 702 and a delivery policy generation module 703.

The network diagram construction module 701 is configured to obtain user interaction behaviors related to a plurality of users, and construct a network diagram according to each user and the user interaction behaviors; a community division module 702, configured to perform community division on the network graph, so as to divide the network graph into a plurality of sub-network graphs; and the delivery strategy generation module 703 is configured to determine importance of each node in each sub-network graph, determine a delivery strategy according to the importance of each node, and perform product delivery based on the delivery strategy.

In one embodiment of the disclosure, the network graph construction module is configured to: taking the users as nodes, setting edges between the users with interactive relations, and constructing a graph according to the nodes and the edges; and determining the weight of the edge corresponding to the user interaction behavior according to the number of the user interaction behaviors, and determining the network graph according to the weight of the edge and the graph.

In one embodiment of the present disclosure, the community dividing module includes: the first community dividing unit is used for dividing communities of all nodes in the network graph, and determining an intermediate network graph according to the modularity of communities formed by the community division; and the second community dividing unit is used for taking all communities in the intermediate network graph as update nodes, dividing the update nodes into communities, and determining the sub-network graph according to the modularity of all update communities formed by the community division.

In one embodiment of the present disclosure, the first community dividing unit includes: an initial division unit, configured to perform initial community division on each node in the network graph, so as to obtain an initial community corresponding to each node; a subdivision unit, configured to divide, with any node in the network map as a target node, the target node into initial communities where nodes adjacent to the target node are located, so as to form subdivision communities; the module degree comparison unit is used for acquiring a first module degree of the sub-divided communities and a second module degree of an initial community where a node adjacent to the target node is located, and executing target operation on the sub-divided communities according to the first module degree and the second module degree; and the repeated dividing unit is used for repeating the functions of the sub-dividing unit and the modularity comparing unit until the modularity of the finally formed sub-dividing community is maximum, so as to obtain the intermediate network graph.

In one embodiment of the present disclosure, the modularity comparing unit is configured to: obtaining a difference between the first modularity and the second modularity; when the difference value is positive, reserving the sub-division communities; and discarding the sub-divided communities when the difference value is not positive.

In one embodiment of the present disclosure, the second community dividing unit includes: an update community forming unit, configured to take any one of the update nodes as a target update node, and divide the target update node into communities where update nodes adjacent to the target update node are located, so as to form an update community; the module degree comparison unit is used for acquiring a third module degree of the updated community and a fourth module degree of the community where the updated node adjacent to the target updated node is located, and executing target operation on the updated community according to the third module degree and the fourth module degree; and the repeated dividing unit is used for repeatedly updating the functions of the community forming unit and the modularity comparing unit until the modularity of the finally formed updated community is maximum.

In one embodiment of the present disclosure, the modularity comparing unit is configured to: obtaining a difference between the third modularity and the fourth modularity; when the difference value is positive, reserving the updated community; and discarding the updated community when the difference value is not positive.

In one embodiment of the disclosure, the delivery policy generation module includes: the node transfer unit is used for recursively transferring nodes with all degree values smaller than or equal to a preset degree value in each sub-network diagram to a corresponding network layer, wherein the preset degree value is smaller than or equal to a core degree value in each sub-network diagram; and the importance determining unit is used for determining the importance corresponding to the node according to the core value of the network layer where the node is located.

In one embodiment of the disclosure, the node transfer unit is configured to: moving the node with the degree value of N in each sub-network graph to a network layer with the core value of N so as to obtain a target sub-network graph; judging whether a node with a degree value of N exists in the target sub-network diagram; when the node with the degree value of N exists, the node with the degree value of N is moved to the network layer with the core value of N; when the node with the degree value of N+1 in the target sub-network diagram does not exist, moving the node with the degree value of N+1 to a network layer with the core value of N+1; repeating the steps until the degree value of each node in the finally obtained core network diagram is equal to the preset degree value; wherein N is an integer greater than or equal to 0, and N is less than or equal to the preset value.

In one embodiment of the present disclosure, the importance of the node is positively correlated with the core value of the network layer at which the node is located.

In one embodiment of the disclosure, the delivery policy generation module is further configured to: sequencing the importance of each node from big to small to obtain node importance sequencing; and determining the delivery strategy according to the node importance degree sequence.

It should be noted that, the computer system 800 of the electronic device shown in fig. 8 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present disclosure.

As shown in fig. 8, the computer system 800 includes a central processing unit (Central Processing Unit, CPU) 801 that can perform various appropriate actions and processes according to a program stored in a Read-Only Memory (ROM) 802 or a program loaded from a storage section 808 into a random access Memory (Random Access Memory, RAM) 803, implementing the search string processing method described in the above embodiment. In the RAM 803, various programs and data required for system operation are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other by 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, mouse, etc.; an output portion 807 including a Cathode Ray Tube (CRT), a liquid crystal display (Liquid Crystal Display, LCD), and the like, and a speaker, and the like; a storage section 808 including a hard disk or the like; and a communication section 809 including a network interface card such as a LAN (Local Area Network ) card, modem, or the like. The communication section 809 performs communication processing via a network such as the internet. The drive 810 is also connected to the I/O interface 805 as needed. 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 needed so that a computer program read out therefrom is mounted into the storage section 808 as needed.

In particular, according to embodiments of the present disclosure, the processes described below with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure 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 shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. When executed by a Central Processing Unit (CPU) 801, performs the various functions defined in the system of the present disclosure.

It should be noted that, the computer readable medium shown in the embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any 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 (Erasable Programmable Read Only Memory, EPROM), 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 context of this 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 the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. 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, wired, etc., or any suitable combination of the foregoing.

The flowcharts 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.

The units involved in the embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.

As another aspect, the present disclosure also provides a computer-readable medium that may be contained in the electronic device described in the above embodiments; or may exist alone without being incorporated into the electronic device. The computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement the methods described in the above embodiments.

It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.

From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present disclosure.

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 disclosure is intended to cover any adaptations, uses, or adaptations of the disclosure following the general 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 is to be understood that the present disclosure is not limited to the precise arrangements and instrumentalities shown in the drawings, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. The method for generating the product release strategy is characterized by comprising the following steps:

obtaining sharing behaviors related to a plurality of users, wherein the sharing behaviors comprise sending a message, sharing product links or praying for sharing of other users;

taking the users as nodes, setting edges between the users with interactive relations, and constructing a graph according to the nodes and the edges; removing the user from the graph if the user does not view the message or open the product link;

Determining the weight of edges between two users according to the number of sharing behaviors between the two users and the number of sharing behaviors between all the users, and determining a network diagram according to the weight of the edges and the diagram, wherein the network diagram is used for representing the sharing willingness of the users;

performing community division on the network graph to divide the network graph into a plurality of sub-network graphs;

determining importance of each node in each sub-network graph, determining a delivery strategy according to the importance of each node, and delivering products based on the delivery strategy.

2. The method of claim 1, wherein said community partitioning the network graph to partition the network graph into a plurality of sub-network graphs comprises:

dividing communities for all nodes in the network graph, and determining an intermediate network graph according to the modularity of communities formed by the division of communities;

and taking all communities in the intermediate network graph as update nodes, dividing the update nodes into communities, and determining the sub-network graph according to the modularity of all update communities formed by the community division.

3. The method of claim 2, wherein the community division is performed on all nodes in the network graph, and determining the intermediate network graph according to the modularity of communities formed by the community division comprises:

Step a, carrying out initial community division on each node in the network graph to obtain an initial community corresponding to each node;

b, taking any node in the network diagram as a target node, and dividing the target node into initial communities where nodes adjacent to the target node are located so as to form sub-divided communities;

step c, obtaining a first modularity of the sub-divided communities and a second modularity of an initial community where a node adjacent to the target node is located, and executing target operation on the sub-divided communities according to the first modularity and the second modularity;

and d, repeating the step b and the step c until the modularity of the finally formed sub-division communities is maximum, so as to obtain the intermediate network graph.

4. The method of claim 3, wherein the performing a target operation on the sub-partitioned communities according to the first modularity and the second modularity comprises:

obtaining a difference between the first modularity and the second modularity;

when the difference value is positive, reserving the sub-division communities;

and discarding the sub-divided communities when the difference value is not positive.

5. A method according to claim 3, wherein said community division of the update node with each community in the intermediate network graph as an update node comprises:

taking any one of the update nodes as a target update node, and dividing the target update node into communities where update nodes adjacent to the target update node are located so as to form an update community;

acquiring a third modularity of the updated community and a fourth modularity of the community where an updated node adjacent to the target updated node is located, and executing target operation on the updated community according to the third modularity and the fourth modularity;

repeating the steps until the modularity of the finally formed updated community is maximum.

6. The method of claim 5, wherein said performing a target operation on said updated community according to said third and fourth modularities comprises:

obtaining a difference between the third modularity and the fourth modularity;

when the difference value is positive, reserving the updated community;

and discarding the updated community when the difference value is not positive.

7. The method of claim 1, wherein determining the importance of each node in each of the sub-network graphs comprises:

recursively moving all nodes with the degree value smaller than or equal to a preset degree value in each sub-network diagram to a corresponding network layer, wherein the preset degree value is smaller than or equal to a core degree value in each sub-network diagram;

and determining importance corresponding to the node according to the core value of the network layer where the node is located.

8. The method of claim 7, wherein recursively moving nodes in each of the sub-network graphs having all degree values less than or equal to a preset degree value to a corresponding network layer comprises:

moving the node with the degree value of N in each sub-network graph to a network layer with the core value of N so as to obtain a target sub-network graph;

judging whether a node with a degree value of N exists in the target sub-network diagram;

when the node with the degree value of N exists, the node with the degree value of N is moved to the network layer with the core value of N;

when the node with the degree value of N+1 in the target sub-network diagram does not exist, moving the node with the degree value of N+1 to a network layer with the core value of N+1;

repeating the steps until the degree value of each node in the finally obtained core network diagram is equal to the preset degree value;

Wherein N is an integer greater than or equal to 0, and N is less than or equal to the preset value.

9. The method of claim 7, wherein the importance of the node is positively correlated with a core value of a network layer at which the node is located.

10. The method of claim 1, wherein said determining a delivery policy based on importance of each of said nodes comprises:

sequencing the importance of each node from big to small to obtain node importance sequencing;

and determining the delivery strategy according to the node importance degree sequence.

11. A device for generating a product release strategy, comprising:

the network diagram construction module is used for acquiring sharing behaviors related to a plurality of users, wherein the sharing behaviors comprise sending messages, sharing product links or praying for sharing of other users; taking the users as nodes, setting edges between the users with interactive relations, and constructing a graph according to the nodes and the edges; removing the user from the graph if the user does not view the message or open the product link; determining the weight of edges between two users according to the number of sharing behaviors between the two users and the number of sharing behaviors between all the users, and determining a network diagram according to the weight of the edges and the diagram, wherein the network diagram is used for representing the sharing willingness of the users;

The community division module is used for carrying out community division on the network graph so as to divide the network graph into a plurality of sub-network graphs;

and the delivery strategy generation module is used for determining the importance degree of each node in each sub-network diagram, determining the delivery strategy according to the importance degree of each node, and delivering the product based on the delivery strategy.

12. A computer readable medium on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements a method of generating a product delivery strategy according to any of claims 1 to 10.

13. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of generating a product delivery strategy as claimed in any one of claims 1 to 10.