Service resource recommendation method and device, equipment, medium and program product

Abstract

The embodiment of the invention discloses a service resource recommendation method and device, equipment, a medium and a program product. The method comprises the following steps: constructing a knowledge graph based on multiple pieces of user data, multiple pieces of first service resource data and multiple pieces of second service resource data; based on the knowledge graph, mapping the first service resource and the second service resource as the same class of nodes to obtain a bipartite graph network, and segmenting the bipartite graph network to obtain a user relationship network; performing user clustering based on the user relationship network to obtain a plurality of user groups, and determining a target user group where a first user is located based on the to-be-recommended first user and the plurality of user groups; in the embodiment of the invention, the target service resource recommended to the first user is determined based on the first existing service resource existing in the first user and the second existing service resource existing in the second user except the first user in the target user group, so that the calculation complexity and the calculation amount of service resource recommendation are reduced, and the recommendation efficiency is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to computer technology, and more particularly to a service resource recommendation method, apparatus, device, medium, and program product. Background Technology

[0002] Service resources are business resources that provide specific services to users. For example, in the telecommunications industry, service resources may include voice packages, data packages, broadband discounts, cloud gaming, and video ringback tones.

[0003] Existing service resource recommendation methods typically rely on neural network models to determine the services recommended to users. However, due to the massive scale of both the user base and the available service resources (e.g., tens of millions of users and billions of services), and the lack of large-scale reasoning capabilities in neural network models, it is difficult to guarantee the efficiency of service resource recommendations using neural network models. Summary of the Invention

[0004] This invention provides a service resource recommendation method, apparatus, device, medium, and program product to reduce the computational complexity and computational load of service resource recommendation, thereby improving the efficiency of service resource recommendation.

[0005] In a first aspect, embodiments of the present invention provide a service resource recommendation method, including:

[0006] Based on multiple user data corresponding to multiple users, multiple first service resource data corresponding to multiple first service resources, and multiple second service resources corresponding to multiple second service resources, a knowledge graph is constructed with the users, the first service resources, and the second service resources as nodes;

[0007] Based on the knowledge graph, the first service resource and the second service resource are mapped as nodes of the same type to obtain a bipartite graph network containing users and service resources, and the bipartite graph network is segmented to obtain a user relationship network.

[0008] User clustering is performed based on the user relationship network to obtain multiple clustered user groups, and the target user group to which the first user belongs is determined based on the first user to be recommended and the multiple user groups.

[0009] Based on the first existing service resources already possessed by the first user and the second existing service resources already possessed by the second users in the target user group other than the first user, the target service resources recommended to the first user are determined.

[0010] Secondly, embodiments of the present invention also provide a service resource recommendation device, comprising:

[0011] The knowledge graph construction module is used to construct a knowledge graph with the users, the first service resources, and the second service resources as nodes, based on multiple user data corresponding to multiple users, multiple first service resource data corresponding to multiple first service resources, and multiple second service resource data corresponding to multiple second service resources.

[0012] The user relationship network determination module is used to map the first service resource and the second service resource as nodes of the same type based on the knowledge graph to obtain a bipartite graph network containing users and service resources, and to segment the bipartite graph network to obtain a user relationship network.

[0013] The user group determination module is used to perform user clustering based on the user relationship network to obtain multiple clustered user groups, and to determine the target user group to which the first user belongs based on the first user to be recommended and the multiple user groups.

[0014] The target service resource determination module is used to determine the target service resources to be recommended to the first user based on the first existing service resources already existing to the first user and the second existing service resources already existing to the second users in the target user group other than the first user.

[0015] Thirdly, embodiments of the present invention also provide an electronic device, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the service resource recommendation method provided in any embodiment of the present invention.

[0019] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute and implement the service resource recommendation method provided in any embodiment of the present invention.

[0020] Fifthly, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the service resource recommendation method as provided in any embodiment of the present invention.

[0021] One embodiment of the above invention has the following advantages or beneficial effects:

[0022] By constructing a knowledge graph with users, first service resources, and second service resources as nodes based on multiple user data, multiple first service resource data, and multiple second service resource data, and mapping the first and second service resources as nodes of the same type based on the knowledge graph, a bipartite graph network containing only users and service resources is obtained. This bipartite graph network is then segmented to quickly obtain the user relationship network. User clustering is performed based on the user relationship network to obtain multiple clustered user groups. Based on the first user to be recommended and the multiple user groups, the target user group to which the first user belongs is determined. Furthermore, based on the first user's existing first service resources and the second existing second service resources of the second users in the target user group (excluding the first user), the target service resources to be recommended to the first user can be quickly and accurately determined. This utilizes the knowledge graph to reduce the computational complexity and amount of computation for service resource recommendation, thereby improving the recommendation efficiency.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a service resource recommendation method provided in one embodiment of the present invention;

[0026] Figure 2 This is an example diagram of nodes and edges in a knowledge graph according to an embodiment of the present invention;

[0027] Figure 3 This is an example diagram of a knowledge graph according to an embodiment of the present invention;

[0028] Figure 4 This is an example diagram of a bipartite graph network according to an embodiment of the present invention;

[0029] Figure 5 This is an example diagram of a user relationship network according to an embodiment of the present invention;

[0030] Figure 6 This is a flowchart of another service resource recommendation method provided in one embodiment of the present invention;

[0031] Figure 7 This is a schematic diagram of the structure of a service resource recommendation device provided in one embodiment of the present invention;

[0032] Figure 8 This is a schematic diagram of the structure of an electronic device that implements the service resource recommendation method of this invention. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0035] It should be noted that the collection, updating, analysis, use, transmission, and storage of user personal information involved in the technical solution disclosed herein (such as the collection and use of user identifiers, user's region, and existing service resource information) all comply with relevant laws and regulations, are used for legitimate and reasonable purposes, and are not shared, disclosed, or sold outside of these legitimate uses, and are subject to supervision and management by national regulatory authorities. Necessary measures should be taken to selectively block the use or access to personal information data to prevent unauthorized access to such personal information data, ensure that personnel authorized to access personal information data comply with relevant laws and regulations, and ensure the security of user personal information. Furthermore, once this user personal information data is no longer needed, the risk should be minimized by restricting or even prohibiting data collection and / or deleting the data.

[0036] Figure 1This is a flowchart illustrating a service resource recommendation method according to an embodiment of the present invention. This embodiment is applicable to situations where target service resources are automatically determined and recommended to users. The method can be executed by a service resource recommendation device, which can be implemented in software and / or hardware, and can be configured in an electronic device. Figure 1 As shown, the method specifically includes the following steps:

[0037] S110. Based on multiple user data corresponding to multiple users, multiple first service resource data corresponding to multiple first service resources, and multiple second service resource data corresponding to multiple second service resources, construct a knowledge graph with users, first service resources, and second service resources as nodes.

[0038] In this context, "user" refers to all existing users. "Multiple user data" includes the user data for each individual user. "First service resource" and "second service resource" refer to two pre-defined categories of service resources. Each service resource category contains multiple different service resources, such as multiple different first service resources and multiple different second service resources. Each first service resource and each second service resource is pre-configured based on business needs. "Multiple first service resource data" includes the first service resource data corresponding to each first service resource. "Multiple second service resource data" includes the second service resource data corresponding to each second service resource. For example, in the telecom operator industry, "first service resource" can refer to product service resources, and "second service resource" can refer to promotional service resources. Product service resources can include different product service resources such as "10 yuan data package," "data service package," and "IoT card payment function." Promotional service resources can include different promotional service resources such as "community discount - X community," "IoT function fee X yuan," and "monthly agreement X yuan, free broadband package."

[0039] For example, multiple user data may include, but are not limited to: a user identifier corresponding to each user, the user's region, and the user's existing service resource information. The user identifier is a unique identifier used to distinguish different users, and may be a user code or user number, etc. The user's region may refer to the user's account opening location. The user's existing service resource information may include the user's existing first service resource information and second service resource information. The user's existing first service resource information may refer to information about a first service resource that the user has subscribed to. The user's existing second service resource information may refer to information about a second service resource that the user has subscribed to. For example, the user's existing service resource information includes: the first service resource code, existing start time, and existing end time corresponding to the user's existing first service resource, and the second service resource code, start time, and end time corresponding to the user's existing second service resource. The existing start time and existing end time can be used to represent the start and end times of the service resource subscribed by the user.

[0040] For example, multiple first service resource data may include, but are not limited to: the first service resource code, first service resource name, first service resource publishing area, and mutually exclusive first service resource information corresponding to each first service resource. The first service resource code can be coding information used to distinguish different first service resources. The first service resource publishing area refers to the geographical area where the first service resource can be processed. Mutually exclusive first service resource information refers to information about other first service resources that are mutually exclusive with the first service resource. A user cannot simultaneously possess two mutually exclusive first service resources; that is, these two first service resources cannot be processed at the same time. For example, mutually exclusive first service resource information may include, but is not limited to: the first service resource code corresponding to the mutually exclusive first service resource, the mutually exclusive area, the mutual exclusion start time, and the mutual exclusion end time. The mutually exclusive area refers to the area where the mutual exclusion exists. The mutual exclusion start time and mutual exclusion end time are the start and end times used to characterize the mutual exclusion between two first service resources.

[0041] For example, multiple second service resource data may include, but are not limited to: a second service resource code corresponding to each second service resource, a second service resource name, a second service resource publishing area, mutually exclusive second service resource information, and a first service resource to which the second service resource belongs. The second service resource code may be coding information used to distinguish different second service resources. The second service resource publishing area refers to the geographical area where the second service resource can be processed. Mutually exclusive second service resource information refers to information about other second service resources that are mutually exclusive with the second service resource. A user cannot simultaneously possess two mutually exclusive second service resources; that is, these two second service resources cannot be processed at the same time. For example, mutually exclusive second service resource information may include, but is not limited to: the second service resource code corresponding to the mutually exclusive second service resource, the mutually exclusive area, the mutual exclusion start time, and the mutual exclusion end time. The mutually exclusive area refers to the area where the mutual exclusion exists. The mutual exclusion start time and mutual exclusion end time are the start and end times used to characterize the mutual exclusion between the two second service resources. The first service resource to which the second service resource belongs refers to the first service resource to which the second service resource belongs. It should be noted that some secondary service resources may belong to some primary service resources, and they are pre-configured based on business needs. For example, the secondary service resource "Community Discount - Community X" belongs to the primary service resource "Province-wide X Yuan Module X Months".

[0042] Specifically, a knowledge graph can be constructed based on all user data, all first service resource data, and all second service resource data, with users, first service resources, and second service resources as nodes, and the user data, first service resource data, and second service resource data can be loaded into the knowledge graph.

[0043] For example, Figure 2 An example graph of nodes and edges in a knowledge graph is given, such as Figure 2 As shown, the constructed knowledge graph contains three types of nodes: user nodes, first service resource nodes, and second service resource nodes. The constructed knowledge graph also contains five types of edges: edges already existing in the first service resource, edges already existing in the second service resource, mutually exclusive edges between first service resources, mutually exclusive edges between second service resources, and edges belonging to the second service resource.

[0044] In this context, an "existing edge of the first service resource" refers to a connection between a user node and a first service resource node, representing an existing relationship between the user and the first service resource. For example, if a user subscribes to a first service resource, the resulting edge is an "existing edge of the first service resource." Similarly, an "existing edge of the second service resource" refers to a connection between a user node and a second service resource node, representing an existing relationship between the user and the second service resource. For example, if a user subscribes to a second service resource, the resulting edge is an "existing edge of the second service resource." A "mutually exclusive edge between first service resources" refers to a connection between two first service resource nodes, representing a mutually exclusive relationship between them. A "mutually exclusive edge between second service resources" refers to a connection between two second service resource nodes, representing a mutually exclusive relationship between them. A "belonging edge of the second service resource" refers to a connection between a first service resource node and a second service resource node, representing that the second service resource belongs to the first service resource.

[0045] All user data, all first-service resource data, and all second-service resource data are loaded into the knowledge graph to obtain the node attribute data corresponding to each node in the knowledge graph. Figure 3 An example graph of a knowledge graph is given, such as Figure 3 As shown, the edge belonging to the second service resource is an attribute-free edge, requiring no data loading. A knowledge graph encompassing all users and all service resources is constructed using three types of entity points and five types of relation edges.

[0046] In some optional implementations, the method further includes: periodically detecting the validity of mutually exclusive edges between first service resources in the knowledge graph based on the mutual exclusion end time in the information of first service resources with mutual exclusion relationships, and deleting invalid mutually exclusive edges between first service resources; and periodically detecting the validity of mutually exclusive edges between second service resources in the knowledge graph based on the mutual exclusion end time in the information of second service resources with mutual exclusion relationships, and deleting invalid mutually exclusive edges between second service resources.

[0047] Specifically, since mutual exclusion relationships have time periods, it is necessary to periodically check whether the mutual exclusion end time has been reached, and to regard the mutual exclusion edges between the first service resources and the mutual exclusion edges between the second service resources that have reached the mutual exclusion end time as invalid edges. At this time, the invalid mutual exclusion edges can be automatically deleted through the deletion function of the graph database, thereby ensuring the accuracy of the knowledge graph.

[0048] S120. Based on the knowledge graph, the first service resource and the second service resource are mapped as nodes of the same type to obtain a bipartite graph network containing users and service resources, and the bipartite graph network is segmented to obtain a user relationship network.

[0049] A bipartite graph network is a network containing only two types of nodes. In this embodiment, the two types of nodes in the bipartite graph network are user nodes and service resource nodes. Both the first and second service resources are classified as the same type of node, namely, service resource nodes. A user relationship network is a graph network containing only user nodes. It is used to represent the relationships between users.

[0050] Specifically, by treating the first and second service resources as similar service resource nodes, the constructed knowledge graph is mapped to obtain a bipartite graph network containing only user nodes and service resource nodes. For example, Figure 4 An example diagram of a bipartite graph network is given. Figure 4 It contains 4 user nodes (nodes 1, 2, 3, and 4) and 11 service resource nodes (nodes A, B, C, D, E, F, G, H, I, J, and K). The edges in the bipartite graph network represent existing relationships between users and service resources. It should be noted that this embodiment only considers the connections between user nodes and the first service resource node, and the connections between user nodes and the second service resource node; it does not need to consider the connections between the first and second service resource nodes, or the connections between the first and second service resource nodes.

[0051] After obtaining the bipartite graph network, the network is segmented through graph projection transformation to obtain a single-partite graph containing only user nodes, thus obtaining the user relationship network. Since there are no direct relationships between users in the knowledge graph, lossless extraction of user relationships and rapid construction of undirected homogeneous networks can be achieved through knowledge graph mapping transformation.

[0052] In some optional implementations, step S120, "segmenting the bipartite graph network to obtain a user relationship network," may include: for every two user nodes in the bipartite graph network, determining the number of service resources in the bipartite graph network that are simultaneously connected to these two user nodes; if the number of service resources is greater than or equal to 1, then connecting the two user nodes to obtain an undirected edge between them, and using the number of service resources as the edge weight of the undirected edge to construct the user relationship network.

[0053] Specifically, for each pair of user nodes in a bipartite graph network, we can check if these two user nodes are connected to the same service resource node. If they are, it means that the two users share the same service resource, and in this case, the two user nodes are connected, with the number of shared service resources used as the edge weight. If the two user nodes are not connected to any service resource node, it means that the two users do not share the same service resource, and in this case, the two user nodes do not need to be connected. For example, Figure 5 An example diagram of a user relationship network is given. Figure 5 Yes Figure 4 This was obtained by segmenting a bipartite graph network. See [link / reference]. Figure 4 and Figure 5 ,for Figure 4 For nodes 1 and 2 in the network, nodes B and D are connected to both nodes 1 and 2. In this case, in the user relationship network, nodes 1 and 2 are connected, and the edge weight between them is set to 2. Similarly, the weight of the edge is determined... Figure 4 By analyzing whether any two other nodes are connected and their corresponding edge weights, a user relationship network can be constructed, such as... Figure 5 As shown.

[0054] S130. Perform user clustering based on user relationship network to obtain multiple user groups after clustering, and determine the target user group to which the first user belongs based on the first user to be recommended and multiple user groups.

[0055] In this context, "all users in a user group" refers to users with similar ordering records. A user group can be viewed as a set of users with similar preferences. The first user refers to any user who needs recommended service resources.

[0056] Specifically, based on community identification algorithms, user nodes in the user relationship network are clustered to identify closely connected communities. Each community represents a user group, thus obtaining all clustered user groups. The first user identifier corresponding to the first user to be recommended can be matched with the user identifiers contained in each user group to determine the target user group containing the first user identifier, thereby obtaining the target user group to which the first user belongs.

[0057] In some optional implementations, step S130, "clustering users based on user relationship networks to obtain multiple clustered user groups", may include: using the Leuven algorithm to identify communities based on user relationship networks, and treating each identified community as a user group.

[0058] The Louvain algorithm uses modularity to measure the quality of a community partition. It identifies communities for user nodes in a user relationship network as follows: Each user node is treated as an independent community. All nodes are traversed, and the modularity increment required to move them to an adjacent community is calculated. The maximum modularity increment is determined. If the maximum modularity increment is greater than 0, the node is moved to the adjacent community corresponding to the maximum modularity increment; otherwise, the node is not moved. When the communities of all nodes no longer change, all nodes in the same community are merged into a new node. Based on the merged network, nodes are moved again in the same manner until the overall modularity of the network remains unchanged. Each community obtained at this point is considered a user group.

[0059] S140. Based on the first existing service resources already available to the first user and the second existing service resources already available to the second users in the target user group other than the first user, determine the target service resources to recommend to the first user.

[0060] The first existing service resource includes the first service resource already owned by the first user and the second service resource already owned by the first user. The second user refers to other users in the target user group besides the first user. The second user is a user similar to the first user. The second existing service resource includes the first service resource already owned by the second user and the second service resource already owned by the second user. The target service resource may include the first service resource and / or the second service resource recommended to the first user.

[0061] Specifically, the first existing service resource can be removed from the second existing service resource to obtain a second existing service resource that the first user does not own but the second user does. The remaining second existing service resource after removal can be determined as the target service resource to be recommended to the first user.

[0062] In some optional implementations, step S140 may include: filtering the second existing service resources of the second users (excluding the first user) in the target user group based on the first existing service resources already possessed by the first user, to obtain second existing service resources that do not contain the first existing service resources; aggregating the filtered second existing service resources to obtain each type of candidate service resource already possessed by the second user and the number of users corresponding to each candidate service resource; determining the recommendation level corresponding to each candidate service resource based on the number of users, and determining the target service resource to recommend to the first user from the candidate service resources based on the recommendation level.

[0063] Here, "service resources to be selected" refers to service resources that the first user does not possess but the second user does, which may include either the first or the second service resources. The number of users corresponding to the service resources to be selected refers to the number of second users who possess the same service resource to be selected.

[0064] Specifically, the first existing service resources contained in the second existing service resources are filtered to obtain second existing service resources that do not contain the first existing service resources. Since different second users may have the same service resources, it is necessary to aggregate the filtered second existing service resources to obtain each type of candidate service resource that the second user already has and the number of users corresponding to each type of candidate service resource. The number of users corresponding to each type of candidate service resource can be divided by the total number of second users, and the result is used as the recommendation level of the candidate service resource. Based on the recommendation level, all candidate service resources are sorted in descending order, and the top preset number of candidate service resources after sorting are determined as target service resources so as to recommend matching target service resources to the first user.

[0065] The technical solution of this embodiment constructs a knowledge graph with users, first service resources, and second service resources as nodes based on multiple user data, multiple first service resource data, and multiple second service resource data. Based on the knowledge graph, the first and second service resources are mapped as nodes of the same type, resulting in a bipartite graph network containing only users and service resources. This bipartite graph network is then segmented to quickly obtain the user relationship network. User clustering is performed based on the user relationship network to obtain multiple clustered user groups. Based on the first user to be recommended and the multiple user groups, the target user group to which the first user belongs is determined. Based on the first user's existing first service resources and the second existing second service resources of the second users in the target user group (excluding the first user), the target service resources to be recommended to the first user can be quickly and accurately determined. This utilizes the knowledge graph to reduce the computational complexity and amount of computation for service resource recommendation, thereby improving the efficiency of service resource recommendation.

[0066] Figure 6 This is a flowchart illustrating another service resource recommendation method according to an embodiment of the present invention. This embodiment describes in detail the process of performing mutual exclusion verification on target service resources, based on the above embodiments. Explanations of terms that are the same as or corresponding to those in the above embodiments are not repeated here.

[0067] See Figure 6 Another service resource recommendation method provided in this embodiment specifically includes the following steps:

[0068] S210. Based on multiple user data corresponding to multiple users, multiple first service resource data corresponding to multiple first service resources, and multiple second service resource data corresponding to multiple second service resources, construct a knowledge graph with users, first service resources, and second service resources as nodes.

[0069] S220. Based on the knowledge graph, the first service resource and the second service resource are mapped as nodes of the same type to obtain a bipartite graph network containing users and service resources. The bipartite graph network is then segmented to obtain a user relationship network.

[0070] S230. Perform user clustering based on user relationship network to obtain multiple user groups after clustering, and determine the target user group to which the first user belongs based on the first user to be recommended and multiple user groups.

[0071] S240. Based on the first existing service resources already available to the first user and the second existing service resources already available to the second users in the target user group other than the first user, determine the target service resources to recommend to the first user.

[0072] S250. Detect whether the target service resource and the first existing service resource are mutually exclusive, and delete the mutually exclusive target service resource to recommend the non-mutually exclusive target service resource to the first user.

[0073] Specifically, by detecting whether each target service resource is mutually exclusive with the first user's existing service resources (e.g., resource or geographical exclusivity), and deleting mutually exclusive target service resources, the system recommends only non-mutually exclusive target service resources to the first user. This avoids recommending mutually exclusive target service resources to the user, ensuring the rationality and feasibility of the recommendation results.

[0074] In some optional implementations, when the target service resource includes at least one target first service resource and the first existing service resource includes at least one existing first service resource, the "detecting whether the target service resource and the first existing service resource are mutually exclusive" in step S250 includes: for each target first service resource, if the target first service resource has a mutually exclusive relationship with at least one existing first service resource, then the target first service resource is determined to be a target first service resource with resource mutual exclusion; or, if the publishing area of ​​the target first service resource does not include the area to which the first user belongs, then the target first service resource is determined to be a target first service resource with regional mutual exclusion.

[0075] Here, the target first service resource refers to the first service resource that needs to be recommended to the first user as determined in step S240. The existing first service resource refers to the first service resource that the first user already possesses, such as the first service resource that the user has subscribed to.

[0076] Specifically, for each target first service resource, the existence of a mutual exclusion relationship between the target first service resource and each existing first service resource in the knowledge graph can be determined by detecting whether there are mutually exclusive edges between the target first service resource and each existing first service resource. If the target first service resource is mutually exclusive with at least one existing first service resource, it indicates that the first user cannot possess the target first service resource, and in this case, the target first service resource is determined to be a target first service resource with resource mutual exclusion. Alternatively, if the publishing region of the target first service resource does not include the region of the first user, it indicates that the first user cannot possess the target first service resource, and in this case, the target first service resource is determined to be a target first service resource with regional mutual exclusion. Through the verification of resource mutual exclusion and regional mutual exclusion, mutually exclusive target first service resources are accurately identified from all target first service resources to avoid recommending mutually exclusive target first service resources to users.

[0077] In some optional implementations, when the target service resource includes at least one target second service resource and the first existing service resource includes at least one existing second service resource, the "detecting whether the target service resource and the first existing service resource are mutually exclusive" step S250 includes: for each target second service resource, if the target second service resource is mutually exclusive with at least one existing second service resource, then the target second service resource is determined to be a target second service resource with resource mutual exclusion; or, if the target second service resource is not mutually exclusive with any of the existing second service resources, but the first service resource to which the target second service resource belongs is mutually exclusive with at least one existing first service resource, then the target second service resource is determined to be a second target service resource with resource mutual exclusion; or, if the publishing area of ​​the target second service resource does not include the area to which the first user belongs, then the target second service resource is determined to be a target second service resource with regional mutual exclusion.

[0078] Here, the target first service resource refers to the second service resource that needs to be recommended to the first user as determined in step S240. Existing second service resources refer to second service resources that the first user already possesses, such as second service resources that the user has already subscribed to.

[0079] Specifically, for each target second service resource, the existence of a mutual exclusion relationship between the target second service resource and each existing second service resource can be determined by detecting whether there are mutually exclusive edges between the target second service resource and each existing second service resource in the knowledge graph. If the target second service resource is mutually exclusive with at least one existing second service resource, it indicates that the first user cannot possess the target second service resource, and the target second service resource is determined to be a target second service resource with resource mutual exclusion. Alternatively, if there is no mutual exclusion relationship between the target second service resource and each existing second service resource, the first service resource to which the target second service resource belongs can be obtained through the knowledge graph, and the existence of mutually exclusive edges between the first service resource to which it belongs and each existing first service resource can be detected to determine whether there is a mutual exclusion relationship between the first service resource to which it belongs and each existing first service resource. If the first service resource to which it belongs is mutually exclusive with at least one existing first service resource, the target second service resource is also determined to be a target second service resource with resource mutual exclusion. Alternatively, if the publishing region of the target second service resource does not include the region of the first user, it indicates that the first user cannot access the target second service resource. In this case, the target second service resource is determined to be a geographically exclusive target second service resource. Through resource exclusivity and geographical exclusivity checks, mutually exclusive target second service resources are accurately identified from all target second service resources to avoid recommending mutually exclusive target second service resources to users.

[0080] The technical solution of this embodiment detects whether there is mutual exclusion between the target service resource and the first existing service resource, and deletes the target service resource that has mutual exclusion, so as to recommend the first user the target service resource that does not have mutual exclusion, thereby avoiding recommending the user the target service resource that has mutual exclusion, and ensuring the rationality and feasibility of the recommendation result.

[0081] The following are embodiments of the service resource recommendation device provided in this invention. This device and the service resource recommendation methods in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the service resource recommendation device, please refer to the embodiments of the above service resource recommendation methods.

[0082] Figure 7 This is a schematic diagram of a service resource recommendation device provided in an embodiment of the present invention. This embodiment is applicable to situations where target service resources are automatically determined and recommended to users. Figure 7 As shown, the device specifically includes: a knowledge graph construction module 410, a user relationship network determination module 420, a user group determination module 430, and a target service resource determination module 440.

[0083] The knowledge graph construction module 410 is used to construct a knowledge graph with users, first service resources, and second service resources as nodes based on multiple user data corresponding to multiple users, multiple first service resource data corresponding to multiple first service resources, and multiple second service resource data corresponding to multiple second service resources. The user relationship network determination module 420 is used to map the first service resources and second service resources as nodes of the same type based on the knowledge graph to obtain a bipartite graph network containing users and service resources, and to segment the bipartite graph network to obtain a user relationship network. The user group determination module 430 is used to perform user clustering based on the user relationship network to obtain multiple clustered user groups, and to determine the target user group to which the first user belongs based on the first user to be recommended and the multiple user groups. The target service resource determination module 440 is used to determine the target service resource to be recommended to the first user based on the first existing service resources already existing to the first user and the second existing service resources already existing to the second users in the target user group other than the first user.

[0084] The technical solution of this embodiment constructs a knowledge graph with users, first service resources, and second service resources as nodes based on multiple user data, multiple first service resource data, and multiple second service resource data. Based on the knowledge graph, the first and second service resources are mapped as nodes of the same type, resulting in a bipartite graph network containing only users and service resources. This bipartite graph network is then segmented to quickly obtain the user relationship network. User clustering is performed based on the user relationship network to obtain multiple clustered user groups. Based on the first user to be recommended and the multiple user groups, the target user group to which the first user belongs is determined. Based on the first user's existing first service resources and the second existing service resources of second users in the target user group (excluding the first user), the target service resources to be recommended to the first user can be quickly and accurately determined. This utilizes the knowledge graph to reduce the computational complexity and amount of computation for service resource recommendation, thereby improving the efficiency of service resource recommendation.

[0085] Optionally, the plurality of user data includes: a user identifier corresponding to each user, the region to which the user belongs, and the service resource information already available to the user;

[0086] The multiple first service resource data include: the first service resource code, the first service resource name, the first service resource publishing area, and first service resource information that have mutual exclusion relationships for each first service resource;

[0087] The multiple second service resource data include: the second service resource code, the second service resource name, the second service resource publishing area, the second service resource information with mutual exclusion relationship, and the first service resource to which the second service resource belongs.

[0088] Optionally, the user's existing service resource information includes: the first service resource code, start time, and end time corresponding to the user's existing first service resource, and the second service resource code, start time, and end time corresponding to the user's existing second service resource.

[0089] The information of the first service resource with mutual exclusion includes: the first service resource code, mutual exclusion region, mutual exclusion start time and mutual exclusion end time corresponding to the first service resource with mutual exclusion;

[0090] The information about the mutually exclusive second service resources includes: the second service resource code, the mutual exclusion region, the mutual exclusion start time, and the mutual exclusion end time corresponding to the mutually exclusive second service resources.

[0091] Optionally, the knowledge graph contains three types of nodes: user nodes, first service resource nodes, and second service resource nodes.

[0092] The knowledge graph contains five types of edges: existing edges of the first service resource, existing edges of the second service resource, mutually exclusive edges between the first service resources, mutually exclusive edges between the second service resources, and edges belonging to the second service resource.

[0093] Wherein, the existing edge of the first service resource refers to the connection between the user node and the first service resource node, which is used to represent that there is an existing relationship between the user and the first service resource.

[0094] The existing edge of the second service resource refers to the connection between the user node and the second service resource node, which is used to represent that there is an existing relationship between the user and the second service resource.

[0095] The first mutual exclusion edge between service resources refers to the line connecting two first service resource nodes, which is used to represent that there is a mutual exclusion relationship between the two first service resource nodes.

[0096] The second mutual exclusion edge between service resources refers to the line connecting two second service resource nodes, which is used to represent that there is a mutual exclusion relationship between the two second service resource nodes;

[0097] The edge to which the second service resource belongs refers to the connection between the first service resource node and the second service resource node, which is used to indicate that the second service resource belongs to the first service resource.

[0098] Optionally, the user relationship network determination module 420 is specifically used for:

[0099] For each pair of user nodes in the bipartite graph network, determine the number of service resources in the bipartite graph network that are simultaneously connected to these two user nodes.

[0100] If the number of service resources is greater than or equal to 1, then connect the two user nodes to obtain an undirected edge between them, and use the number of service resources as the edge weight of the undirected edge to construct a user relationship network.

[0101] Optionally, the user group determination module 430 is specifically used for:

[0102] Using the Leuven algorithm, communities are identified based on the user relationship network, and each identified community is treated as a user group.

[0103] Optionally, the target service resource determination module 440 is specifically used for:

[0104] Based on the first existing service resources already available to the first user, the second existing service resources already available to the second users in the target user group other than the first user are filtered to obtain second existing service resources that do not contain the first existing service resources.

[0105] The filtered second existing service resources are aggregated to obtain each type of candidate service resource already available to the second user and the number of users corresponding to the existing candidate service resources;

[0106] Based on the number of users, the recommendation level corresponding to each candidate service resource is determined, and based on the recommendation level, a target service resource to be recommended to the first user is determined from the candidate service resources.

[0107] Optionally, the device further includes:

[0108] The mutual exclusion detection module is used to detect whether the target service resource and the first existing service resource are mutually exclusive, and to delete the target service resource that is mutually exclusive, so as to recommend the target service resource that is not mutually exclusive to the first user.

[0109] Optionally, when the target service resource includes at least one target first service resource, and the first existing service resource includes at least one existing first service resource, the mutual exclusion detection module is specifically used for:

[0110] For each target first service resource, if the target first service resource has a mutually exclusive relationship with at least one of the existing first service resources, then the target first service resource is determined to be a target first service resource with resource mutual exclusion; or,

[0111] If the publishing area of ​​the target first service resource does not include the area to which the first user belongs, then the target first service resource is determined to be a target first service resource with geographical exclusivity.

[0112] Optionally, when the target service resource includes at least one target second service resource, and the first existing service resource includes at least one existing second service resource, the mutual exclusion detection module is specifically used for:

[0113] For each target second service resource, if the target second service resource has a mutually exclusive relationship with at least one of the existing second service resources, then the target second service resource is determined to be a target second service resource with resource mutual exclusion; or,

[0114] If the target second service resource is not mutually exclusive with any of the existing second service resources, but the first service resource to which the target second service resource belongs is mutually exclusive with at least one existing first service resource, then the target second service resource is determined to be a second target service resource with resource mutual exclusion; or,

[0115] If the publishing area of ​​the target second service resource does not include the area to which the first user belongs, then the target second service resource is determined to be a target second service resource with geographical exclusivity.

[0116] The service resource recommendation device provided in this embodiment of the invention can execute the service resource recommendation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the service resource recommendation method.

[0117] It is worth noting that in the embodiments of the above-mentioned service resource recommendation device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of the present invention.

[0118] Figure 8 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0119] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0120] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0121] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various service resource recommendation methods and processes described above.

[0122] In some embodiments, the service resource recommendation method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the service resource recommendation method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the service resource recommendation method by any other suitable means (e.g., by means of firmware).

[0123] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0124] Computer programs used to implement the service resource recommendation method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0125] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0126] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0127] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0128] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0129] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the service resource recommendation method as provided in any embodiment of this invention.

[0130] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​as well as conventional procedural programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0132] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A service resource recommendation method, characterized in that, include: Based on multiple user data corresponding to multiple users, multiple first service resource data corresponding to multiple first service resources, and multiple second service resources corresponding to multiple second service resources, a knowledge graph is constructed with the users, the first service resources, and the second service resources as nodes; Based on the knowledge graph, the first service resource and the second service resource are mapped as nodes of the same type to obtain a bipartite graph network containing users and service resources, and the bipartite graph network is segmented to obtain a user relationship network. User clustering is performed based on the user relationship network to obtain multiple clustered user groups, and the target user group to which the first user belongs is determined based on the first user to be recommended and the multiple user groups. Based on the first existing service resources already possessed by the first user and the second existing service resources already possessed by the second users in the target user group other than the first user, the target service resources recommended to the first user are determined.

2. The method according to claim 1, characterized in that, The multiple user data include: each user's corresponding user identifier, the user's region, and the user's existing service resource information; The multiple first service resource data include: the first service resource code, the first service resource name, the first service resource publishing area, and first service resource information that have mutual exclusion relationships for each first service resource; The multiple second service resource data include: the second service resource code, the second service resource name, the second service resource publishing area, the second service resource information with mutual exclusion relationship, and the first service resource to which the second service resource belongs.

3. The method according to claim 2, characterized in that, The user's existing service resource information includes: the first service resource code, start time and end time corresponding to the user's existing first service resource, and the second service resource code, start time and end time corresponding to the user's existing second service resource. The information of the first service resource with mutual exclusion includes: the first service resource code, mutual exclusion region, mutual exclusion start time and mutual exclusion end time corresponding to the first service resource with mutual exclusion; The information about the mutually exclusive second service resources includes: the second service resource code, the mutual exclusion region, the mutual exclusion start time, and the mutual exclusion end time corresponding to the mutually exclusive second service resources.

4. The method according to claim 1, characterized in that, The knowledge graph contains three types of nodes: user nodes, first service resource nodes, and second service resource nodes. The knowledge graph contains five types of edges: existing edges of the first service resource, existing edges of the second service resource, mutually exclusive edges between the first service resources, mutually exclusive edges between the second service resources, and edges belonging to the second service resource. Wherein, the existing edge of the first service resource refers to the connection between the user node and the first service resource node, which is used to represent that there is an existing relationship between the user and the first service resource. The existing edge of the second service resource refers to the connection between the user node and the second service resource node, which is used to represent that there is an existing relationship between the user and the second service resource. The first mutual exclusion edge between service resources refers to the line connecting two first service resource nodes, which is used to represent that there is a mutual exclusion relationship between the two first service resource nodes. The second mutual exclusion edge between service resources refers to the line connecting two second service resource nodes, which is used to represent that there is a mutual exclusion relationship between the two second service resource nodes; The edge to which the second service resource belongs refers to the connection between the first service resource node and the second service resource node, which is used to indicate that the second service resource belongs to the first service resource.

5. The method according to claim 1, characterized in that, The step of segmenting the bipartite graph network to obtain a user relationship network includes: For each pair of user nodes in the bipartite graph network, determine the number of service resources in the bipartite graph network that are simultaneously connected to these two user nodes. If the number of service resources is greater than or equal to 1, then connect the two user nodes to obtain an undirected edge between them, and use the number of service resources as the edge weight of the undirected edge to construct a user relationship network.

6. The method according to claim 1, characterized in that, The step of clustering users based on the user relationship network to obtain multiple clustered user groups includes: Using the Leuven algorithm, communities are identified based on the user relationship network, and each identified community is treated as a user group.

7. The method according to claim 1, characterized in that, The step of determining the target service resources to recommend to the first user based on the first user's existing first existing service resources and the second existing service resources of the second users in the target user group other than the first user includes: Based on the first existing service resources already available to the first user, the second existing service resources already available to the second users in the target user group other than the first user are filtered to obtain second existing service resources that do not contain the first existing service resources. The filtered second existing service resources are aggregated to obtain each type of candidate service resource already available to the second user and the number of users corresponding to the existing candidate service resources; Based on the number of users, the recommendation level corresponding to each candidate service resource is determined, and based on the recommendation level, a target service resource to be recommended to the first user is determined from the candidate service resources.

8. The method according to any one of claims 1-7, characterized in that, After determining the target service resource to recommend to the first user, the process also includes: The system detects whether the target service resource is mutually exclusive with the first existing service resource, deletes the mutually exclusive target service resource, and recommends the non-mutually exclusive target service resource to the first user.

9. The method according to claim 8, characterized in that, When the target service resource includes at least one target first service resource, and the first existing service resource includes at least one existing first service resource, detecting whether the target service resource and the first existing service resource are mutually exclusive includes: For each target first service resource, if the target first service resource has a mutually exclusive relationship with at least one of the existing first service resources, then the target first service resource is determined to be a target first service resource with resource mutual exclusion; or, If the publishing area of ​​the target first service resource does not include the area to which the first user belongs, then the target first service resource is determined to be a target first service resource with geographical exclusivity.

10. The method according to claim 8, characterized in that, When the target service resource includes at least one target second service resource, and the first existing service resource includes at least one existing second service resource, detecting whether the target service resource and the first existing service resource are mutually exclusive includes: For each target second service resource, if the target second service resource has a mutually exclusive relationship with at least one of the existing second service resources, then the target second service resource is determined to be a target second service resource with resource mutual exclusion; or, If the target second service resource is not mutually exclusive with any of the existing second service resources, but the first service resource to which the target second service resource belongs is mutually exclusive with at least one existing first service resource, then the target second service resource is determined to be a second target service resource with resource mutual exclusion; or, If the publishing area of ​​the target second service resource does not include the area to which the first user belongs, then the target second service resource is determined to be a target second service resource with regional mutual exclusion.

11. A service resource recommendation device, characterized in that, include: The knowledge graph construction module is used to construct a knowledge graph with the users, the first service resources, and the second service resources as nodes, based on multiple user data corresponding to multiple users, multiple first service resource data corresponding to multiple first service resources, and multiple second service resource data corresponding to multiple second service resources. The user relationship network determination module is used to map the first service resource and the second service resource as nodes of the same type based on the knowledge graph to obtain a bipartite graph network containing users and service resources, and to segment the bipartite graph network to obtain a user relationship network. The user group determination module is used to perform user clustering based on the user relationship network to obtain multiple clustered user groups, and to determine the target user group to which the first user belongs based on the first user to be recommended and the multiple user groups. The target service resource determination module is used to determine the target service resources to be recommended to the first user based on the first existing service resources already existing to the first user and the second existing service resources already existing to the second users in the target user group other than the first user.

12. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the service resource recommendation method according to any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the service resource recommendation method according to any one of claims 1-10.

14. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the service resource recommendation method as described in any one of claims 1-10.

Images