CN112132305A - Node type determination method, related device, equipment and storage medium - Google Patents

Abstract

The embodiment of the present invention discloses a node type determination method, a related device, equipment and a storage medium. The method includes: a terminal device determines at least one neighbor node of a target node; and calculates any neighbor node of the target node based on the connection with the target node. At least one first probability that various types of edges propagate the target label to the target node to obtain a first probability set that each neighbor node propagates the target label to the target node based on various types of edges; the target is determined based on the first probability set The node receives the first probability vector of the target label based on the same type of edges, so as to obtain the first probability vector set of the target node receiving the target label based on multiple types of edges; based on the first probability vector set, the second probability vector of the target node receiving the target label is obtained. probability; determine the node class of the target node based on the second probability. With the embodiment of the present invention, the category of any node in any social network can be predicted, and the applicability is high.

Description

Node category determination method, related apparatus, equipment and storage medium

technical field

The present invention relates to the field of computer technology, and in particular, to a method for determining a node type, a related apparatus, a device and a storage medium.

Background technique

At present, social communication (social influence propagation) has a wide range of application scenarios, and social influence is mainly based on tag propagation in social networks to achieve communication, but most of the traditional tag propagation methods are based on homogeneous networks. Since nodes in a homogeneous network belong to the same type of object (entity), and the nodes are comparable, the class of each node can be predicted based on the propagation of labels in the homogeneous network.

However, for heterogeneous networks, there are many types of different nodes and edges between nodes, and each type of node has different characteristics. The existing label propagation method cannot effectively judge whether each node in a heterogeneous network is affected by other nodes. impact is more limited.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a node category determination method, related apparatus, equipment, and storage medium, which can predict the category of any node in any social network, and have high applicability.

In a first aspect, an embodiment of the present invention provides a method for determining a node type, the method comprising:

The terminal device determines at least one neighbor node of the target node, wherein the neighbor node is a node connected to the target node based on at least one type of edge;

The above-mentioned terminal device calculates at least one first probability that any neighbor node of the above-mentioned target node propagates the target label to the above-mentioned target node based on various types of edges connected to the above-mentioned target node, wherein one type of edge corresponds to a first probability. , to obtain the first probability set that each neighbor node propagates the above target label to the above target node based on various types of edges;

The terminal device determines, based on the first probability set, the first probability vector that the target node receives the target label based on the same type of edges, to obtain a first probability vector set that the target node receives the target label based on multiple types of edges;

The terminal device obtains, based on the first probability vector set, the second probability that the target node receives the target tag;

The terminal device determines the node type of the target node based on the second probability, and outputs the node type of the target node to the user interface of the terminal device for display to the user.

With reference to the first aspect, in a possible implementation manner, the terminal device calculates that any neighbor node of the target node propagates the target label to at least one first node of the target node based on various types of edges connected to the target node. a probability, including:

The above-mentioned terminal device obtains at least one edge attribute of any type of edge connected between any neighbor node and the above-mentioned target node;

The terminal device determines the attribute weight of each edge attribute in the at least one edge attribute;

The above-mentioned terminal device determines the edge weight of the above-mentioned any type of edge based on the attribute weight of each of the above-mentioned edge attributes, and determines the above-mentioned edge weight as the above-mentioned any neighbor node based on the above-mentioned any type of edge to propagate the target label to the above-mentioned target. The first probability of the node is obtained to obtain each first probability that any of the above-mentioned neighbor nodes propagates the target label to the above-mentioned target node based on each type of edge between the above-mentioned target node.

With reference to the first aspect, in a possible implementation manner, the terminal device determines, based on the first probability set, the first probability vector that the target node receives the target label based on the same type of edge, including:

The terminal device determines, from the first probability set, at least one first probability corresponding to edges whose edge types belong to the same type;

The terminal device constructs, based on the at least one first probability, a first probability vector in which the target node receives the target label based on an edge of the same type.

With reference to the first aspect, in a possible implementation manner, the above-mentioned terminal device determines multiple neighbor nodes of the target node, including:

The terminal device acquires the association relationship between each node in at least one social network, determines at least one node that has an association relationship with the target node from the above nodes based on the association relationship between the above nodes, and assigns the at least one node to the target node. It is determined as the neighbor node of the above target node.

With reference to the first aspect, in a possible implementation manner, the terminal device obtains the second probability that the target node receives the target label based on the first probability vector set, including:

The above-mentioned terminal device determines each type weight corresponding to each type in the types of the edge, wherein one type corresponds to one type weight;

The terminal device determines the second probability that the target node receives the target label based on the weights of the respective types and the first probability vector set.

With reference to the first aspect, in a possible implementation manner, the terminal device determines the node type of the target node based on the second probability, including:

The above-mentioned terminal device compares the above-mentioned second probability with a preset threshold;

When the second probability is greater than or equal to the preset threshold, the terminal device determines that the node type of the target node is the node type marked by the target label.

With reference to the first aspect, in a possible implementation manner, the neighbor nodes of the target node include a first-degree neighbor node of the target node and a second-degree neighbor node of the target node, and the first-degree neighbor node is based on at least the target node. A type of edge-connected node, the above-mentioned second-degree neighbor node is any node connected to the above-mentioned target node based on any one-degree neighbor node;

The above method also includes:

The above-mentioned terminal device determines that the above-mentioned target node receives the second probability vector of the above-mentioned target label propagated from each second-degree neighbor node based on the same type of edge, so as to obtain the above-mentioned target node based on multiple types of edges to receive the above-mentioned propagation from each second-degree neighbor node. the second set of probability vectors of target labels;

The terminal device obtains the second probability that the target node receives the target tag based on the first probability vector set and the second probability vector set.

In a second aspect, an embodiment of the present invention provides an apparatus for determining a node type, the apparatus comprising:

a node determination module, configured to determine at least one neighbor node of the target node, wherein the neighbor node is a node connected to the target node based on at least one type of edge;

The first probability determination module is used to calculate at least one first probability that any neighbor node of the above-mentioned target node propagates the target label to the above-mentioned target node based on various types of edges connected to the above-mentioned target node, wherein one type of edge Corresponding to a first probability, to obtain the first probability set that each neighbor node propagates the above-mentioned target label to the above-mentioned target node based on various types of edges;

The probability vector determination module is configured to determine, based on the first probability set, the first probability vector that the target node receives the target label based on the same type of edges, so as to obtain the first probability vector that the target node receives the target label based on multiple types of edges. set of probability vectors;

a second probability determination module, configured to obtain a second probability that the target node receives the target tag based on the first probability vector set;

The node category determination module is configured to determine the node category of the target node based on the second probability, and output the node category of the target node to the user interface of the terminal device for display to the user.

With reference to the second aspect, in a possible implementation manner, the above-mentioned first probability determination module includes:

an edge attribute obtaining unit, used to obtain at least one edge attribute of any type of edge connected between any neighbor node and the above-mentioned target node;

an attribute weight determination unit, configured to determine the attribute weight of each edge attribute in the at least one edge attribute;

The edge weight determination unit is used to determine the edge weight of any of the above-mentioned types of edges based on the attribute weights of the above-mentioned various edge attributes, and determine the above-mentioned edge weights as the above-mentioned any of the neighbor nodes based on the above-mentioned any type of edge. The first probability of propagating to the above-mentioned target node is obtained to obtain each first probability of each of the above-mentioned neighbor nodes propagating the target label to the above-mentioned target node based on various types of edges with the above-mentioned target node.

In combination with the second aspect, in a possible implementation manner, the above probability vector determination module is used for:

at least one first probability corresponding to edges whose edge types belong to the same type are determined from the first probability set;

The first probability vector of the target node receiving the target label based on the same type of edge is constructed based on the at least one first probability.

With reference to the second aspect, in a possible implementation manner, the above node determination module is configured to:

Obtain the association relationship between each node in at least one social network, determine at least one node that has an association relationship with the target node from the above-mentioned each node based on the above-mentioned association relationship between each node, and determine the above-mentioned at least one node as the above-mentioned at least one node. The neighbor nodes of the target node.

With reference to the second aspect, in a possible implementation manner, the above-mentioned second probability determination module is used for:

Determine each type weight corresponding to each type of edge types, wherein one type corresponds to one type weight;

The second probability that the target node receives the target label is determined based on the above-mentioned respective type weights and the above-mentioned first probability vector set.

With reference to the second aspect, in a possible implementation manner, the above node category determination module includes:

a comparison unit, configured to compare the above-mentioned second probability with a preset threshold;

A category determination unit, configured to determine that the node category of the target node is the node category marked by the target label when the second probability is greater than or equal to the preset threshold.

With reference to the second aspect, in a possible implementation manner, the neighbor nodes of the target node include a first-degree neighbor node of the target node and a second-degree neighbor node of the target node, and the first-degree neighbor node is based on at least the target node. A type of edge-connected node, the above-mentioned second-degree neighbor node is any node connected to the above-mentioned target node based on any one-degree neighbor node;

The above-mentioned probability vector determination module is also used to determine that the above-mentioned target node receives the second probability vector of the above-mentioned target label transmitted from each second-degree neighbor node based on the same type of edge, so as to obtain the above-mentioned target node based on multiple types of edges to receive from each of the two probability vectors. The second degree neighbor node propagates the second probability vector set of the above target label;

The second probability determination module is further configured to obtain a second probability that the target node receives the target label based on the first probability vector set and the second probability vector set.

In a third aspect, an embodiment of the present invention provides a terminal device, where the terminal device includes a processor and a memory, and the processor and the memory are connected to each other. The memory is used to store a computer program that supports the terminal device to perform the method provided by the first aspect and/or any possible implementation manner of the first aspect,

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the above-mentioned first aspect and/or any one of the first aspects method provided by a possible implementation.

In the embodiment of the present invention, by converting different types of node relationships in different social networks into the same type of node relationship, the restrictions on node relationships in different social networks can be eliminated, so that the node type of any node in different social networks can be determined. Make predictions. By calculating the attribute weight of each edge attribute of each type of edge, the corresponding weight of each edge attribute in the edge of its corresponding type can be determined. Therefore, the edge weight of each type of edge can be accurately and reasonably determined based on the attribute weight of each edge attribute, and the applicability is high.

Description of drawings

In order to illustrate the technical solutions in the embodiments of the present invention more clearly, the following briefly introduces the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

1 is a schematic diagram of the architecture of a social network provided by an embodiment of the present invention;

2 is a schematic flowchart of a method for determining a node type provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of node association transformation according to an embodiment of the present invention;

4 is a flowchart of a method for calculating a first probability provided by an embodiment of the present invention;

5 is a schematic diagram of a scene of a neighbor node provided by an embodiment of the present invention;

6 is a schematic structural diagram of an apparatus for determining a node type provided by an embodiment of the present invention;

FIG. 7 is a schematic structural diagram of a terminal device provided by an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Please refer to FIG. 1. FIG. 1 is a schematic structural diagram of a social network provided by an embodiment of the present invention. The network architecture includes multiple users and devices and networks used to connect the multiple users. As shown in FIG. 1, multiple users can form social network 1 based on terminal 100 and terminal 200, some users can form social network 3 based on Wifi300 and Wifi400, and other users can form social network 3 based on other terminals, such as mobile phones, tablet computers, laptop computers , PDAs, mobile internet devices (mobile internet devices, MIDs), wearable devices (such as smart watches, smart bracelets, etc.), etc., form a social network 2 . Among them, users in social network 1, social network 2 and social network 3 can disseminate social information based on a certain social method, for example, social information can be disseminated based on Moments and Moments advertisements. User A sees User B’s social behavior After (posting the circle of friends, sharing the text of the official account, and liking the advertisement), there may be social information interaction with user B, such as commenting on the circle of friends of B, reposting the article shared by B, liking the advertisement that B has liked, etc. In simple terms, each user in a social network can be regarded as each node in the social network, and each node propagates a label to other nodes associated with it to give the label to other nodes, thereby changing the reception in the social network. The node class of the node where the labels are propagated.

Please refer to FIG. 2. FIG. 2 is a schematic flowchart of a method for determining a node type provided by an embodiment of the present invention. The node type determination method provided by the embodiment of the present invention may include the following steps 101-104:

101. The terminal device determines at least one neighbor node of the target node.

In some feasible implementations, since an actual social network consists of multiple devices and connections and/or behavioral relationships between users, and different users can associate with other users through multiple devices and networks. Therefore, for any node in the social network, only a part of other nodes in the social network have multiple associations with the node. It can be seen from this that when determining the node type of a node (for the convenience of description, the node may be represented by a target node, which will not be repeated below), the terminal device can obtain at least one social network where the target node is located. and determine at least one node that has an association relationship with the target node based on the association relationship between the nodes, and determine the at least one node as the neighbor node of the target node, so that it can be based on The category of the target node is determined by the probability that the neighbor nodes of the target node propagate the label to the target node.

In some feasible implementation manners, since the above-mentioned target node may exist in different social networks, and there are differences between the types of node associations in different social networks, that is, under normal circumstances, two different social networks cannot be directly connected. Nodes in the network directly compare node relationships. Not only that, the types of associations between nodes in different social networks are not necessarily the same type of associations, so before determining the neighbor nodes of the above target node, the associations before each node in different social networks can be converted. For the same type of association relationship, to avoid the limitation that neighbor nodes cannot be determined due to different association relationships between nodes in different social networks. For details, refer to FIG. 3 , which is a schematic diagram of node association transformation according to an embodiment of the present invention. As shown in FIG. 2 , nodes B, C, and D are all associated with node A through a certain association relationship, that is, node B, node C, and node D establish an association relationship with each other through node A. If node B, node C, and node D belong to nodes in different social networks at this time, although node B, node C, and node D have a certain relationship with each other through node A, the node cannot be directly determined. The relationship between B, node C, and node D. At this time, node B, node C, and node D can be formed into a fully connected graph of association relationship to represent the association relationship established by node B, node C, and node D based on node A. For example, when node A is a certain device, and node B, node C, and node D are respectively associated with three users of the device, the three The user association relationship established by each user based on the above device.

102. The terminal device calculates at least one first probability that any neighbor node of the target node propagates the target label to the target node based on various types of edges connected to the target node.

In some feasible implementations, after the terminal device determines at least one neighbor node of the target node, any neighbor node of the target node can be calculated to propagate the target label to the target node based on various types of edges connected to the target node. at least one first probability of the above target node. Thus, a first probability set for the table node to propagate the target label to the target node based on various types of edges can be obtained. Wherein, a type of edge between any neighbor node and the above-mentioned target node corresponds to a first probability. Specifically, reference may be made to FIG. 4 for the calculation method of the first probability. FIG. 4 is a flowchart of a method for calculating the first probability provided by an embodiment of the present invention. The method for calculating the first probability provided by the embodiment of the present invention may include the following steps 201-204:

201. The terminal device acquires at least one edge attribute of any type of edge connecting any neighbor node to the target node.

In some feasible implementations, the target node and any neighbor node may be connected to each other based on at least one type of edge, and in different social scenarios of different types of social networks, the target node and any neighbor node The types of edges between them are also different, which can be determined based on actual application scenarios, and are not limited here. For example, when a certain type of edge connecting the above target node to any node can represent the transfer relationship between the two nodes, the wifi connection relationship between the nodes, or the chat relationship between the two nodes, etc. This does not limit. For any type of edge between the above-mentioned target node and any neighbor node, the terminal device can obtain different edge attributes in the above-mentioned any type of edge, so that it can be based on the different edge attributes in the above-mentioned any type of edge. . For example, for an edge that represents a transfer relationship, the edge attributes of the edge can include edge attributes such as transfer amount and transfer frequency. For an edge that represents a wifi connection relationship between nodes, the edge attributes of the edge can include connection duration, connection frequency. Equilateral attributes, the type and number of edge attributes of each type of edge can be determined based on the actual type of edge, which is not limited here.

202. The terminal device determines an attribute weight of each edge attribute in the at least one edge attribute.

实现，其中k为归一化系数，x为每个边属性对应的边值。基于经过归一化处理后的边值，可基于每个边值的归一化值确定每个边属性的属性权重，其中，每个边属性的属性权重为

In some feasible implementation manners, after the terminal device determines at least one edge attribute of any type of edge connected between any neighbor node and the above-mentioned target node, it can determine edge values corresponding to different edge attributes and then calculate each edge The attribute weight of the attribute. Among them, since the boundary values of different edge attributes have different dimensions, after determining the boundary values corresponding to different edge attributes, the terminal device can perform data normalization processing on the boundary values of different dimensions to eliminate different boundary values. effects of different dimensions. Among them, the normalization processing method of specific data can be based on

Implementation, where k is the normalization coefficient and x is the edge value corresponding to each edge attribute. Based on the normalized edge values, the attribute weight of each edge attribute can be determined based on the normalized value of each edge value, wherein the attribute weight of each edge attribute is

203. The terminal device determines the edge weight of any type of edge based on the attribute weight of each edge attribute.

来得出上述任一类型的边的边权重。In some feasible implementation manners, after the terminal device calculates the edge attribute weights of any type of edge between the target node and any neighbor node, the terminal device can determine any of the above-mentioned types based on the attribute weights of the above-mentioned various edge attributes The edge weights of the edges. Specifically, when any of the above types of edges has only one edge attribute, the attribute weight of the edge attribute may be determined as the edge weight of any of the above types of edges. When any of the above types of edges has two edge attributes, the edge weight of any of the above types of edges can be determined based on W=(w ₁ +w ₂ )-(w ₁ *w ₂ ), where w ₁ and w ₂ is the edge weight of any of the above-mentioned types of edges, respectively, and W represents the edge weight of any of the above-mentioned types of edges. It is not difficult to obtain that when any of the above types of edges has n edge attributes, it can be based on

to derive edge weights for any of the above types of edges.

204. The terminal device determines the edge weight as the first probability that any neighbor node propagates the target label to the target node based on any type of edge, so as to obtain any neighbor node based on various types of edges between the target node and the target node. Each first probability for the target label to propagate to the target node.

In some feasible implementation manners, after obtaining the edge weight W of the above-mentioned any type of edge, the terminal device may determine the above-mentioned edge weight W of any type of edge as the above-mentioned any neighbor node based on any type of edge. The first probability that the target label propagates to the above target node. Based on the above method, the terminal device can obtain a plurality of first probabilities that any of the above neighbor nodes propagate the target label to the target node based on various types of edges with the target node, and then obtain that each neighbor node will be based on various types of first probabilities. The edge propagates the target label to the first set of probabilities of the target node. Briefly, the first set of probabilities contains the first probability that each neighbor node propagates the target label to the target node based on each type of edge.

In the embodiment of the present invention, by calculating the attribute weight of each edge attribute of each type of edge, the corresponding proportion of each edge attribute in the corresponding type of edge can be determined. Therefore, the edge weight of each type of edge can be accurately and reasonably determined based on the attribute weight of each edge attribute, and the applicability is high.

103. The terminal device determines, based on the first probability set, a first probability vector for the target node to receive the target label based on the same type of edges, to obtain a first probability vector set for the target node to receive the target label based on multiple types of edges.

In some feasible implementation manners, the terminal device may determine, from the first probability set, at least one first probability corresponding to edges whose edge types belong to the same type, and the at least one first probability may include different neighbor nodes based on the same type of edge. Multiple first probabilities that different edges of the edge type relay the target label to the target node. That is, the terminal device can classify each first probability in the first probability set based on the type of the edge, and obtain a plurality of sub-first probability sets, wherein at least one first probability included in each sub-first probability set is of the same type The edge corresponding to the first probability. At the same time, the terminal device may construct, based on each sub-first probability set, a first probability vector ps for the target node to receive the target label based on the same type of edge, where _s represents the type of the edge, such as the edge based on the first type. The first probability vector of receiving the target label is p _s1 , and the first probability vector of receiving the target label based on the second type of edge is p _s2 , so that the first probability vector of the target node receiving the target label based on various types of edges can be obtained. Collection P.

104. The terminal device obtains, based on the first probability vector set, a second probability that the target node receives the target tag.

确定出目标节点接收目标标签的第二概率，其中，Y为每个边类型对应的类型权重，X为上述目标节点基于同一类型的边接收目标标签的概率，m为边类型数。In some feasible implementation manners, after the terminal device determines that the target node receives the first probability vector of the target label based on multiple types of edges combined with P, since the importance of different nodes in the social network is different, the importance levels of different nodes are different. Nodes can influence the probability of a tag spreading in a social network. Therefore, a new first probability vector set S can be obtained based on the importance of the target label, where S=αP+(1-α)V, P is the first probability vector set obtained above, and V represents the target node. , and V=(1-α), 0≤α≤1. Based on the terminal device, each type weight corresponding to each type of the above edge types can be determined, and each type corresponds to a type weight. So that the terminal device can be based on

Determine the second probability that the target node receives the target label, where Y is the type weight corresponding to each edge type, X is the probability that the target node receives the target label based on the same type of edge, and m is the number of edge types.

In some feasible implementations, the neighbor nodes of the target node may include multi-degree neighbor nodes. Please refer to FIG. 5 , which is a schematic diagram of a scenario of neighbor nodes according to an embodiment of the present invention. 5, when node A is the target node, and the neighbor nodes include the first-degree neighbor nodes (node B1, node B2, node B3, and node B4) and second-degree neighbor nodes (node C1 and node C2) of the target node, the terminal device It is possible to first calculate the probability vector that the above target node receives the target label transmitted from each one-degree neighbor node (node B1, node B2, node B3 and node B4) based on the same type of edge, so as to obtain the target node based on multiple types of edge reception. A set of probability vectors for target labels are propagated from each one-degree neighbor node (NodeB1, NodeB2, NodeB3, and NodeB4). The terminal device can calculate the probability vector of the target node receiving the target label propagated from each second-degree neighbor node (node C1 and node C2) based on the same type of edges, so as to obtain the target node based on multiple types of edges receiving from each second-degree neighbor node. Neighboring nodes (node C1 and node C2) propagate the set of probability vectors of target labels. Among them, the probability vector of target node A receiving second-degree neighbor node C2 based on multiple types of edges can be received by first-degree neighbor grounding B3 based on the propagation probability of multiple types of edges with node B2 and the one-degree neighbor node based on multiple types. The propagation probability of the edge of the target label to the target node A is determined, and the specific method is not limited here. Obtain the second probability vector set of the target node receiving the target label propagated by each neighbor node based on the multiple types of edges based on the above two probability vector sets, thereby obtaining the second probability of the target node receiving the target label based on the second probability vector set. . The specific calculation method may be based on the implementation manner shown above, which is not limited herein.

105. The terminal device determines the node type of the target node based on the second probability, and outputs the node type of the target node to the user interface of the terminal device for display to the user.

In some feasible implementation manners, after the terminal device determines the second probability that the target node receives the target tag, the second probability may be compared with a preset threshold. When the second probability is greater than or equal to the preset threshold, the terminal device may determine that the node type of the target node is the node type marked by the target label. Optionally, when the above-mentioned second probability is less than the preset threshold, it can be determined that the target label propagated to the target node is a negative label (such as gambling, fraud, etc.), and at the same time, after the terminal device determines the node type of the target node, it can be The node category of the target node is output to the user interface of the terminal device for display to the user.

In the embodiment of the present invention, by converting different types of node relationships in different social networks into the same type of node relationship, the restrictions on node relationships in different social networks can be eliminated, so that the node type of any node in different social networks can be determined. Make predictions. By calculating the attribute weight of each edge attribute of each type of edge, the corresponding weight of each edge attribute in the edge of its corresponding type can be determined. Therefore, the edge weight of each type of edge can be accurately and reasonably determined based on the attribute weight of each edge attribute, and the applicability is high.

Referring to FIG. 6, FIG. 6 is a schematic structural diagram of an apparatus for determining a node type provided by an embodiment of the present invention. The device for determining a node type provided by the embodiment of the present invention includes:

A node determination module 31, configured to determine at least one neighbor node of the target node, wherein the neighbor node is a node connected to the target node based on at least one type of edge;

The first probability determination module 32 is used to calculate at least one first probability that any neighbor node of the above-mentioned target node propagates the target label to the above-mentioned target node based on various types of edges connected to the above-mentioned target node, wherein one type of The edge corresponds to a first probability, so as to obtain the first probability set that each neighbor node propagates the above-mentioned target label to the above-mentioned target node based on various types of edges;

The probability vector determination module 33 is configured to determine, based on the first probability set, the first probability vector that the target node receives the target label based on the same type of edges, so as to obtain the first probability vector that the target node receives the target label based on multiple types of edges. a set of probability vectors;

The second probability determination module 34 is configured to obtain the second probability that the target node receives the target tag based on the first probability vector set;

The node category determination module 35 is configured to determine the node category of the target node based on the second probability, and output the node category of the target node to the user interface of the terminal device for display to the user.

In some feasible implementations, the above-mentioned first probability determination module 32 includes:

The edge attribute obtaining unit 321 is used to obtain at least one edge attribute of any type of edge connected between any neighbor node and the above-mentioned target node;

an attribute weight determination unit 322, configured to determine the attribute weight of each edge attribute in the at least one edge attribute;

The edge weight determination unit 323 is configured to determine the edge weight of the above-mentioned any type of edge based on the attribute weight of each of the above-mentioned edge attributes, and determine the above-mentioned edge weight as the above-mentioned any neighbor node based on the above-mentioned any type of edge. The first probability that the label propagates to the target node is obtained to obtain each first probability that any of the neighbor nodes propagates the target label to the target node based on various types of edges with the target node.

In some feasible implementations, the above probability vector determination module 33 is used to:

at least one first probability corresponding to edges whose edge types belong to the same type are determined from the first probability set;

The first probability vector of the target node receiving the target label based on the same type of edge is constructed based on the at least one first probability.

In some feasible implementation manners, the above-mentioned node determination module 31 is used for:

Obtain the association relationship between each node in at least one social network, determine at least one node that has an association relationship with the target node from the above-mentioned each node based on the above-mentioned association relationship between each node, and determine the above-mentioned at least one node as the above-mentioned at least one node. The neighbor nodes of the target node.

In some feasible implementation manners, the above-mentioned second probability determination module 34 is used for:

Determine each type weight corresponding to each type of edge types, wherein one type corresponds to one type weight;

The second probability that the target node receives the target label is determined based on the above-mentioned respective type weights and the above-mentioned first probability vector set.

In some feasible implementations, the above-mentioned node category determination module 35 includes:

a comparison unit 351, configured to compare the above-mentioned second probability with a preset threshold;

The category determination unit 352 is configured to determine that the node category of the target node is the node category marked by the target label when the second probability is greater than or equal to the preset threshold.

In some feasible implementation manners, the neighbor nodes of the target node include first-degree neighbor nodes of the target node and second-degree neighbor nodes of the target node, and the first-degree neighbor nodes are connected to the target node based on at least one type of edge The node, the above-mentioned second-degree neighbor node is any node connected with the above-mentioned target node based on any one-degree neighbor node;

The above-mentioned probability vector determination module 33 is also used to determine that the above-mentioned target node receives the second probability vector of the above-mentioned target label propagated from each second-degree neighbor node based on the same type of edge, so as to obtain the above-mentioned target node based on multiple types of edges to receive from. Each second-degree neighbor node propagates the second probability vector set of the target label;

The second probability determination module 34 is further configured to obtain a second probability that the target node receives the target label based on the first probability vector set and the second probability vector set.

In a specific implementation, the above-mentioned node type determination device may execute the implementation manner provided by each step in FIG. 1 to FIG. 5 through its built-in modules and/or units, which will not be repeated here.

In the embodiment of the present invention, by converting different types of node relationships in different social networks into the same type of node relationship, the restrictions on node relationships in different social networks can be eliminated, so that the node type of any node in different social networks can be determined. Make predictions. By calculating the attribute weight of each edge attribute of each type of edge, the corresponding weight of each edge attribute in the edge of its corresponding type can be determined. Therefore, the edge weight of each type of edge can be accurately and reasonably determined based on the attribute weight of each edge attribute, and the applicability is high.

Referring to FIG. 7, FIG. 7 is a schematic structural diagram of a terminal device provided by an embodiment of the present invention. The electronic device 1000 may include: a processor 1001 , a network interface 1004 and a memory 1005 , in addition, the electronic device 1000 may further include: a user interface 1003 , and at least one communication bus 1002 . Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display) and a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. Optionally, the network interface 1004 may include a standard wired interface and a wireless interface (eg, a WI-FI interface). The memory 1005 may be a high-speed RAM memory, or a non-volatile memory, such as at least one disk memory. Optionally, the memory 1005 may also be at least one storage device located away from the aforementioned processor 1001 . As shown in FIG. 7 , the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a device control application program.

In the electronic device 1000 shown in FIG. 7 , the network interface 1004 can provide a network communication function; the user interface 1003 is mainly used to provide an input interface for the user; and the processor 1001 can be used to call the device control application stored in the memory 1005 program to achieve:

determining at least one neighbor node of the target node, wherein the neighbor node is a node connected to the target node based on at least one type of edge;

Calculate at least one first probability that any neighbor node of the above-mentioned target node propagates the target label to the above-mentioned target node based on various types of edges connected to the above-mentioned target node, wherein one type of edge corresponds to a first probability to obtain Each neighbor node propagates the target label to the first probability set of the target node based on various types of edges;

Determine the first probability vector of the target node receiving the target label based on the same type of edges based on the first probability set, so as to obtain the first probability vector set of the target node receiving the target label based on multiple types of edges;

Obtaining the second probability that the target node receives the target label based on the first probability vector set;

The node category of the target node is determined based on the second probability, and the node category of the target node is output to the user interface of the terminal device for display to the user.

In some possible implementations, the above-mentioned processor 1001 is used for:

Obtain at least one edge attribute of any type of edge connecting any neighbor node to the above-mentioned target node;

determining the attribute weight of each edge attribute in the at least one edge attribute;

Based on the attribute weights of the above-mentioned various edge attributes, the edge weights of any of the above-mentioned types of edges are determined, and the above-mentioned edge weights are determined as the number of the above-mentioned neighbor nodes that propagate the target label to the above-mentioned target node based on any of the above-mentioned types of edges. A probability to obtain each first probability that any of the neighbor nodes above propagates the target label to the above target node based on each type of edge between the above target node and the above target node.

In some possible implementations, the above-mentioned processor 1001 is used for:

at least one first probability corresponding to edges whose edge types belong to the same type are determined from the first probability set;

The first probability vector of the target node receiving the target label based on the same type of edge is constructed based on the at least one first probability.

In some possible implementations, the above-mentioned processor 1001 is used for:

Obtain the association relationship between each node in at least one social network, determine at least one node that has an association relationship with the target node from the above-mentioned each node based on the above-mentioned association relationship between each node, and determine the above-mentioned at least one node as the above-mentioned at least one node. The neighbor nodes of the target node.

In some possible implementations, the above-mentioned processor 1001 is used for:

Determine each type weight corresponding to each type of edge types, wherein one type corresponds to one type weight;

The second probability that the target node receives the target label is determined based on the above-mentioned respective type weights and the above-mentioned first probability vector set.

In some possible implementations, the above-mentioned processor 1001 is used for:

comparing the above-mentioned second probability with a preset threshold;

When the second probability is greater than or equal to the preset threshold, it is determined that the node type of the target node is the node type marked by the target label.

In some feasible implementation manners, the neighbor nodes of the target node include first-degree neighbor nodes of the target node and second-degree neighbor nodes of the target node, and the first-degree neighbor nodes are connected to the target node based on at least one type of edge The node, the above-mentioned second-degree neighbor node is any node connected with the above-mentioned target node based on any one-degree neighbor node;

The above processor 1001 is also used for:

It is determined that the above-mentioned target node receives the second probability vector of the above-mentioned target label propagated from each second-degree neighbor node based on the same type of edge, so as to obtain the above-mentioned target node based on multiple types of edges to receive the above-mentioned target label from each second-degree neighbor node. the second probability vector set;

The second probability that the target node receives the target tag is obtained based on the first probability vector set and the second probability vector set.

It should be understood that, in some feasible implementation manners, the above-mentioned processor 1001 may be a central processing unit (central processing unit, CPU), and the processor 1001 may also be other general-purpose processors, digital signal processors (digital signal processor, DSP) ), application specific integrated circuit (ASIC), off-the-shelf programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 1005 may include read only memory and random access memory, and provides instructions and data to the processor 1001 . A portion of memory 1005 may also include non-volatile random access memory. For example, the memory 1005 may also store information of the device type.

In specific implementation, the above-mentioned terminal device can execute the implementation manners provided by the respective steps in the above-mentioned FIG. 1 to FIG. 5 through various built-in function modules. For details, please refer to the implementation manners provided by the above-mentioned respective steps, which will not be repeated here.

In the embodiment of the present invention, by converting different types of node relationships in different social networks into the same type of node relationship, the restrictions on node relationships in different social networks can be eliminated, so that the node type of any node in different social networks can be determined. Make predictions. By calculating the attribute weight of each edge attribute of each type of edge, the corresponding weight of each edge attribute in the edge of its corresponding type can be determined. Therefore, the edge weight of each type of edge can be accurately and reasonably determined based on the attribute weight of each edge attribute, and the applicability is high.

An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and is executed by a processor to implement the method provided by each step in FIG. 1 to FIG. 5 . For details, please refer to the above steps. The provided implementation manner is not repeated here.

The above-mentioned computer-readable storage medium may be the task processing apparatus provided in any of the foregoing embodiments or an internal storage unit of the above-mentioned terminal device, such as a hard disk or a memory of an electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash memory equipped on the electronic device card (flash card), etc. The above-mentioned computer-readable storage medium may also include a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), and the like. Further, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been or will be output.

The terms "first", "second" and the like in the claims, description and drawings of the present invention are used to distinguish different objects, rather than to describe a specific order. Furthermore, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but optionally also includes unlisted steps or units, or optionally also includes For other steps or units inherent to these processes, methods, products or devices. Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification is not necessarily all referring to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments. As used in this specification and the appended claims, the term "and/or" refers to and including any and all possible combinations of one or more of the associated listed items.

Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. Interchangeability, the above description has generally described the components and steps of each example in terms of function. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.

The above disclosures are only preferred embodiments of the present invention, and of course, the scope of the rights of the present invention cannot be limited by this. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims (10)

1. A node category determination method, characterized in that the method comprises: The terminal device determines at least one neighbor node of the target node, wherein the neighbor node is a node connected to the target node based on at least one type of edge; The terminal device calculates at least one first probability that any neighbor node of the target node propagates a target label to the target node based on various types of edges connected to the target node, wherein one type of edge corresponds to a first probability to obtain a first set of probabilities that each neighbor node propagates the target label to the target node based on various types of edges; The terminal device determines, based on the first probability set, a first probability vector that the target node receives the target label based on the same type of edges, so as to obtain the probability that the target node receives the target label based on multiple types of edges. the first probability vector set; obtaining, by the terminal device, a second probability that the target node receives the target label based on the first probability vector set; The terminal device determines the node type of the target node based on the second probability, and outputs the node type of the target node to the user interface of the terminal device for display to the user. 2 . The method according to claim 1 , wherein the terminal device calculates that any neighbor node of the target node propagates target labels to the target node based on various types of edges connected to the target node. 3 . at least one first probability of , including: The terminal device acquires at least one edge attribute of any type of edge connecting any neighbor node to the target node; determining, by the terminal device, an attribute weight of each edge attribute in the at least one edge attribute; The terminal device determines the edge weight of the edge of any type based on the attribute weight of each edge attribute, and determines the edge weight as the edge weight of any neighbor node based on the edge of any type. The first probability of the target label being propagated to the target node to obtain each first probability of the target label being propagated to the target node by any of the neighbor nodes based on each type of edge between the target node and the target node. 3. The method according to claim 1, wherein the terminal device determines, based on the first probability set, the first probability vector that the target node receives the target label based on the same type of edge, comprising: The terminal device determines, from the first probability set, at least one first probability corresponding to edges whose edge types belong to the same type; The terminal device constructs, based on the at least one first probability, a first probability vector for the target node to receive the target label based on an edge of the same type. 4. The method according to any one of claims 1 to 3, wherein the terminal device determines a plurality of neighbor nodes of the target node, comprising: The terminal device acquires the association relationship between each node in at least one social network, determines at least one node that has an association relationship with the target node from the various nodes based on the association relationship between the various nodes, and assigns the associated relationship to the target node. The at least one node is determined as a neighbor node of the target node. 5. The method according to any one of claims 1 to 4, wherein the terminal device obtains, based on the first probability vector set, the second probability that the target node receives the target label, comprising: The terminal device determines each type weight corresponding to each type in the types of the edge, wherein one type corresponds to one type weight; The terminal device determines a second probability that the target node receives the target label based on the respective type weights and the first probability vector set. 6. The method according to any one of claims 1 to 5, wherein the terminal device determines the node type of the target node based on the second probability, comprising: The terminal device compares the second probability with a preset threshold; When the second probability is greater than or equal to the preset threshold, the terminal device determines that the node type of the target node is the node type marked by the target label. 7. The method according to claim 1, wherein the neighbor nodes of the target node include a first-degree neighbor node of the target node and a second-degree neighbor node of the target node, and the first-degree neighbor node is the same as the target node. Nodes connected based on at least one type of edge, the second-degree neighbor node is any node connected to the target node based on any one-degree neighbor node; The method also includes: The terminal device determines that the target node receives the second probability vector of the target label propagated from each second-degree neighbor node based on the same type of edges, so as to obtain that the target node receives from each second-degree based on multiple types of edges. Neighbor nodes propagate the second probability vector set of the target label; The terminal device obtains, based on the first probability vector set and the second probability vector set, a second probability that the target node receives the target tag. 8. An apparatus for determining a node type, wherein the apparatus comprises: a node determination module, configured to determine at least one neighbor node of the target node, wherein the neighbor node is a node connected to the target node based on at least one type of edge; A first probability determination module for calculating at least one first probability that any neighbor node of the target node propagates a target label to the target node based on various types of edges connected to the target node, one of which The type of edge corresponds to a first probability, so as to obtain a first probability set that each neighbor node propagates the target label to the target node based on various types of edges; A probability vector determination module, configured to determine, based on the first probability set, a first probability vector of the target node receiving the target label based on the same type of edges, so as to obtain the target node receiving the target label based on multiple types of edges the first probability vector set of target labels; a second probability determination module, configured to obtain a second probability that the target node receives the target tag based on the first probability vector set; A node type determination module, configured to determine the node type of the target node based on the second probability, and output the node type of the target node to the user interface of the terminal device for display to the user. 9. A terminal device, comprising: a processor and a memory; The processor is connected to a memory, wherein the memory is used to store program codes, and the processor is used to call the program codes to execute the method according to any one of claims 1-7. 10. A computer storage medium, characterized in that the computer storage medium stores a computer program, the computer program comprises program instructions, and the program instructions, when executed by a processor, execute any one of claims 1-7. method described in item.

Images