Method and apparatus for processing graph data, device, storage medium, and program product

A graph data processing apparatus, comprising:

• at least one memory configured to store computer program code;
• and
• at least one processor configured to operate as instructed by the computer program code, the computer program code including:
• acquisition code configured to cause the at least one processor to acquire relationship data formed when terminals interact through an application server, the relationship data representing interactions between user identifiers in a network system;
• generation code configured to cause the at least one processor to generate a directed graph from the relationship data, wherein a vertex in the directed graph represents a user identifier, and a directed edge in the directed graph represents a directional relationship between user identifiers corresponding to a start vertex and a destination vertex;
• edge representation code configured to cause the at least one processor to re-represent the directed edge in a unified form that is different from a form of the directed graph as obtained, in a data structure comprising a matrix or a list, according to a specified order between a vertex identifier of the start vertex and a vertex identifier of the destination vertex, wherein the specified order is determined independently from a traversal order of the directed graph;
• edge tagging code configured to cause the at least one processor to record, in the data structure, a tagged edge indicating an original edge direction of the directed edge prior to re-representing the directed edge in the unified form based on the original edge direction being different than an edge direction of the re-represented directed edge, to obtain a tagged directed graph, wherein a tag of the tagged edge indicates which first vertex from among vertices in the acquired directed graph corresponds to the start vertex and which second vertex from among the vertices in the acquired directed graph corresponds to the destination vertex;
• and
• identification code configured to cause the at least one processor to identify a category of a triangle constituted by a vertex in the tagged directed graph, a neighbor vertex of the vertex, and a common vertex commonly adjacent to the vertex and the neighbor vertex, based on tagged edges between two of the vertex, the neighbor vertex, and the common vertex, the identified category of the triangle being used for generating a feature vector of the vertex,
• wherein the identified category of the triangle is configured for generating a feature vector of the vertex for application to pattern identification tasks including identifying abnormal network activities or discovering network communities.

At least one non-transitory computer-readable storage medium, storing computer-readable instructions that, when executed by at least one processor, cause the at least one processor to:

• acquire relationship data formed when terminals interact through an application server, the relationship data representing interactions between user identifiers in a network system;
• generate a directed graph from the relationship data, wherein a vertex in the directed graph represents a user identifier, and a directed edge in the directed graph represents a directional relationship between user identifiers corresponding to a start vertex and a destination vertex;
• acquire a directed graph, a directed edge in the directed graph being represented as pointing to a destination vertex from a start vertex;
• re-representing the directed edge in a unified form that is different from a form of the directed graph as obtained, in a data structure comprising a matrix or a list, according to a specified order between a vertex identifier of the start vertex and a vertex identifier of the destination vertex, wherein the specified order is determined independently from a traversal order of the directed graph;
• recording, in the data structure, a tagged edge indicating an original edge direction of the directed edge prior to re-representing the directed edge in the unified form based on the original edge direction being different than an edge direction of the re-represented directed edge, to obtain a tagged directed graph, wherein a tag of the tagged edge indicates which first vertex from among vertices in the acquired directed graph corresponds to the start vertex and which second vertex from among the vertices in the acquired directed graph corresponds to the destination vertex;
• and
• identify a category of a triangle constituted by a vertex in the tagged directed graph, a neighbor vertex of the vertex, and a common vertex commonly adjacent to the vertex and the neighbor vertex, based on tagged edges between two of the vertex, the neighbor vertex, and the common vertex, the identified category of the triangle being used for generating a feature vector of the vertex,
• wherein the identified category of the triangle is configured for generating a feature vector of the vertex for application to pattern identification tasks including identifying abnormal network activities or discovering network communities.