Classification model generation method and apparatus, and data identification method and apparatus

A non-transitory, computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

• obtaining, by one or more processing devices, a training sample dataset, wherein the training sample dataset comprises at least two pieces of sample data and a sample label corresponding to each piece of sample data;
• constructing, by the one or more processing devices, a first relational network of the at least two pieces of sample data, and representing the at least two pieces of sample data using nodes of the first relational network, wherein each node in the first relational network is connected to a set of adjacent nodes through a set of outgoing edges, each outgoing edge comprising a weight value;
• obtaining, by the one or more processing devices, a vectorized representation of each node in the first relational network based on a predetermined network embedding learning model comprising:
• for each node in the first relational network,
• calculating a transition probability for each outgoing edge of the node based on i) the weight value of the outgoing edge and ii) a sum of weight values of the set of outgoing edges;
• generating a first node sequence using a random walk process based on the transition probability of each outgoing edge, the first node sequence comprising a set of nodes reached during the random walk process;
• and
• vectorizing each node in the first node sequence based on the predetermined network embedding learning model;
• and
• training, by the one or more processing devices, a classification model based on the training sample dataset, wherein the classification model associates the sample label with the vectorized representation of each node in the first relational network, wherein the classification model is periodically updated based on a updated training sample datasets.

A computer-implemented system, comprising:

• one or more computers;
• and
• one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:
• obtaining, by one or more processing devices, a training sample dataset, wherein the training sample dataset comprises at least two pieces of sample data and a sample label corresponding to each piece of sample data;
• constructing, by the one or more processing devices, a first relational network of the at least two pieces of sample data, and representing the at least two pieces of sample data using nodes of the first relational network, wherein each node in the first relational network is connected to a set of adjacent nodes through a set of outgoing edges, each outgoing edge comprising a weight value;
• obtaining, by the one or more processing devices, a vectorized representation of each node in the first relational network based on a predetermined network embedding learning model comprising:
• for each node in the first relational network,
• calculating a transition probability for each outgoing edge of the node based on i) the weight value of the outgoing edge and ii) a sum of weight values of the set of outgoing edges;
• generating a first node sequence using a random walk process based on the transition probability of each outgoing edge, the first node sequence comprising a set of nodes reached during the random walk process;
• and
• vectorizing each node in the first node sequence based on the predetermined network embedding learning model;
• and
• training, by the one or more processing devices, a classification model based on the training sample dataset, wherein the classification model associates the sample label with the vectorized representation of each node in the first relational network, wherein the classification model is periodically updated based on updated training sample datasets.