Load balancing method and system for providing artificial intelligence service

An Artificial Intelligence (AI) service providing system, comprising:

• a data center including a load balancing device and a plurality of servers;
• and
• a user device connected to the data center via a network,
• wherein the plurality of servers generates load balancing information and transmits the load balancing information to the load balancing device, wherein the load balancing information for a respective one server of the plurality of servers comprises connection information of the respective one server, information of one or more AI models supported by the respective one server, and information of hardware supporting the one or more AI models,
• wherein the load balancing device generates a load balancing table based on the load balancing information, wherein the load balancing table is used for load balancing between the plurality of servers and comprises connection information of the plurality of servers, information of AI models supported by the plurality of servers, and information of hardware supporting the AI models supported by the plurality of servers, wherein the load balancing device obtains an inference task request message for an AI service from the user device, derives at least one target server among the plurality of servers based on the inference task request message for the AI service and the load balancing table, performs load balancing for an inference task of the AI service on the derived target server based on a preset load balancing algorithm, and transmits a result of the inference task transmitted from a target server to which the inference task is distributed to the user device, and
• wherein the load balancing device derives target load balancing information including same information as information included in the inference task request message from the load balancing table, and wherein the load balancing device derives a server indicated by connection information of the derived target load balancing information as the target server.