| CPC G06N 5/025 (2013.01) [G06N 20/20 (2019.01)] | 14 Claims |
|
1. A device for providing content based on a knowledge graph, the device comprising:
a communication interface;
a memory storing one or more instructions; and
a processor configured to execute the one or more instructions to:
obtain context information related to the device;
generate, using the device, a first device knowledge graph of a user of the device by inputting the obtained context information to a first artificial intelligence (AI) model for determining a relation between entities related to the user of the device;
control to request, from a server, a server knowledge graph generated by the server;
control to receive the server knowledge graph from the server;
generate, using the device, a second device knowledge graph of the user by inputting the generated first device knowledge graph and the received server knowledge graph to a second AI model for extending the first device knowledge graph on the device; and
provide content based on the generated second device knowledge graph,
wherein the context information includes at least one information related to privacy of the user, the at least one information related to the privacy of the user is not transmitted outside of the device, and the server knowledge graph is generated without using any information related to the privacy of the user,
wherein each of the first AI model and the second AI model is an AI model trained by using, as an AI algorithm, a neural network algorithm in which a plurality of neural network layers have a plurality of weight values, wherein the plurality of weight values of the plurality of neural network layers are applied to the input context information and a computation result of a previous layer to determine the relation between entities related to the user of the device, and wherein the plurality of weight values are updated based on the determined relation between entities to reduce a loss value obtained by the AI model to optimize a training result of the AI model,
wherein the server knowledge graph is generated by the server based on big data provided to the server by the device and at least one other device,
wherein the processor is further configured to execute the one or more instructions to determine a privacy level for the first device knowledge graph and input the determined privacy level to the first AI model,
wherein a part of data in the first device knowledge graph output from the first AI model comprises data abstracted according to the privacy level,
wherein based on the privacy level being a first privacy level, the data includes a reference to a specific name, and based on the privacy level being a second privacy level, the data is abstracted to refer to a general name and not the specific name, and
wherein the second AI model extends the first device knowledge graph by analyzing and integrating the first device knowledge graph and the server knowledge graph.
|