| CPC G06F 16/9535 (2019.01) [G06F 16/9024 (2019.01); G06N 5/022 (2013.01)] | 16 Claims |
|
1. A method of a device for generating a knowledge graph, the method comprising:
obtaining, by the device, log history information about an operation of the device;
generating, by the device, a device knowledge graph based on the log history information, wherein the device knowledge graph is in an ontology form comprising a first entity expressed in a resource description framework (RDF);
generating, by the device, a pattern knowledge graph associated with a behavior pattern of a user of the device based on first entities in the device knowledge graph and a relationship between the first entities;
updating, by the device, the device knowledge graph by adding the pattern knowledge graph to the device knowledge graph, wherein device recommendation knowledge generated based on the log history information of the device is connected to server recommendation knowledge generated based on a server knowledge graph of a server to update the device knowledge graph, whereby a content recommendation is formulated at the device based on both the server recommendation knowledge and the device recommendation knowledge, wherein the knowledge graph of the server is in the ontology form expressing a second entity, the knowledge graph of the server is updated periodically by the server based on big data collected through web crawling, the server supports a search engine and the knowledge graph of the server supports the search engine;
updating, by the device, the server knowledge graph generated by the server, based on the pattern knowledge graph by connecting the device recommendation knowledge in the form of the first entity to server recommendation knowledge in the form of the second entity learned through big data, and
providing to the user of the device the content recommendation on a user interface of the device, wherein the content recommendation is based on the updated device knowledge graph, whereby the device is configured to recommend user-customized content to the user by using the updated device knowledge graph,
wherein the log history information includes data indicating the operation of the device, and the data indicating the operation of the device is collected in the device as the user uses the device;
the method further comprising:
obtaining context data indicating a current context of the device;
determining a function to be provided to the user by using the obtained context data and the pattern knowledge graph in the updated device knowledge graph; and
executing the determined function, wherein the executing the determined function includes providing the content recommendation to the user based on the updated device knowledge graph,
wherein the determining of the function comprises determining the content recommendation to be provided to the user, and
the determining of the content recommendation comprises:
determining a first recommended content based on the obtained context data indicating the current context of the user and the server knowledge graph;
confirming a presence or absence of the pattern knowledge graph; and
selecting a recommended content based on a result of the confirming.
|