Natural language-based content system with corrective feedback and training

A network device comprising:

• a communication interface;
• a memory, wherein the memory stores instructions;
• and
• a processor, wherein the processor executes the instructions to:
• present a search result for contents based on a first search query from a user;
• monitor, in response to the presentment, an interaction of the user with the search result, wherein the interaction includes the user providing a second search query;
• analyze the second search query;
• identify, based on the analysis and quaternary choices including a full generalization, a partial generalization, a full refinement, and a partial refinement, that the second search query is one of the full generalization, the partial generalization, the full refinement, or the partial refinement;
• generate, based on the identification, feedback data indicating the interaction of the user;
• and
• update, based on the feedback data, at least one of a natural language understanding device that interprets search queries from users based on query object types or a search and discovery device that searches and selects relevant content items for inclusion in search results.

A non-transitory computer-readable storage medium storing instructions executable by a processor of a device, which when executed, cause the device to:

• present a search result for contents based on a first search query from a user;
• monitor, in response to the presentment, an interaction of the user with the search result, wherein the interaction includes the user providing a second search query;
• analyze the second search query;
• identify, based on the analysis and quaternary choices including a full generalization, a partial generalization, a full refinement, and a partial refinement, that the second search query is one of the full generalization, the partial generalization, the full refinement, or the partial refinement;
• generate, based on the identification, feedback data indicating the interaction of the user;
• and
• update, based on the feedback data, at least one of a natural language understanding device that interprets search queries from users based on query object types or a search and discovery device that searches and selects relevant content items for inclusion in search results.