Systems and methods for updating a knowledge graph through user input

1. A method for providing recommendations based on a user's conversational communications, the method comprising:

receiving, via a user interface, a user communication;

extracting a first term of the user communication;

comparing the first term to a plurality of terms represented by a respective plurality of nodes in a knowledge graph;

in response to determining that no node in the knowledge graph represents a term corresponding to the first term:

identifying a candidate node;

generating for output, via the user interface, a prompt to confirm an association between the first term and a second term represented by the candidate node of the knowledge graph; and

in response to receiving, in response to the prompt, a confirmation of association between the first term and the second term, creating a new node corresponding to the first term and an edge connecting the new node with the candidate node in the knowledge graph; and

generating a content recommendation associated with the second term.

2. The method of claim 1 , further comprising:

receiving, via the user interface, a second user communication;

identifying a third term of the second user communication, wherein the third term corresponds to the candidate node;

generating for output, via the user interface, a second prompt for user input directed to confirming whether the third term is associated with the first term; and

in response to receiving the user input, modifying a strength of association between the new node and the candidate node.

3. The method of claim 2 , wherein modifying the strength of associated between the new node and the candidate node further comprises:

determining whether the user input confirms or denies that the third term is associated with the first term; and

in response to determining that the user input confirms that the third term is associated with the first term, increasing the strength of association between the new node and the candidate node.

4. The method of claim 2 , wherein modifying the strength of associated between the new node and the candidate node further comprises:

determining whether the user input confirms or denies that the third term is associated with the first term; and

in response to determining that the user input denies that the third term is associated with the first term, decreasing the strength of association between the new node and the candidate node.

5. The method of claim 2 , wherein the strength of association is represented by a weight allocated to an edge connecting the new node and the candidate node.

6. The method of claim 1 , wherein generating the prompt further comprises providing information associated with the candidate node.

7. The method of claim 1 , further comprising providing information associated with an additional component of the knowledge graph that has high strength of association between the first term and the additional component.

8. The method of claim 1 , wherein identifying the candidate node further comprises cross-referencing the first term with candidate terms represented by candidate nodes of the knowledge graph stored in a database.

9. The method of claim 1 , wherein identifying the candidate node further comprises:

identifying a plurality of candidate nodes of the knowledge graph;

ranking each of the plurality of candidate nodes;

identifying a highest ranked candidate node of the plurality of candidate nodes as the candidate node;

receiving a user input that denies that the first term is associated with the candidate node; and

in response to receiving the user input, identifying a next highest ranked candidate node of the plurality of candidate nodes as the candidate node.

10. The method of claim 1 , wherein the user communication is verbal or textual.

11. A system for providing recommendations based on a user's conversational communications, the system comprising:

storage circuitry configured to store a knowledge graph having a plurality of nodes and a plurality of edges;

communications circuitry configured to receive a user communication; and

control circuitry configured to:

receive, via a user interface, a user communication;

extract a first term of the user communication;

compare the first term to a plurality of terms represented by a respective plurality of nodes in a knowledge graph;

in response to determining that no node in the knowledge graph represents a term corresponding to the first term:

identify a candidate node;

generate for output, via the user interface, a prompt to confirm an association between the first term and a second term represented by the candidate node of the knowledge graph; and

in response to receiving, in response to the prompt, a confirmation of association between the first term and the second term, create a new node corresponding to the first term and an edge connecting the new node with the candidate node in the knowledge graph; and

generate a content recommendation associated with the second term.

12. The system of claim 11 , wherein the control circuitry is further configured to:

receive, via the user interface, a second user communication;

identify a third term of the second user communication, wherein the third term corresponds to the candidate node;

generate for output, via the user interface, a second prompt for user input directed to confirming whether the third term is associated with the first term; and

in response to receiving the user input, modifying a strength of association between the new node and the candidate node.

13. The system of claim 12 , wherein the control circuitry configured to modify the strength of associated between the new node and the candidate node is further configured to:

determine whether the user input confirms or denies that the third term is associated with the first term; and

in response to determining that the user input confirms that the third term is associated with the first term, increase the strength of association between the new node and the candidate node.

14. The system of claim 12 , wherein the control circuitry configured to modify the strength of associated between the new node and the candidate node is further configured to:

determine whether the user input confirms or denies that the third term is associated with the first term; and

in response to determining that the user input denies that the third term is associated with the first term, decrease the strength of association between the new node and the candidate node.

15. The system of claim 12 , wherein the strength of association is represented by a weight allocated to an edge connecting the new node and the candidate node.

16. The system of claim 11 , wherein the control circuitry configured to generate the prompt is further configured to provide information associated with the candidate node.

17. The system of claim 11 , wherein the control circuitry is further configured to provide information associated with an additional component of the knowledge graph that has high strength of association between the first term and the additional component.

18. The system of claim 11 , wherein the control circuitry configured to identify the candidate node is further configured to cross-reference the first term with candidate terms represented by candidate nodes of the knowledge graph stored in a database.

19. The system of claim 11 , wherein the control circuitry configured to identify the candidate node is further configured to:

identify a plurality of candidate nodes of the knowledge graph;

rank each of the plurality of candidate nodes;

identify a highest ranked candidate node of the plurality of candidate nodes as the candidate node;

receive a user input that denies that the first term is associated with the candidate node; and

in response to receiving the user input, identify a next highest ranked candidate node of the plurality of candidate nodes as the candidate node.

20. The system of claim 11 , wherein the user communication is verbal or textual.