Systems and methods for updating a knowledge graph through user input
Methods and systems are disclosed herein for updating a knowledge graph based on a user confirmation. A media guidance application receives a user communication and isolates a term of the user communication. The media guidance application identifies a candidate component of a knowledge graph associated with the term. The media guidance application requests user input directed to confirming whether the term is associated with the candidate component. In response to receiving the user input, the media guidance application modifies a strength of association between the term and the component.
1. A method comprising:
receiving, via a user interface, a first user input;
extracting a term of the first user input;
accessing a database comprising a plurality of candidate components;
identifying a subset of the plurality of candidate components related to the extracted term;
assigning a plurality of ranks to each candidate component of the subset of the plurality of candidate components;
identifying a first candidate component of the subset of the plurality of candidate components based on a first rank of the plurality of ranks assigned to the first candidate component;
generating for display, via the user interface, a first prompt directed to confirming whether the term is associated with the first candidate component;
receiving a second user input, wherein the second user input denies that the term is associated with the first candidate component;
in response to receiving the second user input, identifying a second candidate component of the subset of the plurality of candidate components based on a second rank assigned to the second candidate component; and
generating a content recommendation associated with the second candidate component.
2. The method of claim 1 , further comprising:
generating for display, via the user interface, a second prompt directed to confirming whether the term is associated with the second candidate component;
receiving a third user input, wherein the third user input confirms that the term is associated with the first candidate component; and
in response to receiving the third user input, generating the content recommendation associated with the second candidate component.
3. The method of claim 2 , wherein the second candidate component of the subset of the plurality of candidate components is identified because the second rank assigned to the second candidate component is the next highest rank after the first rank.
4. The method of claim 1 , wherein the first rank is assigned according to a first date associated with the first candidate component.
5. The method of claim 1 , wherein the first rank is assigned according to a first piece of metadata associated with the first candidate component.
6. The method of claim 1 , wherein assigning the plurality of ranks to each candidate component of the subset of the plurality of candidate components comprises:
determining a relevance between the first candidate component and the term; and
assigning the first rank to the first candidate component based on the relevance between the first candidate component and the term.
7. The method of claim 1 , wherein the database comprises a knowledge graph having a plurality of nodes representing different pieces of information and a plurality of edges connecting the plurality of nodes representing relationships between the different pieces of information.
8. The method of claim 7 , wherein assigning the plurality of ranks to each candidate component of the subset of the plurality of candidate components comprises:
identifying a first node of the plurality of nodes representing the first candidate component that is connected to a second node of the plurality of nodes representing the term;
determining a distance in the knowledge graph between the first node of the plurality of nodes and the second node of the plurality of nodes; and
assigning the first rank to the first candidate component based on the distance between the first node of the plurality of nodes and the second node of the plurality of nodes.
9. The method of claim 7 , further comprising:
identifying a first node of the plurality of nodes representing the first candidate component that is connected to a second node of the plurality of nodes representing the term; and
modifying a strength of association represented by a weight allocated to an edge connecting the second node and the first node in the knowledge graph in response to receiving the first user input.
10. The method of claim 7 , further comprising:
identifying a third node of the plurality of nodes representing the second candidate component that is connected to the second node of the plurality of nodes representing the term; and
modifying a strength of association represented by a weight allocated to an edge connecting the second node and the third node in the knowledge graph in response to receiving the second user input.
11. An apparatus, comprising:
control circuitry; and
at least one memory including computer program code for one or more programs, the at least one memory and the computer program code configured to, with the control circuitry, cause the apparatus to perform at least the following:
receive a first user input;
extract a term of the first user input;
access a database comprising a plurality of candidate components;
identify a subset of the plurality of candidate components related to the extracted term;
assign a plurality of ranks to each candidate component of the subset of the plurality of candidate components;
identify a first candidate component of the subset of the plurality of candidate components based on a first rank of the plurality of ranks assigned to the first candidate component;
generate for display a first prompt directed to confirming whether the term is associated with the first candidate component;
receive a second user input, wherein the second user input denies that the term is associated with the first candidate component;
identify, in response to receiving the second user input, a second candidate component of the subset of the plurality of candidate components based on a second rank assigned to the second candidate component; and
generate a content recommendation associated with the second candidate component.
12. The apparatus of claim 11 , wherein the apparatus is further caused to:
generate for display a second prompt directed to confirming whether the term is associated with the second candidate component;
receive a third user input, wherein the third user input confirms that the term is associated with the first candidate component; and
generate the content recommendation associated with the second candidate component in response to receiving the third user input.
13. The apparatus of claim 12 , wherein the second candidate component of the subset of the plurality of candidate components is identified because the second rank assigned to the second candidate component is the next highest rank after the first rank.
14. The apparatus of claim 11 , wherein the first rank is assigned according to a first date associated with the first candidate component.
15. The apparatus of claim 11 , wherein the first rank is assigned according to a first piece of metadata associated with the first candidate component.
16. The apparatus of claim 11 , wherein the apparatus is further caused, when assigning the plurality of ranks to each candidate component of the subset of the plurality of candidate components, to:
determine a relevance between the first candidate component and the term; and
assign the first rank to the first candidate component based on the relevance between the first candidate component and the term.
17. The apparatus of claim 11 , wherein the database comprises a knowledge graph having a plurality of nodes representing different pieces of information and a plurality of edges connecting the plurality of nodes representing relationships between the different pieces of information.
18. The apparatus of claim 17 , wherein the apparatus is further caused, when assigning the plurality of ranks to each candidate component of the subset of the plurality of candidate components, to:
identify a first node of the plurality of nodes representing the first candidate component that is connected to a second node of the plurality of nodes representing the term;
determine a distance in the knowledge graph between the first node of the plurality of nodes and the second node of the plurality of nodes; and
assign the first rank to the first candidate component based on the distance between the first node of the plurality of nodes and the second node of the plurality of nodes.
19. The apparatus of claim 17 , wherein the apparatus is further caused to:
identify a first node of the plurality of nodes representing the first candidate component that is connected to a second node of the plurality of nodes representing the term; and
modify a strength of association represented by a weight allocated to an edge connecting the second node and the first node in the knowledge graph in response to receiving the first user input.
20. The apparatus of claim 17 , wherein the apparatus is further caused to:
identify a third node of the plurality of nodes representing the second candidate component that is connected to the second node of the plurality of nodes representing the term; and
modify a strength of association represented by a weight allocated to an edge connecting the second node and the third node in the knowledge graph in response to receiving the second user input.