System and methods for disambiguating an ambiguous entity in a search query based on the gaze of a user
Systems and methods for disambiguation of an ambiguous entity in a search query based on the gaze of a user. These systems and methods may be implemented by a media guidance application (e.g., executed by user equipment associated with the user). In some aspects, the media guidance application may monitor the gaze of the user and attempt to disambiguate the ambiguous entity based on an area of the screen the user viewed while issuing the search query. If the media guidance application receives an indication that it did not disambiguate the ambiguous entity in the search query correctly, the media guidance application may increase the area of the screen that the user viewed in order to find an additional entity. This may allow the media guidance application to quickly and accurately find the correct answer to the user's search query.
1. A method for disambiguating a search query, the method comprising:
receiving, at a first time during display of media content, an ambiguous search query related to the media content;
identifying a frame of the media content being displayed at the first time;
determining a first portion of the identified frame corresponding to a gaze of the user at the first time;
retrieving metadata associated with the first portion of the identified frame;
generating a first disambiguated search query using the ambiguous search query and the metadata;
generating for output a search result for the first disambiguated search query;
receiving input indicating that the first disambiguated search query is not correct;
in response to receiving the input indicating that the first disambiguated search query is not correct, determining an enlarged portion of the identified frame, wherein a center point of the enlarged portion is same as a center point of the first portion of the identified frame, wherein determining the enlarged portion comprises enlarging the first portion until at least one additional entity is encompassed therein;
retrieving metadata associated with the enlarged portion of the identified frame;
generating a second disambiguated search query using the ambiguous search query and the metadata associated with the enlarged portion of the identified frame; and
generating for output a search result for the second disambiguated search query.
2. The method of claim 1 , wherein determining the first portion of the identified frame corresponding to a gaze of the user at the first time further comprises:
identifying a direction of the gaze of the user relative to a display screen on which the media content is being displayed; and
determining, based on the direction, a first area of the display screen corresponding to the gaze of the user.
3. The method of claim 1 , further comprising:
identifying an entity displayed in the first portion of the identified frame corresponding to the gaze of the user;
identifying a pronoun in the ambiguous search query; and
determining, based on the metadata, whether the identified entity displayed in the first portion of the identified frame is associated with the identified pronoun.
4. The method of claim 3 , wherein generating the first disambiguated search query using the ambiguous search query and the metadata further comprises determining that the identified entity displayed in the first portion of the identified frame is associated with the identified pronoun.
5. The method of claim 3 , wherein generating the first disambiguated search query based on the ambiguous search query and the metadata further comprises:
in response to determining that the identified entity displayed in the first portion of the identified frame is not associated with the identified pronoun:
identifying a second entity displayed in the first portion of the identified frame; and
determining, based on the metadata, whether the second entity is associated with the identified pronoun, wherein the first disambiguated search query is generated based on the second entity and the metadata in response to determining that the second entity is associated with the identified pronoun.
6. The method of claim 1 , further comprising generating for display a prompt for additional input, wherein the prompt indicates an entity displayed in the first portion of the identified frame as a potential disambiguation of the ambiguous search query.
7. The method of claim 6 , further comprising:
receiving, in response to the prompt, an input indicating that the indicated entity is a correct disambiguation of the ambiguous search query; and
in response to receiving the input, disambiguating the ambiguous search query based on the indicated entity.
8. The method of claim 6 , further comprising:
receiving, in response to the prompt, an input indicating that the indicated entity is not a correct disambiguation of the ambiguous search query; and
in response to receiving the input:
identifying a second entity displayed in the first portion of the identified frame; and
generating for display a second prompt for additional input, wherein the second prompt indicates the second entity as a second potential disambiguation of the ambiguous search query.
9. The method of claim 1 , further comprising searching a database for media content that includes an entity corresponding to the disambiguated search query.
10. The method of claim 1 , wherein an entity corresponding to the disambiguated search query is selected from the group consisting of an actor, and actress, an object, an animal, and a character.
11. A system for disambiguating a search query, the system comprising:
input circuitry configured to receive, at a first time during display of media content, an ambiguous search query related to the media content; and
control circuitry configured to:
identify a frame of the media content being displayed at the first time;
determine a first portion of the identified frame corresponding to a gaze of the user at the first time;
retrieve metadata associated with the first portion of the identified frame;
generate a disambiguated search query using the ambiguous search query and the metadata;
generate for output a search result for the first disambiguated search query;
receive input indicating that the first disambiguated search query is not correct;
in response to receiving the input indicating that the first disambiguated search query is not correct, determine an enlarged portion of the identified frame, wherein a center point of the enlarged portion is same as a center point of the first portion of the identified frame, wherein determining the enlarged portion comprises enlarging the first portion until at least one additional entity is encompassed therein;
retrieve metadata associated with the enlarged portion of the identified frame;
generate a second disambiguated search query using the ambiguous search query and the metadata associated with the enlarged portion of the identified frame; and
generate for output a search result for the second disambiguated search query.
12. The system of claim 11 , wherein the control circuitry configured to determine the first portion of the identified frame corresponding to a gaze of the user at the first time is further configured to:
identify a direction of the gaze of the user relative to a display screen on which the media content is being displayed; and
determine, based on the direction, a first area of the display screen corresponding to the gaze of the user.
13. The system of claim 11 , wherein the control circuitry is further configured to:
identify an entity displayed in the first portion of the identified frame corresponding to the gaze of the user;
identify a pronoun in the ambiguous search query; and
determine, based on the metadata, whether the identified entity displayed in the first portion of the identified frame is associated with the identified pronoun.
14. The system of claim 13 , wherein the control circuitry configured to generate the first disambiguated search query based on the ambiguous search query and the metadata is further configured to determine that the identified entity displayed in the first portion of the identified frame is associated with the identified pronoun.
15. The system of claim 13 , wherein the control circuitry configured to generate the first disambiguated search query based on the ambiguous search query and the metadata is further configured to:
in response to determining that the identified entity displayed in the first portion of the identified frame is not associated with the identified pronoun:
identify a second entity displayed in the first portion of the identified frame; and
determine, based on the metadata, whether the second entity is associated with the identified pronoun, wherein the control circuitry is configured to generate the first disambiguated search query based on the second entity and the metadata in response to determining that the second entity is associated with the identified pronoun.
16. The system of claim 11 , wherein the control circuitry is further configured to generate for display a prompt for additional input, wherein the prompt indicates an entity displayed in the first portion of the identified frame as a potential disambiguation of the ambiguous search query.
17. The system of claim 16 , wherein:
the input circuitry is further configured to receive, in response to the prompt, an input indicating that the indicated entity is a correct disambiguation of the ambiguous search query; and
the control circuitry is further configured to, in response to receiving the input, disambiguate the ambiguous search query based on the indicated entity.
18. The system of claim 16 , wherein:
the input circuitry is further configured to receive, in response to the prompt, an input indicating that the indicated entity is not a correct disambiguation of the ambiguous search query; and
the control circuitry is further configured to, in response to receiving the input:
identify a second entity displayed in the first portion of the identified frame; and
generate for display a second prompt for additional input, wherein the second prompt indicates the second entity as a second potential disambiguation of the ambiguous search query.
19. The system of claim 11 , wherein the control circuitry is further configured to search a database for media content that includes an entity corresponding to the disambiguated search query.
20. The system of claim 11 , wherein an entity corresponding to the disambiguated search query is selected from the group consisting of an actor, and actress, an object, an animal, and a character.
21. The method of claim 1 , wherein the enlarging the first portion of the identified frame comprises adding an additional portion of the identified frame corresponding to the gaze of the user at the first time.