Systems and methods for using conjunctions in a voice input to cause a search application to wait for additional inputs

1. A computer-implemented method, comprising:

receiving, at a media device, a voice input from a user;

detecting, by processing the voice input, a conjunction;

in response to detecting the conjunction, waiting for additional input associated with a particular entity being displayed to the user or being captured by a camera of the media device;

receiving the additional input associated with the particular entity;

querying a database based on the voice input and the particular entity;

based on querying the database, receiving at least one identifier of at least one content item; and

generating for display, on the media device, the at least one identifier.

2. The method of claim 1 , wherein the particular entity is a second entity, the method further comprising:

receiving, at the media device, a selection of a first entity currently being displayed on a display of the media device, wherein the first entity is associated with the voice input;

wherein querying the database is further based on the first entity, in addition to the second entity and the voice input.

3. The method of claim 1 , wherein querying the database further comprises:

constructing a search query based on the voice input and the particular entity; and

transmitting the search query to the database.

4. The method of claim 3 , wherein the conjunction is a coordinating conjunction, and constructing the search query further comprises:

determining a type of the coordinating conjunction;

identifying a logical operator corresponding to the type of coordinating conjunction; and

generating a search string comprising an entity associated with the voice input and the particular entity separated by the logical operator.

5. The method of claim 3 , wherein the conjunction is a subordinating conjunction, and constructing the search query further comprises:

identifying a search parameter corresponding to the type of subordinating conjunction; and

generating a search string comprising the identified search parameter, an entity associated with the voice input, and the particular entity.

6. The method of claim 3 , further comprising:

processing the voice input to identify a search operator;

wherein the search query is constructed based on the conjunction, an entity associated with the voice input, the particular entity, and the identified search operator.

7. The method of claim 1 , wherein receiving the additional input comprises:

identifying a gesture made by the user; and

determining that the particular entity is associated with the gesture, wherein the particular entity is not being displayed on the display of the media device.

8. The method of claim 7 , wherein:

identifying the gesture made by the user comprises capturing, using the camera, an image of an area associated with the gesture, wherein the image comprises a real-world entity; and

determining the particular entity corresponds to the real-world entity.

9. The method of claim 7 , wherein:

the media device is a first media device;

the particular entity is being displayed on a second media device proximate to the user; and

the gesture is associated with the particular entity being displayed on the second media device.

10. The method of claim 1 , further comprising:

processing the voice input to identify a pronoun;

identifying a plurality of candidate entities being displayed to the user or being captured by the camera of the media device;

performing image processing to identify a plurality of entities in the image; and

determining a respective pronoun corresponding to each respective candidate entity of the plurality of candidate entities;

determining the particular entity by selecting a candidate entity of the plurality of candidate entities having a respective pronoun that matches the identified pronoun.

11. A computer-implemented system, comprising:

input/output (I/O) circuitry;

control circuitry configured to:

receive, at a media device, a voice input from a user;

detect, by processing the voice input, a conjunction; and

in response to detecting the conjunction, wait for additional input associated with a particular entity being displayed to the user or being captured by a camera of the media device; and

receive the additional input associated with the particular entity;

wherein the I/O circuitry is configured to:

query a database based on the voice input and the particular entity; and

based on querying the database, receive at least one identifier of at least one content item;

wherein the control circuitry is further configured to:

generate for display, on the media device, the at least one identifier.

12. The system of claim 11 , wherein the particular entity is a second entity, and the control circuitry is further configured to:

determine, at the media device, a selection of a first entity currently being displayed on a display of the media device, wherein the first entity is associated with the voice input; and

query the database further based on the first entity, in addition to the second entity and the voice input.

13. The system of claim 11 , wherein:

the control circuitry is further configured to construct a search query based on the voice input and the particular entity; and

the I/O circuitry is configured to query the database by transmitting the search query to the database.

14. The system of claim 13 , wherein the conjunction is a coordinating conjunction, and the control circuitry is configured to construct the search query by:

determining a type of the coordinating conjunction;

identifying a logical operator corresponding to the type of coordinating conjunction; and

generating a search string comprising an entity associated with the voice input and the particular entity separated by the logical operator.

15. The system of claim 13 , wherein the conjunction is a subordinating conjunction, and the control circuitry is configured to construct the search query by:

identifying a search parameter corresponding to the type of subordinating conjunction; and

generating a search string comprising the identified search parameter, an entity associated with the voice input, and the particular entity.

16. The system of claim 13 , wherein the control circuitry is further configured to:

process the voice input to identify a search operator; and

construct the search query based on the conjunction, an entity associated with the voice input, the particular entity, and the identified search operator.

17. The system of claim 11 , wherein receiving the additional input comprises:

identifying a gesture made by the user; and

determining that the particular entity is associated with the gesture, wherein the particular entity is not being displayed on the display of the media device.

18. The system of claim 17 , wherein:

identifying the gesture made by the user comprises capturing, using the camera, an image of an area associated with the gesture, wherein the image comprises a real-world entity; and

determining the particular entity corresponds to the real-world entity.

19. The system of claim 17 , wherein:

the media device is a first media device;

the particular entity is being displayed on a second media device proximate to the user; and

the gesture is associated with the particular entity being displayed on the second media device.

20. The system of claim 11 , further comprising:

processing the voice input to identify a pronoun;

identifying a plurality of candidate entities being displayed to the user or being captured by the camera of the media device;

performing image processing to identify a plurality of entities in the image; and

determining a respective pronoun corresponding to each respective candidate entity of the plurality of candidate entities;

determining the particular entity by selecting a candidate entity of the plurality of candidate entities having a respective pronoun that matches the identified pronoun.