Systems and methods for searching for a media asset
Systems and methods for searching for a media asset are described. In some aspects, the system includes control circuitry that receives a first search query from a user. The control circuitry identifies media assets related to the first search query from a content database. The control circuitry receives a second search query following the first search query. The control circuitry determines whether a media asset from the media assets is related to the second search query. In response to determining that less than a threshold number of media assets from the media assets are related to the second search query, the control circuitry transmits an instruction requesting the user to repeat the second search query. The control circuitry receives a third search query related to the first search query. The control circuitry determines a media asset from the media assets that is related to the third search query.
1. A method for proactively predicting errors in automatic speech recognition system when searching for a media asset by storing contexts of a user's earlier queries, comprising:
receiving, using control circuitry, a first search query from a user;
identifying, from a content database, a plurality of media assets related to the first search query;
receiving, using the control circuitry, a second search query following the first search query;
detecting whether an error exists in the receipt of the second search query by:
determining, using the control circuitry, a number of media assets that are related to the second search query from the plurality of media assets related to the first search query;
comparing the number of media assets that are related to the second search query to a threshold number; and
in response to determining that the number of media assets that are related to the second search query is less than the threshold number, detecting an error;
in response to detecting the error, transmitting, using the control circuitry, an instruction requesting the user to repeat the second search query;
receiving, using the control circuitry, a third search query related to the first search query; and
determining, using the control circuitry, a media asset from the plurality of media assets related to the third search query.
2. The method of claim 1 , wherein determining whether a media asset from the plurality of media assets is related to the second search query comprises determining whether a context identifier for the second search query exists in a mapping of context identifiers including a first context identifier for the first search query.
3. The method of claim 1 , wherein the third search query being related to the first search query comprises a first context identifier for the first search query and a second context identifier for the third search query being connected in a mapping of context identifiers.
4. The method of claim 3 , wherein the mapping of context identifiers that connects the first context identifier with the second context identifier is part of a knowledge graph.
5. The method of claim 3 , wherein the mapping of context identifiers that connects the first context identifier and the third context identifier is stored in a user profile of the user.
6. The method of claim 3 , wherein the first context identifier and the second context identifier are selected from at least one of a genre, an actor, and a start time of a media asset.
7. The method of claim 3 , wherein the first context identifier is substantially similar to the first search query and the second context identifier is substantially similar to the third search query.
8. The method of claim 1 , wherein the instruction requesting the user to repeat the second search query includes an error message indicating that less than a threshold number of media assets relate to both the first search query and the second search query.
9. The method of claim 1 , wherein the instruction requesting the user to repeat the second search query includes a media asset from the content database relating to the second search query but not relating to the first search query.
10. The method of claim 1 , wherein at least one of the first search query, the second search query, and the third search query is received from an automated speech to text system.
11. A system for proactively predicting errors in automatic speech recognition system when searching for a media asset by storing contexts of a user's earlier queries, comprising:
a content database;
control circuitry configured to:
receive a first search query from a user;
identify, from the content database, a plurality of media assets related to the first search query;
receive a second search query following the first search query;
detect whether an error exists in the receipt of the second search query by:
determining, using the control circuitry, a number of media assets that are related to the second search query from the plurality of media assets related to the first search query;
comparing the number of media assets that are related to the second search query to a threshold number; and
in response to determining that the number of media assets that are related to the second search query is less than the threshold number, detecting an error;
in response to detecting the error, transmit an instruction requesting the user to repeat the second search query;
receive a third search query related to the first search query; and
determine a media asset from the plurality of media assets related to the third search query.
12. The system of claim 11 , wherein control circuitry configured to determine whether a media asset from the plurality of media assets is related to the second search query comprises control circuitry configured to determine whether a context identifier for the second search query exists in a mapping of context identifiers including a first context identifier for the first search query.
13. The system of claim 11 , wherein the third search query being related to the first search query comprises a first context identifier for the first search query and a second context identifier for the third search query being connected in a mapping of context identifiers.
14. The system of claim 13 , wherein the mapping of context identifiers that connects the first context identifier with the second context identifier is part of a knowledge graph.
15. The system of claim 13 , wherein the mapping of context identifiers that connects the first context identifier and the third context identifier is stored in a user profile of the user.
16. The system of claim 13 , wherein the first context identifier and the second context identifier are selected from at least one of a genre, an actor, and a start time of a media asset.
17. The system of claim 13 , wherein the first context identifier is substantially similar to the first search query and the second context identifier is substantially similar to the third search query.
18. The system of claim 11 , wherein the instruction requesting the user to repeat the second search query includes an error message indicating that less than a threshold number of media assets relate to both the first search query and the second search query.
19. The system of claim 11 , wherein the instruction requesting the user to repeat the second search query includes a media asset from the content database relating to the second search query but not relating to the first search query.
20. The system of claim 11 , wherein at least one of the first search query, the second search query, and the third search query is received from an automated speech to text system.