Generating input alternatives
Exemplary embodiments relate to a system for recovering a conversation between a user and the system when the system is unable to properly respond to a user's input. The system may process the user input and determine an error condition exists. The system may query one or more storage systems to identify candidate text data based on their semantic similarity to the user input. The storage systems may store data related to past frequently entered inputs and/or user-generated inputs. Alternative text data is selected from the candidate text data, and presented to the user for confirmation.
1. A method comprising:
receiving input data corresponding to a user input;
determining first data representing an alternative for the input data based on a similarity of sound between the first data and the user input;
generating first output data proposing the first data to be used as the alternative for the input data;
receiving a response confirming the first data is to be used;
determining first application data associated with the first data; and
generating second output data based on the first application data.
2. The method of claim 1 , wherein the input data comprises input audio data and the method further comprises:
determining the similarity of sound using the input audio data and the first data.
3. The method of claim 1 , further comprising:
performing language processing on the input data to determine results data,
wherein identifying the first data is performed at least partially in response to the results data.
4. The method of claim 3 , wherein the language processing comprises natural language processing and the results data comprises a confidence score.
5. The method of claim 1 , wherein the input data is received from a first device and the method further comprises sending, to the first device, the second output data.
6. The method of claim 1 , further comprising:
identifying storage comprising previous input data represents past inputs made by a plurality of users;
querying the storage using at least a portion of the input data to determine a plurality of candidate input representations; and
identifying the first data based on the plurality of candidate input representations.
7. The method of claim 6 , further comprising:
determining the plurality of candidate input representations based at least in part on a keyword represented in the user input.
8. The method of claim 1 , further comprising:
determining a first list of candidate input representations by processing the input data using a trained model;
determining a second list of candidate input representations by processing the first list of candidate input representations based at least in part on at least one of device type data, second application data corresponding to the input data, or domain data corresponding to the input data; and
selecting the first data from the second list of candidate input representations.
9. The method of claim 1 , further comprising:
querying a storage using at least a portion of the input data to determine a plurality of candidate input representations, the storage storing data representing a mapping between sample input data and system actionable data; and
identifying the first data based on the plurality of candidate input representations.
10. The method of claim 9 , wherein the first data is identified from the plurality of candidate input representations based at least in part on user profile data.
11. A system, comprising:
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive input data corresponding to a user input;
determine first data representing an alternative for the input data based on a similarity of sound between the first data and the user input;
generate first output data proposing the first data should be used as the alternative for the input data;
receive a response confirming the first data is to be used;
determine first application data associated with the first data; and
generate second output data based on the first application data.
12. The system of claim 11 , wherein the input data comprises input audio data and wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine the similarity of sound using the input audio data and the first data.
13. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
performing language processing on the input data to determine results data,
wherein identifying the first data is performed at least partially in response to the results data.
14. The system of claim 13 , wherein the language processing comprises natural language processing and the results data comprises a confidence score.
15. The system of claim 11 , wherein the input data is received from a first device and wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to send, to the first device, the second output data.
16. The system of claim 11 , wherein the input data is associated with a user profile and wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
identify storage comprising previous input data represents past inputs made by a plurality of users;
query the storage using at least a portion of the input data to determine a plurality of candidate input representations; and
identify the first data based on the plurality of candidate input representations.
17. The system of claim 16 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine the plurality of candidate input representations based at least in part on a keyword represented in the user input.
18. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
determine a first list of candidate input representations by processing the input data using a trained model;
determine a second list of candidate input representations by processing the first list of candidate input representations based at least in part on at least one of device type data, second application data corresponding to the input data, or domain data corresponding to the input data; and
select the first data from the second list of candidate input representations.
19. The system of claim 11 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
query a storage using at least a portion of the input data to determine a plurality of candidate input representations, the storage storing data representing a mapping between sample input data and system actionable data; and
identify the first data based on the plurality of candidate input representations.
20. The system of claim 19 , wherein the first data is identified from the plurality of candidate input representations based at least in part on user profile data.