Determining a user-specific approach for disambiguation based on an interaction recommendation machine learning model
In various embodiments, a natural language (NL) application implements functionality that enables users to more effectively access various data storage systems based on NL requests. As described, the operations of the NL application are guided by, at least in part, on one or more templates and/or machine-learning models. Advantageously, the templates and/or machine-learning models provide a flexible framework that may be readily tailored to reduce the amount of time and user effort associated with processing NL requests and to increase the overall accuracy of NL application implementations.
1. A computer-implemented method, comprising:
generating an inquiry based on a first natural language (NL) query received from a user and a first interaction model that associates the first NL query and the user with the inquiry;
generating a clarification based on a second NL query received from the user and a second interaction model that associates the second NL query with the clarification, wherein the second interaction model is generated via a machine learning algorithm that operates on data produced in conjunction with one or more user responses to the inquiry;
generating a disambiguated query based on the second NL query and the clarification, wherein the disambiguated query is written in a domain-specific language (DSL) associated with a data storage system; and
causing the disambiguated query to be applied to the data storage system.
2. The computer-implemented method of claim 1 , wherein generating the disambiguated query comprises:
generating a disambiguated NL query based on the second NL query and the clarification; and
translating the disambiguated NL query to the DSL.
3. The computer-implemented method of claim 1 , further comprising:
re-generating the disambiguated query based on a third NL query received from the user and a third interaction model that associates the third NL query with a disambiguated NL query, wherein the third interaction model is generated via the machine learning algorithm trained on data produced in conjunction with one or more user responses to the clarification; and
causing the disambiguated query to be re-applied to the data storage system.
4. The computer-implemented method of claim 1 , wherein the inquiry includes a plurality of phrases that are ordered based on estimated probabilities of accurately disambiguating the first NL query.
5. The computer-implemented method of claim 1 , further comprising causing the inquiry to be provided to the user by at least one of causing an audio device to output the inquiry or causing a display device to display the inquiry.
6. The computer-implemented method of claim 1 , further comprising generating a domain-specific language (DSL) query based on the first NL query, the one or more user responses, and a different DSL that is associated with a different data storage system.
7. The computer-implemented method of claim 1 , further comprising generating a domain-specific language (DSL) query expressed in a pipelined search language based on the first NL query and the one or more user responses.
8. The computer-implemented method of claim 1 , further comprising:
generating a domain-specific language (DSL) query expressed in a pipelined search language based on the first NL query and the one or more user responses; and
applying the DSL query to the data storage system to generate a search result, wherein the data storage system stores data as a plurality of time-indexed events including respective segments of raw machine data.
9. The computer-implemented method of claim 1 , wherein the one or more user responses indicate how accurately the inquiry disambiguates the first NL query.
10. A computing device, comprising
a memory; and
one or more processors that execute one or more instructions stored in the memory to:
generate an inquiry based on a first natural language (NL) query received from a user and a first interaction model that associates the first NL query and the user with the inquiry;
generate a clarification based on a second NL query received from the user and a second interaction model that associates the second NL query with the clarification, wherein the second interaction model is generated via a machine learning algorithm that operates on data produced in conjunction with one or more user responses to the inquiry;
generate a disambiguated query based on the second NL query and the clarification, wherein the disambiguated query is written in a domain-specific language (DSL) associated with a data storage system; and
cause the disambiguated query to be applied to the data storage system.
11. The computing device of claim 10 , wherein generating the disambiguated query comprises:
generating a disambiguated NL query based on the second NL query and the clarification; and
translating the disambiguated NL query to the DSL.
12. The computing device of claim 10 , wherein the instructions that, when executed by a processor, further cause the processor to perform the steps of:
re-generating the disambiguated query based on a third NL query received from the user and a third interaction model that associates the third NL query with a disambiguated NL query, wherein the third interaction model is generated via the machine learning algorithm trained on data produced in conjunction with one or more user responses to the clarification; and
causing the disambiguated query to be re-applied to the data storage system.
13. The computing device of claim 10 , wherein the inquiry includes a plurality of phrases that are ordered based on estimated probabilities of accurately disambiguating the first NL query.
14. The computing device of claim 10 , further comprising causing the inquiry to be provided to the user by at least one of causing an audio device to output the inquiry or causing a display device to display the inquiry.
15. The computing device of claim 10 , wherein the instructions that, when executed by a processor, further cause the processor to perform the step of generating a domain-specific language (DSL) query based on the first NL query, the one or more user responses, and a different DSL that is associated with a different data storage system.
16. The computing device of claim 10 , wherein the instructions that, when executed by a processor, further cause the processor to perform the step of generating a domain-specific language (DSL) query expressed in a pipelined search language based on the first NL query and the one or more user responses.
17. The computing device of claim 10 , wherein the instructions that, when executed by a processor, further cause the processor to perform the steps of:
generating a domain-specific language (DSL) query expressed in a pipelined search language based on the first NL query and the one or more user responses; and
applying the DSL query to the data storage system to generate a search result, wherein the data storage system stores data as a plurality of time-indexed events including respective segments of raw machine data.
18. The computing device of claim 10 , wherein the one or more user responses indicate how accurately the inquiry disambiguates the first NL query.
19. One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to perform the steps of:
generating an inquiry based on a first natural language (NL) query received from a user and a first interaction model that associates the first NL query and the user with the inquiry;
generating a clarification based on a second NL query received from the user and a second interaction model that associates the second NL query with the clarification, wherein the second interaction model is generated via a machine learning algorithm that operates on data produced in conjunction with one or more user responses to the inquiry;
generating a disambiguated query based on the second NL query and the clarification, wherein the disambiguated query is written in a domain-specific language (DSL) associated with a data storage system; and
causing the disambiguated query to be applied to the data storage system.
20. The one or more non-transitory computer-readable storage media of claim 19 , wherein generating the disambiguated query comprises:
generating a disambiguated NL query based on the second NL query and the clarification; and
translating the disambiguated NL query to the DSL.