Combining parameters of multiple search queries that share a line of inquiry
AssigneeGoogle Inc.
InventorsMatthew Sharifi, Victor Carbune
Life of this patent
Estimating the term…
Abstract
Methods, systems, and computer readable media related to generating a combined search query based on search parameters of a current search query of a user and search parameters of one or more previously submitted search quer(ies) of the user that are determined to be of the same line of inquiry as the current search query. Two or more search queries may be determined to share a line of inquiry when it is determined that they are within a threshold level of semantic similarity to one another. Once a shared line of inquiry has been identified and a combined search query generated, users may interact with the search parameters and/or the search results to update the search parameters of the combined search query.
Claims20
A method implemented using one or more processors, comprising:
- obtaining data indicative of free form natural language input provided by a user to an input device associated with the user, the data including a first virtual assistant query;
- comparing the first virtual assistant query to a second virtual assistant query, wherein the comparing includes determining a distance in latent space between a first embedding generated from the first virtual assistant query and a second embedding generated from the second virtual assistant query;
- based on the comparing, determining that the first virtual assistant query and the second virtual assistant query relate to a shared line of inquiry;
- based on the determining, formulating a combined virtual assistant query to include at least one search parameter from each of the first virtual assistant query and the second virtual assistant query;
- submitting the combined virtual assistant query to one or more virtual assistants;
- and
- causing content responsive to the combined virtual assistant query to be provided at an output device associated with the user.
A system comprising one or more processors and memory storing instructions that, in response to execution by the one or more processors, cause the one or more processors to:
- obtain data indicative of free form natural language input provided by a user to an input device associated with the user, the data including a first virtual assistant query;
- compare the first virtual assistant query to a second virtual assistant query, wherein the comparing includes determining a distance in latent space between a first embedding generated from the first virtual assistant query and a second embedding generated from the second virtual assistant query;
- based on the comparison, determine that the first virtual assistant query and the second virtual assistant query relate to a shared line of inquiry;
- based on the determination, formulate a combined virtual assistant query to include at least one search parameter from each of the first virtual assistant query and the second virtual assistant query;
- submit the combined virtual assistant query to one or more virtual assistants;
- and
- cause content responsive to the combined virtual assistant query to be provided at an output device associated with the user.
At least one non-transitory computer-readable medium comprising instructions that, in response to execution by one or more processors, cause the one or more processors to:
- obtain data indicative of free form natural language input provided by a user to an input device associated with the user, the data including a first virtual assistant query;
- compare the first virtual assistant query to a second virtual assistant query, wherein the comparing includes determining a distance in latent space between a first embedding generated from the first virtual assistant query and a second embedding generated from the second virtual assistant query;
- based on the comparison, determine that the first virtual assistant query and the second virtual assistant query relate to a shared line of inquiry;
- based on the determination, formulate a combined virtual assistant query to include at least one search parameter from each of the first virtual assistant query and the second virtual assistant query;
- submit the combined virtual assistant query to one or more virtual assistants;
- and
- cause content responsive to the combined virtual assistant query to be provided at an output device associated with the user.
Dependencies are inferred from the claim text.