Systems and methods for processing subjective queries
Methods and systems for processing subjective queries are described. A query is received from a user. The method involves determining whether the query is subjective. In response to determining that the query is subjective, a plurality of people qualified to answer the query are identified. Moreover, a subset of the plurality of people who are available to answer the query are identified, and the query is transmitted to the subset of people available to answer the query. The received responses to the transmitted query from each of the people in the subset are then generated for display.
1 . A method comprising:
receiving a query associated with a user account;
extracting keywords included in the query;
training a model to identify queries indicative of subjective queries, wherein training the model comprises:
querying a corpus of information with a plurality of training queries;
determining whether objective results are found in the corpus of information for each of the plurality of training queries; and
classifying each of the plurality of training queries for which the objective results are not found in the corpus of information as indicative of the subjective queries;
determining, using the trained model, whether the query is subjective based at least in part on the extracted keywords;
based at least in part on determining the query is subjective, retrieving social media activity associated with one or more accounts associated with the user account based on a social relationship with the user account;
determining whether the extracted keywords in the query relate to the social media activity of the one or more accounts associated with the user account;
based at least in part on determining the extracted words in the query relate to the social media activity of the one or more accounts associated with the user account, identifying, a subset of accounts from the one or more accounts as qualified to answer the query;
transmitting the query to the subset of accounts; and
providing for output at least one response from the subset of accounts associated with a response to the transmitted query.
2 . The method of claim 1 , wherein the query is a first query received at a first time, the method further comprises:
receiving a second query at a second time;
extracting keywords included in the second query;
determining, using the trained model, that the second query is not subjective;
searching the corpus of information for an answer to the second query; and
providing for output the answer to the second query.
3 . The method of claim 1 , further comprising:
determining the extracted words in the query do not relate to the social media activity of the one or more accounts associated with the user account;
retrieving geolocation information from the one or more accounts associated with the user account based on the social relationship; and
identifying from the one or more accounts associated with the user account based on the social relationship the subset of accounts as qualified to answer the query based on the subset of accounts geolocation information relating to the keywords included in the query.
4 . The method of claim 1 , wherein identifying, the one or more accounts as qualified to answer the query, further comprises:
determining the social media activity was within a predetermined period of time preceding the receipt of the query.
5 . The method of claim 1 , further comprising:
retrieving availability information from the subset of accounts identified as qualified to answer the query; and
in response to determining at least one of the subset of accounts is available, transmitting the query to the at least one of the subset of accounts.
6 . The method of claim 5 , wherein retrieving the availability information further comprises:
determining capability information associated with a user device of the subset of accounts; and
in response to determining an account from the subset of accounts does not have access to a user device associated with the account from the subset of accounts, excluding the account from the subset of accounts that is available.
7 . The method of claim 1 , further comprising:
receiving, a plurality of responses from the subset of accounts;
generating, a summary of the plurality of received response into a single response; and
generating, for output, a generated summary of the plurality of responses in the single response.
8 . The method of claim 1 , further comprises:
comparing, the extracted keywords to a database storing a list of keywords indicative of a subjective query; and
based at least in part on identifying a match, determining the query is subjective.
9 . The method of claim 1 , wherein transmitting the query to the subset of accounts further comprises:
determining a location or schedule information of the subset of accounts identified as qualified to answer the query; and
determining, an appropriate delivery method for transmitting the query based at least in part on the location or the schedule of the subset of accounts, wherein the appropriate delivery method is either transmitting the query in textual or audible form.
10 . The method of claim 1 , further comprising:
determining a nature of the received query; and
based at least in part on determining the nature of the received query is one in which an image would aid the subset of accounts responses, transmitting the image with the query to the subset of accounts.
11 . A system comprising:
input/output circuitry configured to:
receive a query associated with a user account;
control circuitry configured to:
extract keywords included in the query;
train a model to identify queries associated with subjective queries, wherein training the model comprises:
query a corpus of information with a plurality of training queries;
determine whether objective results are found in the corpus of information for each of the plurality of training queries; and
classify each of the plurality of training queries for which the objective results are not found in the corpus of information as indicative of the subjective queries;
determine, using the trained model, whether the query is subjective based at least in part on the extracted keywords;
based at least in part on determining the query is subjective, retrieve social media activity associated with one or more accounts associated with the user account based on a social relationship with the user account;
determine whether the extracted keywords in the query relate to the social media activity of the one or more accounts associated with the user account;
based at least in part on determining the extracted words in the query relate to the social media activity of the one or more accounts associated with the user account, identify, a subset of accounts from the one or more accounts as qualified to answer the query; and
transmit the query to the subset of accounts;
wherein the input/output circuitry is further configured to:
provide for output at least one response from the subset of accounts associated with a response to the transmitted query.
12 . The system of claim 11 , wherein the query is a first query received at a first time, the input/output circuitry is further configured to:
receive a second query at a second time;
wherein the control circuitry is further configured to:
extract keywords included in the second query;
determine, using the trained model, that the query is not subjective;
search the corpus of information for an answer to the query; and
wherein the input/output circuitry is further configured to:
provide for output the answer to the second query.
13 . The system of claim 11 , wherein the control circuitry is further configured to:
determine the extracted words in the query do not relate to the social media activity of the one or more accounts associated with the user account;
retrieve geolocation information from the one or more accounts associated with the user account based on the social relationship; and
identify from the one or more accounts associated with the user account based on the social relationship the subset of accounts as qualified to answer the query based on the subset of accounts geolocation information relating to the keywords included in the query.
14 . The system of claim 11 , wherein the control circuitry is configured to identify, the one or more accounts as qualified to answer the query, is further configured to:
determine the social media activity was within a predetermined period of time preceding the receipt of the query.
15 . The system of claim 11 ,
wherein the control circuitry is further configured to:
retrieve availability information from the subset of accounts identified as qualified to answer the query; and
wherein the input/output circuitry is further configured to:
in response to determining at least one of the subset of accounts is available, transmit the query to the at least one of the subset of accounts.
16 . The system of claim 15 , wherein the control circuitry is configured to retrieve the availability information, the control circuitry is further configured to:
determine capability information associated with a user device of the subset of accounts; and
in response to determining an account from the subset of accounts does not have access to a user device associated with the account from the subset of accounts, exclude the account from the subset of accounts that is available.
17 . The system of claim 11 ,
wherein the control circuitry is further configured to:
receive, a plurality of responses from the subset of accounts;
generate, a summary of the plurality of received response into a single response; and
the input/output circuitry is further configured to:
generate, for output, a generated summary of the plurality of responses in the single response.
18 . The system of claim 11 , wherein the control circuitry is further configured to:
compare, the extracted keywords to a database storing a list of keywords indicative of a subjective query; and
based at least in part on identifying a match, determine the query is subjective.
19 . The system of claim 11 , wherein the control circuitry is configured to transmit the query to the subset of accounts is further configured to:
determine a location or schedule information of the subset of accounts identified as qualified to answer the query; and
determine, an appropriate delivery method for transmitting the query based at least in part on the location or the schedule of the subset of accounts, wherein the appropriate delivery method is either transmitting the query in textual or audible form.
20 . The system of claim 11 , wherein the control circuitry is further configured to:
determine a nature of the received query; and
based at least in part on determining the nature of the received query is one in which an image would aid the subset of accounts responses, transmit the image with the query to the subset of accounts.