Database search query enhancer

1. A search query enhancer comprising:

a memory; and

a hardware processor communicatively coupled to the memory, the hardware processor configured to:

receive a query from a device, the query comprising first search parameters;

retrieve, from a database and based on the first search parameters, at least one of a plurality of previously issued queries, a plurality of responses generated for the plurality of previously issued queries, and a plurality of selections made from the plurality of responses;

apply a machine learning algorithm based at least on the plurality of selections to determine second search parameters;

use the second search parameters to modify the query to form an enhanced query;

communicate the enhanced query to a plurality of response systems;

receive, from the plurality of response systems, a plurality of responses to the enhanced query;

determine, for each response of the plurality of responses, a likelihood that the response will be selected and whether that likelihood exceeds a set threshold;

construct, based on the plurality of responses to the enhanced query, an enhanced response to the query, wherein the enhanced response comprises a ranking of each response determined to exceed the set threshold, the ranking being based on the determined likelihoods; and

communicate the enhanced response to the device for selection of a response from the plurality of responses to the enhanced query.

2. The search query enhancer of claim 1 , wherein the processor is further configured to:

determine that the query was initiated by a user, the plurality of previously issued queries retrieved from the database comprise a plurality of queries previously issued by the user, the plurality of responses generated for the plurality of previously issued queries comprises a plurality of responses communicated to the user, or the plurality of selections made from the plurality of responses comprises a plurality of selections made by the user; and

determine, based on at least one of the plurality of queries previously issued by the user, the plurality of responses communicated to the user, and the plurality of selections made by the user and by applying the machine learning algorithm, a preference of the user, the second search parameters comprise the preference.

3. The search query enhancer of claim 1 , wherein the processor is further configured to:

determine that the query was initiated by a user, the plurality of previously issued queries retrieved from the database comprise a plurality of queries previously issued by the user, the plurality of responses generated for the plurality of previously issued queries comprises a plurality of responses communicated to the user, or the plurality of selections made from the plurality of responses comprises a plurality of selections made by the user; and

for each response of the plurality of responses to the enhanced query, determine, based on the plurality of queries previously issued by the user, the plurality of responses communicated to the user, or the plurality of selections made by the user, a likelihood that the user will select that response, wherein constructing the enhanced response comprises adding, to the enhanced response, a response of the plurality of responses to the enhanced query based on the determined likelihood that the user will select the response of the plurality of responses to the enhanced query.

4. The search query enhancer of claim 1 , wherein the processor is further configured to:

determine that the query was initiated by a category of user, the plurality of previously issued queries retrieved from the database comprise a plurality of queries previously issued by the category of user, the plurality of responses generated for the plurality of previously issued queries comprises a plurality of responses communicated to the category of user, or the plurality of selections made from the plurality of responses comprises a plurality of selections made by the category of user; and

determine, based on at least one of the plurality of queries previously issued by the category user, the plurality of responses communicated to the category of user, and the plurality of selections made by the category of user and by applying the machine learning algorithm, a preference of the category of user, the second search parameters comprise the preference.

5. The search query enhancer of claim 1 , wherein:

determining the second search parameters comprises determining a likelihood that a response from a first response system of the plurality of response systems will be selected; and

forming the enhanced query comprises:

if the likelihood is below a threshold, adding an instruction that the first response system form the response by querying a database of responses using the first search parameters; and

if the likelihood is above the threshold, adding an instruction that the first response system form the response using the second search parameters.

6. The search query enhancer of claim 5 , wherein the first response system is configured to:

receive the enhanced query;

if the determined likelihood is below the threshold, construct the response by adding to the response a result of querying the database of responses using the first search parameters; and

if the determined likelihood is above the threshold, construct the response by adding to the response a result of evaluating the second search parameters.

7. The search query enhancer of claim 1 , the hardware processor further configured to:

after receiving the plurality of responses, communicate, to a first response system of the plurality of response systems, a message indicating a factor that affects a likelihood that a response of the plurality of responses will be selected, the response of the plurality of responses is received from the first response system; and

receive, from the first response system, a second response based on the message, the second response incorporates a change based on the indicated factor, wherein the enhanced response is constructed further based on the second response from the first response system.

8. The search query enhancer of claim 1 , wherein:

determining the second search parameters comprises determining a likelihood that the query was automatically and programmatically generated; and

the enhanced query comprises the determined likelihood.

9. The search query enhancer of claim 1 , the hardware processor further configured to:

retrieve, from the database and based on the plurality of responses, a plurality of previously selected responses; and

apply a machine learning algorithm on the plurality of previously selected responses to determine a response parameter for each response of the plurality of responses, wherein the enhanced response comprises the response parameter for each response of the plurality of responses.

10. The search query enhancer of claim 1 , the hardware processor further configured to:

add the query to the database;

determine that a first response of the plurality of response was selected; and

add the first response to the database.

11. A method comprising:

receiving, by a hardware processor, a query from a device, the query comprising first search parameters;

retrieving, by the processor, from a database and based on the first search parameters, at least one of a plurality of previously issued queries, a plurality of responses generated for the plurality of previously issued queries, and a plurality of selections made from the plurality of responses;

applying, by the processor, a machine learning algorithm based at least on the plurality of selections to determine second search parameters;

using, by the processor, the second search parameters to modify the query to form an enhanced query;

communicating, by the processor, the enhanced query to a plurality of response systems;

receiving, from the plurality of response systems, a plurality of responses to the enhanced query;

determining, for each response of the plurality of responses, a likelihood that the response will be selected and whether that likelihood exceeds a set threshold;

constructing, based on the plurality of responses to the enhanced query, an enhanced response to the query, wherein the enhanced response comprises a ranking of each response determined to exceed the set threshold, the ranking being based on the determined likelihoods; and

communicating the enhanced response to the device for selection of a response from the plurality of responses to the enhanced query.

12. The method of claim 11 , further comprising:

determining, by the processor, that the query was initiated by a user, the plurality of previously issued queries retrieved from the database comprise a plurality of queries previously issued by the user, the plurality of responses generated for the plurality of previously issued queries comprises a plurality of responses communicated to the user, or the plurality of selections made from the plurality of responses comprises a plurality of selections made by the user; and

determining, by the processor, based on at least one of the plurality of queries previously issued by the user, the plurality of responses communicated to the user, and the plurality of selections made by the user and by applying the machine learning algorithm, a preference of the user, the second search parameters comprise the preference.

13. The method of claim 11 , further comprising:

determining, by the processor, that the query was initiated by a user, the plurality of previously issued queries retrieved from the database comprise a plurality of queries previously issued by the user, the plurality of responses generated for the plurality of previously issued queries comprises a plurality of responses communicated to the user, or the plurality of selections made from the plurality of responses comprises a plurality of selections made by the user; and

for each response of the plurality of responses to the enhanced query, determine, by the processor, based on the plurality of queries previously issued by the user, the plurality of responses communicated to the user, or the plurality of selections made by the user, a likelihood that the user will select that response, wherein constructing the enhanced response comprises adding, to the enhanced response, a response of the plurality of responses to the enhanced query based on the determined likelihood that the user will select the response of the plurality of responses to the enhanced query.

14. The method of claim 11 , wherein:

determining the second search parameters comprises determining a likelihood that a response from a first response system of the plurality of response systems will be selected; and

forming the enhanced query comprises:

if the likelihood is below a threshold, adding an instruction that the first response system form the response by querying a database of responses using the first search parameters; and

if the likelihood is above the threshold, adding an instruction that the first response system form the response using the second search parameters.

15. The method of claim 11 , further comprising:

after receiving the plurality of responses, communicating, to a first response system of the plurality of response systems, a message indicating a factor that affects a likelihood that a response of the plurality of responses will be selected, the response of the plurality of responses is received from the first response system; and

receiving, from the first response system, a second response based on the message, the second response incorporates a change based on the indicated factor, wherein the enhanced response is constructed further based on the second response from the first response system.