System and method for ranking search results based on usefulness parameter

1. A method of generating a search engine results page (SERP), the method executable at a server, the method comprising:

a) receiving, by the server, a search query from an electronic device associated with a user;

b) responsive to the search query, generating, by the server, a search query result set, the search query result set including at least one general search result and at least one vertical search result;

c) ranking, by the server, based at least in part on a usefulness parameter, the search query result set to obtain a ranked plurality of search results, the usefulness parameter being indicative of an optimal position of the at least one vertical search result in the ranked plurality of search results; and

d) generating, by the server, the SERP, the SERP displaying the ranked plurality of search results with the at least one vertical search result being placed at the optimal position;

wherein the usefulness parameter has been predetermined based on a training set of user data on past user interactions with the at least one vertical search result, by:

i) previously receiving the search query from a test electronic device associated with a first member of a first test user group (TUG);

ii) in response to the receiving the search query, generating and ranking a second search query result set to obtain a second ranked plurality of search results, the second ranked plurality of search results including a mixed ranking of the at least one general search result and the at least one vertical search result, the ranking the second search query result set including: modifying an original rank of the at least one vertical search result to rank the at least one vertical search result randomly;

iii) displaying the second ranked plurality of search results in a previous SERP on the test electronic device associated with the first member of the first TUG, the previous SERP including the at least one vertical search result placed at a first random position;

iv) analyzing user interactions of the first member of the first TUG with respect to the at least one vertical search result on the previous SERP;

v) based at least in part on the user interactions of the first member of the first TUG with respect to the at least one vertical search result at the first random position on the previous SERP, determining a usefulness of the at least one vertical search result relative to the search query; and

vi) generating the usefulness parameter based on the determined usefulness of the at least one vertical search result relative to the search query, the usefulness parameter for determining, in use, the optimal position of the at least one vertical search result.

2. The method of claim 1 , wherein the user interactions of the first member of the first TUG with respect to the at least one vertical search result at the first random position on the previous SERP comprises one or more of: a click-through rate, time spent after click-through, and other click-based data.

3. The method of claim 2 , wherein the first random position represents a lower ranking than the original rank of the at least one vertical search result.

4. The method of claim 2 , wherein the first random position represents a higher ranking than the original rank of the at least one vertical search result.

5. The method of claim 3 , wherein the click-through or the time spent after click-through by the first member of the first TUG on the at least one vertical search result having the lower ranking indicates usefulness of the at least one vertical search result.

6. The method of claim 4 , wherein lack of the click-through or the time spent after click-through by the first member of the first TUG on the at least one vertical search result having the higher ranking indicates non-usefulness of the at least one vertical search result.

7. The method of claim 1 , wherein the ranked plurality of search results have been ranked based at least in part on the usefulness parameter, and a second usefulness parameter, the second usefulness parameter indicating a second optimal position of the at least one general search result in the ranked plurality of search results, the second usefulness parameter having been predetermined based on a second training set of user data on past user interactions with the at least one general search result, by:

i) previously receiving the search query from a second test electronic device associated with a second member of a second TUG;

ii) in response to the receiving the search query, generating and ranking a third search query result set to obtain a third ranked plurality of search results, the third ranked plurality of search results including a second mixed ranking of the at least one general search result and the at least one vertical search result, the ranking the third search query result set including: modifying a second original rank of the at least one general search result to rank the at least one general search result randomly;

iii) displaying the third ranked plurality of search results in a second previous SERP on the second test electronic device associated with the second member of the second TUG, the second previous SERP including the at least one general search result placed at a second random position;

iv) analyzing user interactions of the second member of the second TUG with respect to the at least one general search result on the second previous SERP;

v) based at least in part on the user interactions of the second member of the second TUG with respect to the at least one general search result at the second random position on the second previous SERP, determining a second usefulness of the at least one general search result relative to the search query; and

vi) generating the second usefulness parameter based on the second determined usefulness of the at least one general search result relative to the search query, the second usefulness parameter for determining, in use, the second optimal position of the at least one general search result.

8. The method of claim 1 , wherein the usefulness parameter has been generated using a machine learning algorithm.

9. The method of claim 1 , wherein the at least one vertical search result was ranked randomly by generating a random number as its intent weight.

10. The method of claim 1 , wherein the usefulness parameter determines an intent weight of the at least one vertical search result based on the determined usefulness, thereby determining the optimal position of the at least one vertical search result in the ranked plurality of search results.

11. A server comprising:

a communication interface for communication with an electronic device associated with a user via a communication network;

a memory storage;

a processor operationally connected with the communication interface and the memory storage, the processor configured to store objects, in association with the user, on the memory storage, the processor being further configured to:

receive a search query from an electronic device associated with a user;

responsive to the search query, generate a search query result set, the search query result set including at least one general search result and at least one vertical search result;

rank, based at least in part on a usefulness parameter, the search query result set to obtain a ranked plurality of search results, the usefulness parameter being indicative of an optimal position of the at least one vertical search result in the ranked plurality of search results; and

generate the SERP, the SERP displaying the ranked plurality of search results with the at least one vertical result placed at the optimal position;

wherein the usefulness parameter has been predetermined based on a training set of user data on past user interactions with the at least one vertical search result, by:

i) previously receiving the search query from a test electronic device associated with a first member of a first test user group (TUG);

ii) in response to the receiving the search query, generating and ranking a second search query result set to obtain a second ranked plurality of search results, the second ranked plurality of search results including a mixed ranking of the at least one general search result and the at least one vertical search result, the ranking the second search query result set including: modifying an original rank of the at least one vertical search result to rank the at least one vertical search result randomly;

iii) displaying the second ranked plurality of search results in a previous SERP on the test electronic device associated with the first member of the first TUG, the previous SERP including the at least one vertical search result placed at a first random position;

iv) analyzing user interactions of the first member of the first TUG with respect to the at least one vertical search result on the previous SERP;

v) based at least in part on the user interactions of the first member of the first TUG with respect to the at least one vertical search result at the first random position on the previous SERP, determining a usefulness of the at least one vertical search result relative to the search query; and

vi) generating the usefulness parameter based on the determined usefulness of the at least one vertical search result relative to the search query, the usefulness parameter for determining, in use, the optimal position of the at least one vertical search result.

12. The server of claim 11 , wherein the user interactions of the first member of the first TUG with respect to the at least one vertical search result at the first random position on the previous SERP comprises one or more of: a click-through rate, time spent after click-through, and other click-based data.

13. The server of claim 12 , wherein the first random position represents a lower ranking than the original rank of the at least one vertical search result.

14. The server of claim 12 , wherein the first random position represents a higher ranking than the original rank of the at least one vertical search result.

15. The server of claim 13 , wherein the click-through or the time spent after click-through by the first member of the first TUG on the at least one vertical search result having the lower ranking indicates usefulness of the at least one vertical search result.

16. The server of claim 14 , wherein lack of the click-through or the time spent after click-through by the first member of the first TUG on the at least one vertical search result having the higher ranking indicates non-usefulness of the at least one vertical search result.

17. The server of claim 11 , wherein the processor is further configured to rank the plurality of search results based at least in part on the usefulness parameter and a second usefulness parameter, the second usefulness parameter indicating a second optimal position of the at least one general search result in the ranked plurality of search results, the second usefulness parameter having been predetermined based on a second training set of user data on past user interactions with the at least one general search result, by:

i) previously receiving the search query from a second test electronic device associated with a second member of a second TUG;

ii) in response to the receiving the search query, generating and ranking a third search query result set to obtain a third ranked plurality of search results, the third ranked plurality of search results including a second mixed ranking of the at least one general search result and the at least one vertical search result, the ranking the third search query result set including: modifying a second original rank of the at least one general search result to rank the at least one general search result randomly;

iii) displaying the third ranked plurality of search results in a second previous SERP on the second test electronic device associated with the second member of the second TUG, the second previous SERP including the at least one general search result placed at a second random position;

iv) analyzing user interactions of the second member of the second TUG with respect to the at least one general search result on the second previous SERP;

v) based at least in part on the user interactions of the second member of the second TUG with respect to the at least one general search result at the second random position on the second previous SERP, determining a second usefulness of the at least one general search result relative to the search query; and

vi) generating the second usefulness parameter based on the second determined usefulness of the at least one general search result relative to the search query, the second usefulness parameter for determining, in use, the second optimal position of the at least one general search result.

18. A method of generating a usefulness parameter for ranking search results, the method executable at a server, the method comprising:

a) receiving a search query from a test electronic device associated with a first member of a first test user group (TUG);

b) responsive to the search query, performing a search and generating a test search query result set, the test search query result set including at least one general search result and at least one vertical search result;

c) ranking the test search query result set to obtain a test ranked plurality of search results, the test ranked plurality of search results including a mixed ranking of the at least one general search result and the at least one vertical search result, the ranking the test search query result set including: modifying an original rank of the at least one vertical search result to rank the at least one general search result randomly;

d) generating a test SERP displaying the test ranked plurality of search results, the test SERP including the at least one vertical search result placed at a first random position;

e) displaying the test SERP on the test electronic device to the first member of the first TUG;

f) analyzing user interactions of the first member of the first TUG with respect to the at least one vertical search result on the test SERP;

g) based at least in part on the user interactions of the first member of the first TUG with respect to the at least one vertical search result at the first random position on the test SERP, determining the usefulness of the at least one vertical search result relative to the search query;

h) generating the usefulness parameter based on the determined usefulness of the at least one vertical search result relative to the search query, the usefulness parameter for determining, in use, an optimal position of the at least one vertical search result;

i) storing the usefulness parameter for use in ranking future search results for the search query.